jonahdvt commited on
Commit
a2d778f
·
verified ·
1 Parent(s): f3ea033

Upload LoRA adapter for Qwen2.5-7B SSML conversion

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. README.md +78 -0
  3. adapter_config.json +39 -0
  4. adapter_model.safetensors +3 -0
  5. added_tokens.json +24 -0
  6. bigscience_T0_3B_ssml/added_tokens.json +105 -0
  7. bigscience_T0_3B_ssml/checkpoint-12/added_tokens.json +105 -0
  8. bigscience_T0_3B_ssml/checkpoint-12/config.json +32 -0
  9. bigscience_T0_3B_ssml/checkpoint-12/generation_config.json +7 -0
  10. bigscience_T0_3B_ssml/checkpoint-12/model-00001-of-00003.safetensors +3 -0
  11. bigscience_T0_3B_ssml/checkpoint-12/model-00002-of-00003.safetensors +3 -0
  12. bigscience_T0_3B_ssml/checkpoint-12/model-00003-of-00003.safetensors +3 -0
  13. bigscience_T0_3B_ssml/checkpoint-12/model.safetensors.index.json +565 -0
  14. bigscience_T0_3B_ssml/checkpoint-12/optimizer.pt +3 -0
  15. bigscience_T0_3B_ssml/checkpoint-12/rng_state.pth +3 -0
  16. bigscience_T0_3B_ssml/checkpoint-12/scaler.pt +3 -0
  17. bigscience_T0_3B_ssml/checkpoint-12/scheduler.pt +3 -0
  18. bigscience_T0_3B_ssml/checkpoint-12/special_tokens_map.json +125 -0
  19. bigscience_T0_3B_ssml/checkpoint-12/spiece.model +3 -0
  20. bigscience_T0_3B_ssml/checkpoint-12/tokenizer_config.json +965 -0
  21. bigscience_T0_3B_ssml/checkpoint-12/trainer_state.json +41 -0
  22. bigscience_T0_3B_ssml/checkpoint-12/training_args.bin +3 -0
  23. bigscience_T0_3B_ssml/config.json +32 -0
  24. bigscience_T0_3B_ssml/generation_config.json +7 -0
  25. bigscience_T0_3B_ssml/model-00001-of-00003.safetensors +3 -0
  26. bigscience_T0_3B_ssml/model-00002-of-00003.safetensors +3 -0
  27. bigscience_T0_3B_ssml/model-00003-of-00003.safetensors +3 -0
  28. bigscience_T0_3B_ssml/model.safetensors.index.json +565 -0
  29. bigscience_T0_3B_ssml/special_tokens_map.json +125 -0
  30. bigscience_T0_3B_ssml/spiece.model +3 -0
  31. bigscience_T0_3B_ssml/tokenizer_config.json +965 -0
  32. bigscience_T0_3B_ssml/training_args.bin +3 -0
  33. chat_template.jinja +54 -0
  34. checkpoint-735/README.md +202 -0
  35. checkpoint-735/adapter_config.json +39 -0
  36. checkpoint-735/adapter_model.safetensors +3 -0
  37. checkpoint-735/added_tokens.json +24 -0
  38. checkpoint-735/chat_template.jinja +54 -0
  39. checkpoint-735/merges.txt +0 -0
  40. checkpoint-735/optimizer.pt +3 -0
  41. checkpoint-735/rng_state.pth +3 -0
  42. checkpoint-735/scheduler.pt +3 -0
  43. checkpoint-735/special_tokens_map.json +31 -0
  44. checkpoint-735/tokenizer.json +3 -0
  45. checkpoint-735/tokenizer_config.json +207 -0
  46. checkpoint-735/trainer_state.json +286 -0
  47. checkpoint-735/training_args.bin +3 -0
  48. checkpoint-735/vocab.json +0 -0
  49. facebook_bart-base_ssml/added_tokens.json +6 -0
  50. facebook_bart-base_ssml/checkpoint-120/added_tokens.json +6 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-735/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Qwen/Qwen2.5-7B
4
+ library_name: peft
5
+ tags:
6
+ - text-to-speech
7
+ - ssml
8
+ - qwen2.5
9
+ - lora
10
+ - peft
11
+ language:
12
+ - en
13
+ - fr
14
+ pipeline_tag: text-generation
15
+ ---
16
+
17
+ # Qwen2.5-7B SSML LoRA Adapter
18
+
19
+ This is a LoRA (Low-Rank Adaptation) fine-tuned version of Qwen2.5-7B for converting plain text to SSML (Speech Synthesis Markup Language) with appropriate pause predictions.
20
+
21
+ ## Model Details
22
+
23
+ - **Base Model**: Qwen/Qwen2.5-7B
24
+ - **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
25
+ - **Task**: Text-to-SSML conversion with pause prediction
26
+ - **Languages**: English, French (and others supported by base model)
27
+
28
+ ## Usage
29
+
30
+ ```python
31
+ import torch
32
+ from transformers import AutoTokenizer, AutoModelForCausalLM
33
+ from peft import PeftModel
34
+
35
+ # Load base model and tokenizer
36
+ base_model = AutoModelForCausalLM.from_pretrained(
37
+ "Qwen/Qwen2.5-7B",
38
+ torch_dtype=torch.bfloat16,
39
+ device_map="auto"
40
+ )
41
+ tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B")
42
+
43
+ # Load LoRA adapter
44
+ model = PeftModel.from_pretrained(base_model, "jonahdvt/qwen-ssml-lora")
45
+
46
+ # Prepare input
47
+ instruction = "Convert text to SSML with pauses:"
48
+ text = "Hello, how are you today? I hope everything is going well."
49
+ formatted_input = f"### Task:\n{instruction}\n\n### Text:\n{text}\n\n### SSML:\n"
50
+
51
+ # Generate
52
+ inputs = tokenizer(formatted_input, return_tensors="pt").to(model.device)
53
+ with torch.no_grad():
54
+ outputs = model.generate(
55
+ **inputs,
56
+ max_new_tokens=256,
57
+ temperature=0.7,
58
+ do_sample=True,
59
+ pad_token_id=tokenizer.eos_token_id
60
+ )
61
+
62
+ response = tokenizer.decode(outputs[0], skip_special_tokens=True)
63
+ ssml_output = response.split("### SSML:\n")[-1]
64
+ print(ssml_output)
65
+ ```
66
+
67
+ ## Training Details
68
+
69
+ - **LoRA Rank**: 8
70
+ - **LoRA Alpha**: 16
71
+ - **Target Modules**: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
72
+ - **Training Epochs**: 5
73
+ - **Batch Size**: 1 (with gradient accumulation)
74
+ - **Learning Rate**: 3e-4
75
+
76
+ ## License
77
+
78
+ This model is released under the Apache 2.0 license, same as the base Qwen2.5-7B model.
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "o_proj",
29
+ "down_proj",
30
+ "q_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7236ab3287bb82ebd8c852fa1f4bd67cfe70b56c43a70ad48ba6cf966835560
3
+ size 80792096
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
bigscience_T0_3B_ssml/added_tokens.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</prosody>": 32101,
3
+ "<break/>": 32102,
4
+ "<extra_id_0>": 32099,
5
+ "<extra_id_10>": 32089,
6
+ "<extra_id_11>": 32088,
7
+ "<extra_id_12>": 32087,
8
+ "<extra_id_13>": 32086,
9
+ "<extra_id_14>": 32085,
10
+ "<extra_id_15>": 32084,
11
+ "<extra_id_16>": 32083,
12
+ "<extra_id_17>": 32082,
13
+ "<extra_id_18>": 32081,
14
+ "<extra_id_19>": 32080,
15
+ "<extra_id_1>": 32098,
16
+ "<extra_id_20>": 32079,
17
+ "<extra_id_21>": 32078,
18
+ "<extra_id_22>": 32077,
19
+ "<extra_id_23>": 32076,
20
+ "<extra_id_24>": 32075,
21
+ "<extra_id_25>": 32074,
22
+ "<extra_id_26>": 32073,
23
+ "<extra_id_27>": 32072,
24
+ "<extra_id_28>": 32071,
25
+ "<extra_id_29>": 32070,
26
+ "<extra_id_2>": 32097,
27
+ "<extra_id_30>": 32069,
28
+ "<extra_id_31>": 32068,
29
+ "<extra_id_32>": 32067,
30
+ "<extra_id_33>": 32066,
31
+ "<extra_id_34>": 32065,
32
+ "<extra_id_35>": 32064,
33
+ "<extra_id_36>": 32063,
34
+ "<extra_id_37>": 32062,
35
+ "<extra_id_38>": 32061,
36
+ "<extra_id_39>": 32060,
37
+ "<extra_id_3>": 32096,
38
+ "<extra_id_40>": 32059,
39
+ "<extra_id_41>": 32058,
40
+ "<extra_id_42>": 32057,
41
+ "<extra_id_43>": 32056,
42
+ "<extra_id_44>": 32055,
43
+ "<extra_id_45>": 32054,
44
+ "<extra_id_46>": 32053,
45
+ "<extra_id_47>": 32052,
46
+ "<extra_id_48>": 32051,
47
+ "<extra_id_49>": 32050,
48
+ "<extra_id_4>": 32095,
49
+ "<extra_id_50>": 32049,
50
+ "<extra_id_51>": 32048,
51
+ "<extra_id_52>": 32047,
52
+ "<extra_id_53>": 32046,
53
+ "<extra_id_54>": 32045,
54
+ "<extra_id_55>": 32044,
55
+ "<extra_id_56>": 32043,
56
+ "<extra_id_57>": 32042,
57
+ "<extra_id_58>": 32041,
58
+ "<extra_id_59>": 32040,
59
+ "<extra_id_5>": 32094,
60
+ "<extra_id_60>": 32039,
61
+ "<extra_id_61>": 32038,
62
+ "<extra_id_62>": 32037,
63
+ "<extra_id_63>": 32036,
64
+ "<extra_id_64>": 32035,
65
+ "<extra_id_65>": 32034,
66
+ "<extra_id_66>": 32033,
67
+ "<extra_id_67>": 32032,
68
+ "<extra_id_68>": 32031,
69
+ "<extra_id_69>": 32030,
70
+ "<extra_id_6>": 32093,
71
+ "<extra_id_70>": 32029,
72
+ "<extra_id_71>": 32028,
73
+ "<extra_id_72>": 32027,
74
+ "<extra_id_73>": 32026,
75
+ "<extra_id_74>": 32025,
76
+ "<extra_id_75>": 32024,
77
+ "<extra_id_76>": 32023,
78
+ "<extra_id_77>": 32022,
79
+ "<extra_id_78>": 32021,
80
+ "<extra_id_79>": 32020,
81
+ "<extra_id_7>": 32092,
82
+ "<extra_id_80>": 32019,
83
+ "<extra_id_81>": 32018,
84
+ "<extra_id_82>": 32017,
85
+ "<extra_id_83>": 32016,
86
+ "<extra_id_84>": 32015,
87
+ "<extra_id_85>": 32014,
88
+ "<extra_id_86>": 32013,
89
+ "<extra_id_87>": 32012,
90
+ "<extra_id_88>": 32011,
91
+ "<extra_id_89>": 32010,
92
+ "<extra_id_8>": 32091,
93
+ "<extra_id_90>": 32009,
94
+ "<extra_id_91>": 32008,
95
+ "<extra_id_92>": 32007,
96
+ "<extra_id_93>": 32006,
97
+ "<extra_id_94>": 32005,
98
+ "<extra_id_95>": 32004,
99
+ "<extra_id_96>": 32003,
100
+ "<extra_id_97>": 32002,
101
+ "<extra_id_98>": 32001,
102
+ "<extra_id_99>": 32000,
103
+ "<extra_id_9>": 32090,
104
+ "<prosody>": 32100
105
+ }
bigscience_T0_3B_ssml/checkpoint-12/added_tokens.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</prosody>": 32101,
3
+ "<break/>": 32102,
4
+ "<extra_id_0>": 32099,
5
+ "<extra_id_10>": 32089,
6
+ "<extra_id_11>": 32088,
7
+ "<extra_id_12>": 32087,
8
+ "<extra_id_13>": 32086,
9
+ "<extra_id_14>": 32085,
10
+ "<extra_id_15>": 32084,
11
+ "<extra_id_16>": 32083,
12
+ "<extra_id_17>": 32082,
13
+ "<extra_id_18>": 32081,
14
+ "<extra_id_19>": 32080,
15
+ "<extra_id_1>": 32098,
16
+ "<extra_id_20>": 32079,
17
+ "<extra_id_21>": 32078,
18
+ "<extra_id_22>": 32077,
19
+ "<extra_id_23>": 32076,
20
+ "<extra_id_24>": 32075,
21
+ "<extra_id_25>": 32074,
22
+ "<extra_id_26>": 32073,
23
+ "<extra_id_27>": 32072,
24
+ "<extra_id_28>": 32071,
25
+ "<extra_id_29>": 32070,
26
+ "<extra_id_2>": 32097,
27
+ "<extra_id_30>": 32069,
28
+ "<extra_id_31>": 32068,
29
+ "<extra_id_32>": 32067,
30
+ "<extra_id_33>": 32066,
31
+ "<extra_id_34>": 32065,
32
+ "<extra_id_35>": 32064,
33
+ "<extra_id_36>": 32063,
34
+ "<extra_id_37>": 32062,
35
+ "<extra_id_38>": 32061,
36
+ "<extra_id_39>": 32060,
37
+ "<extra_id_3>": 32096,
38
+ "<extra_id_40>": 32059,
39
+ "<extra_id_41>": 32058,
40
+ "<extra_id_42>": 32057,
41
+ "<extra_id_43>": 32056,
42
+ "<extra_id_44>": 32055,
43
+ "<extra_id_45>": 32054,
44
+ "<extra_id_46>": 32053,
45
+ "<extra_id_47>": 32052,
46
+ "<extra_id_48>": 32051,
47
+ "<extra_id_49>": 32050,
48
+ "<extra_id_4>": 32095,
49
+ "<extra_id_50>": 32049,
50
+ "<extra_id_51>": 32048,
51
+ "<extra_id_52>": 32047,
52
+ "<extra_id_53>": 32046,
53
+ "<extra_id_54>": 32045,
54
+ "<extra_id_55>": 32044,
55
+ "<extra_id_56>": 32043,
56
+ "<extra_id_57>": 32042,
57
+ "<extra_id_58>": 32041,
58
+ "<extra_id_59>": 32040,
59
+ "<extra_id_5>": 32094,
60
+ "<extra_id_60>": 32039,
61
+ "<extra_id_61>": 32038,
62
+ "<extra_id_62>": 32037,
63
+ "<extra_id_63>": 32036,
64
+ "<extra_id_64>": 32035,
65
+ "<extra_id_65>": 32034,
66
+ "<extra_id_66>": 32033,
67
+ "<extra_id_67>": 32032,
68
+ "<extra_id_68>": 32031,
69
+ "<extra_id_69>": 32030,
70
+ "<extra_id_6>": 32093,
71
+ "<extra_id_70>": 32029,
72
+ "<extra_id_71>": 32028,
73
+ "<extra_id_72>": 32027,
74
+ "<extra_id_73>": 32026,
75
+ "<extra_id_74>": 32025,
76
+ "<extra_id_75>": 32024,
77
+ "<extra_id_76>": 32023,
78
+ "<extra_id_77>": 32022,
79
+ "<extra_id_78>": 32021,
80
+ "<extra_id_79>": 32020,
81
+ "<extra_id_7>": 32092,
82
+ "<extra_id_80>": 32019,
83
+ "<extra_id_81>": 32018,
84
+ "<extra_id_82>": 32017,
85
+ "<extra_id_83>": 32016,
86
+ "<extra_id_84>": 32015,
87
+ "<extra_id_85>": 32014,
88
+ "<extra_id_86>": 32013,
89
+ "<extra_id_87>": 32012,
90
+ "<extra_id_88>": 32011,
91
+ "<extra_id_89>": 32010,
92
+ "<extra_id_8>": 32091,
93
+ "<extra_id_90>": 32009,
94
+ "<extra_id_91>": 32008,
95
+ "<extra_id_92>": 32007,
96
+ "<extra_id_93>": 32006,
97
+ "<extra_id_94>": 32005,
98
+ "<extra_id_95>": 32004,
99
+ "<extra_id_96>": 32003,
100
+ "<extra_id_97>": 32002,
101
+ "<extra_id_98>": 32001,
102
+ "<extra_id_99>": 32000,
103
+ "<extra_id_9>": 32090,
104
+ "<prosody>": 32100
105
+ }
bigscience_T0_3B_ssml/checkpoint-12/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 5120,
7
+ "d_kv": 64,
8
+ "d_model": 2048,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "gradient_checkpointing": false,
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 32,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.52.2",
30
+ "use_cache": true,
31
+ "vocab_size": 32103
32
+ }
bigscience_T0_3B_ssml/checkpoint-12/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.52.2"
7
+ }
bigscience_T0_3B_ssml/checkpoint-12/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf8bbd564f313c9a94957b19a284ed4d29b10f8fdd5120debc85e3d602c6c17
3
+ size 4994608408
bigscience_T0_3B_ssml/checkpoint-12/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed198d9e7699a55889472809014cd70a2d15ca93914e3bdc233b01bc196efcb7
3
+ size 4974952864
bigscience_T0_3B_ssml/checkpoint-12/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0fc95b10c186424f1c43b2f01a19094cfe80c8c8ec21c2c097a9915b54266c
3
+ size 1429126552
bigscience_T0_3B_ssml/checkpoint-12/model.safetensors.index.json ADDED
@@ -0,0 +1,565 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11398619136
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00001-of-00003.safetensors",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00001-of-00003.safetensors",
15
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
16
+ "decoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
17
+ "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
18
+ "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
19
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
20
+ "decoder.block.0.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
21
+ "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
22
+ "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
23
+ "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
24
+ "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
25
+ "decoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
26
+ "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
27
+ "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
28
+ "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
29
+ "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
30
+ "decoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
31
+ "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
32
+ "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
33
+ "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
34
+ "decoder.block.1.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
35
+ "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
36
+ "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
37
+ "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
38
+ "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
39
+ "decoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
40
+ "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
41
+ "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
42
+ "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
43
+ "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
44
+ "decoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
45
+ "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
46
+ "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
47
+ "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
48
+ "decoder.block.10.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
49
+ "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
50
+ "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
51
+ "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
52
+ "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
53
+ "decoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
54
+ "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
55
+ "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
56
+ "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
57
+ "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
58
+ "decoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
59
+ "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
60
+ "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
61
+ "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
62
+ "decoder.block.11.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
63
+ "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
64
+ "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
65
+ "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
66
+ "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
67
+ "decoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
68
+ "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
69
+ "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
70
+ "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
71
+ "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
72
+ "decoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
73
+ "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
74
+ "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
75
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
76
+ "decoder.block.12.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
77
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
78
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
79
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
80
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
81
+ "decoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
82
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
83
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
84
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
85
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
86
+ "decoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
87
+ "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
88
+ "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
89
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
90
+ "decoder.block.13.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
91
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
92
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
93
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
94
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
95
+ "decoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
96
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
97
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
98
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
99
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
100
+ "decoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
101
+ "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
102
+ "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
103
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
104
+ "decoder.block.14.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
105
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
106
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
107
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
108
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
109
+ "decoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
110
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
111
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
112
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
113
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
114
+ "decoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
115
+ "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
116
+ "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
117
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
118
+ "decoder.block.15.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
119
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
120
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
121
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
122
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
123
+ "decoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
124
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
125
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
126
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
127
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
128
+ "decoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
129
+ "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
130
+ "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
131
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
132
+ "decoder.block.16.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
133
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
134
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
135
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
136
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
137
+ "decoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
138
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
139
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
140
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
141
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
142
+ "decoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
143
+ "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
144
+ "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
145
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
146
+ "decoder.block.17.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
147
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
148
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
149
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
150
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
151
+ "decoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
152
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
153
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
154
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
155
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
156
+ "decoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
157
+ "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
158
+ "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
159
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
160
+ "decoder.block.18.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
161
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
162
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
163
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
164
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
165
+ "decoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
166
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
167
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
168
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
169
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
170
+ "decoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
171
+ "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
172
+ "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
173
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
174
+ "decoder.block.19.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
175
+ "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
176
+ "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
177
+ "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
178
+ "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
179
+ "decoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
180
+ "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
181
+ "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
182
+ "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
183
+ "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
184
+ "decoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
185
+ "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
186
+ "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
187
+ "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
188
+ "decoder.block.2.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
189
+ "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
190
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
191
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
192
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
193
+ "decoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
194
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
195
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
196
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
197
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
198
+ "decoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
199
+ "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
200
+ "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
201
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
202
+ "decoder.block.20.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
203
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
204
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
205
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
206
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
207
+ "decoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
208
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
209
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
210
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
211
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
212
+ "decoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
213
+ "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
214
+ "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
215
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
216
+ "decoder.block.21.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
217
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
218
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
219
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
220
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
221
+ "decoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
222
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
223
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
224
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
225
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
226
+ "decoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
227
+ "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
228
+ "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
229
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
230
+ "decoder.block.22.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
231
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
232
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
233
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
234
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
235
+ "decoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
236
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
237
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
238
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
239
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
240
+ "decoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
241
+ "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
242
+ "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
243
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
244
+ "decoder.block.23.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
245
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
246
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
247
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
248
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
249
+ "decoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
250
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
251
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
252
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
253
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
254
+ "decoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
255
+ "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
256
+ "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
257
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
258
+ "decoder.block.3.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
259
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
260
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
261
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
262
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
263
+ "decoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
264
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
265
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
266
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
267
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
268
+ "decoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
269
+ "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
270
+ "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
271
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
272
+ "decoder.block.4.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
273
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
274
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
275
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
276
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
277
+ "decoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
278
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
279
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
280
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
281
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
282
+ "decoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
283
+ "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
284
+ "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
285
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
286
+ "decoder.block.5.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
287
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
288
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
289
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
290
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
291
+ "decoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
292
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
293
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
294
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
295
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
296
+ "decoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
297
+ "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
298
+ "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
299
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
300
+ "decoder.block.6.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
301
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
302
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
303
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
304
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
305
+ "decoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
306
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
307
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
308
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
309
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
310
+ "decoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
311
+ "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
312
+ "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
313
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
314
+ "decoder.block.7.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
315
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
316
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
317
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
318
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
319
+ "decoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
320
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
321
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
322
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
323
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
324
+ "decoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
325
+ "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
326
+ "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
327
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
328
+ "decoder.block.8.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
329
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
330
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
331
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
332
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
333
+ "decoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
334
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
335
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
336
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
337
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
338
+ "decoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
339
+ "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
340
+ "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
341
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
342
+ "decoder.block.9.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
343
+ "decoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
344
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
345
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
346
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
347
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
348
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
349
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
350
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
351
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
352
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
353
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
354
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
355
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
356
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
357
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
358
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
359
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
360
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
361
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
362
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
363
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
364
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
365
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
366
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
367
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
368
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
369
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
370
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
371
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
372
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
373
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
374
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
375
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
376
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
377
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
378
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
379
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
380
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
381
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
382
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
383
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
384
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
385
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
386
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
387
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
388
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
389
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
390
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
391
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
392
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
393
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
394
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
395
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
396
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
397
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
398
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
399
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
400
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
401
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
402
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
403
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
404
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
405
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
406
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
407
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
408
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
409
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
410
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
411
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
412
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
413
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
414
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
415
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
416
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
417
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
418
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
419
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
420
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
421
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
422
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
423
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
424
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
425
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
426
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
427
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
428
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
429
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
430
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
431
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
432
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
433
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
434
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
435
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
436
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
437
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
438
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
439
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
440
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
441
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
442
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
443
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
444
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
445
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
446
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
447
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
448
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
449
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
450
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
451
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
452
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
453
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
454
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
455
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
456
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
457
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
458
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
459
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
460
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
461
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
462
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
463
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
464
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
465
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
466
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
467
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
468
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
469
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
470
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
471
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
472
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
473
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
474
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
475
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
476
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
477
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
478
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
479
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
480
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
481
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
482
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
483
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
484
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
485
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
486
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
487
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
488
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
489
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
490
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
491
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
492
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
493
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
494
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
495
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
496
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
497
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
498
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
499
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
500
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
501
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
502
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
503
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
504
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
505
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
506
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
507
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
508
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
509
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
510
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
511
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
512
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
513
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
514
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
515
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
516
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
517
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
518
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
519
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
520
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
521
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
522
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
523
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
524
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
525
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
526
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
527
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
528
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
529
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
530
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
531
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
532
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
533
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
534
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
535
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
536
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
537
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
538
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
539
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
540
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
541
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
542
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
543
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
544
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
545
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
546
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
547
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
548
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
549
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
550
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
551
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
552
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
553
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
554
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
555
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
556
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
557
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
558
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
559
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
560
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
561
+ "encoder.final_layer_norm.weight": "model-00001-of-00003.safetensors",
562
+ "lm_head.weight": "model-00003-of-00003.safetensors",
563
+ "shared.weight": "model-00001-of-00003.safetensors"
564
+ }
565
+ }
bigscience_T0_3B_ssml/checkpoint-12/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38c1a0726430cca2fddc9af556f0a0fa20260ebecfa38a6976d054ca9892f38c
3
+ size 22797727725
bigscience_T0_3B_ssml/checkpoint-12/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95136deb85084a0c709c920aacd09fbfca914759fa48901e4e352c1dfc48c797
3
+ size 14645
bigscience_T0_3B_ssml/checkpoint-12/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b21c5349d5e7d02de630ebc1cb53ade1d9c6079eeb8594d223bb786011a0428b
3
+ size 1383
bigscience_T0_3B_ssml/checkpoint-12/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f83baff7e6600abdfa2553a73cce7ae5a3e8bfce07cc9b0cf223052f0da9d013
3
+ size 1465
bigscience_T0_3B_ssml/checkpoint-12/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
bigscience_T0_3B_ssml/checkpoint-12/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
bigscience_T0_3B_ssml/checkpoint-12/tokenizer_config.json ADDED
@@ -0,0 +1,965 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": true,
783
+ "normalized": false,
784
+ "rstrip": true,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": true,
791
+ "normalized": false,
792
+ "rstrip": true,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": true,
799
+ "normalized": false,
800
+ "rstrip": true,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": true,
807
+ "normalized": false,
808
+ "rstrip": true,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": true,
815
+ "normalized": false,
816
+ "rstrip": true,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": true,
823
+ "normalized": false,
824
+ "rstrip": true,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32100": {
829
+ "content": "<prosody>",
830
+ "lstrip": false,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": false
835
+ },
836
+ "32101": {
837
+ "content": "</prosody>",
838
+ "lstrip": false,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": false
843
+ },
844
+ "32102": {
845
+ "content": "<break/>",
846
+ "lstrip": false,
847
+ "normalized": true,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": false
851
+ }
852
+ },
853
+ "additional_special_tokens": [
854
+ "<extra_id_0>",
855
+ "<extra_id_1>",
856
+ "<extra_id_2>",
857
+ "<extra_id_3>",
858
+ "<extra_id_4>",
859
+ "<extra_id_5>",
860
+ "<extra_id_6>",
861
+ "<extra_id_7>",
862
+ "<extra_id_8>",
863
+ "<extra_id_9>",
864
+ "<extra_id_10>",
865
+ "<extra_id_11>",
866
+ "<extra_id_12>",
867
+ "<extra_id_13>",
868
+ "<extra_id_14>",
869
+ "<extra_id_15>",
870
+ "<extra_id_16>",
871
+ "<extra_id_17>",
872
+ "<extra_id_18>",
873
+ "<extra_id_19>",
874
+ "<extra_id_20>",
875
+ "<extra_id_21>",
876
+ "<extra_id_22>",
877
+ "<extra_id_23>",
878
+ "<extra_id_24>",
879
+ "<extra_id_25>",
880
+ "<extra_id_26>",
881
+ "<extra_id_27>",
882
+ "<extra_id_28>",
883
+ "<extra_id_29>",
884
+ "<extra_id_30>",
885
+ "<extra_id_31>",
886
+ "<extra_id_32>",
887
+ "<extra_id_33>",
888
+ "<extra_id_34>",
889
+ "<extra_id_35>",
890
+ "<extra_id_36>",
891
+ "<extra_id_37>",
892
+ "<extra_id_38>",
893
+ "<extra_id_39>",
894
+ "<extra_id_40>",
895
+ "<extra_id_41>",
896
+ "<extra_id_42>",
897
+ "<extra_id_43>",
898
+ "<extra_id_44>",
899
+ "<extra_id_45>",
900
+ "<extra_id_46>",
901
+ "<extra_id_47>",
902
+ "<extra_id_48>",
903
+ "<extra_id_49>",
904
+ "<extra_id_50>",
905
+ "<extra_id_51>",
906
+ "<extra_id_52>",
907
+ "<extra_id_53>",
908
+ "<extra_id_54>",
909
+ "<extra_id_55>",
910
+ "<extra_id_56>",
911
+ "<extra_id_57>",
912
+ "<extra_id_58>",
913
+ "<extra_id_59>",
914
+ "<extra_id_60>",
915
+ "<extra_id_61>",
916
+ "<extra_id_62>",
917
+ "<extra_id_63>",
918
+ "<extra_id_64>",
919
+ "<extra_id_65>",
920
+ "<extra_id_66>",
921
+ "<extra_id_67>",
922
+ "<extra_id_68>",
923
+ "<extra_id_69>",
924
+ "<extra_id_70>",
925
+ "<extra_id_71>",
926
+ "<extra_id_72>",
927
+ "<extra_id_73>",
928
+ "<extra_id_74>",
929
+ "<extra_id_75>",
930
+ "<extra_id_76>",
931
+ "<extra_id_77>",
932
+ "<extra_id_78>",
933
+ "<extra_id_79>",
934
+ "<extra_id_80>",
935
+ "<extra_id_81>",
936
+ "<extra_id_82>",
937
+ "<extra_id_83>",
938
+ "<extra_id_84>",
939
+ "<extra_id_85>",
940
+ "<extra_id_86>",
941
+ "<extra_id_87>",
942
+ "<extra_id_88>",
943
+ "<extra_id_89>",
944
+ "<extra_id_90>",
945
+ "<extra_id_91>",
946
+ "<extra_id_92>",
947
+ "<extra_id_93>",
948
+ "<extra_id_94>",
949
+ "<extra_id_95>",
950
+ "<extra_id_96>",
951
+ "<extra_id_97>",
952
+ "<extra_id_98>",
953
+ "<extra_id_99>"
954
+ ],
955
+ "clean_up_tokenization_spaces": false,
956
+ "eos_token": "</s>",
957
+ "extra_ids": 100,
958
+ "extra_special_tokens": {},
959
+ "legacy": true,
960
+ "model_max_length": 512,
961
+ "pad_token": "<pad>",
962
+ "sp_model_kwargs": {},
963
+ "tokenizer_class": "T5Tokenizer",
964
+ "unk_token": "<unk>"
965
+ }
bigscience_T0_3B_ssml/checkpoint-12/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 100,
7
+ "global_step": 12,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 2.533333333333333,
14
+ "grad_norm": 2082258.875,
15
+ "learning_rate": 8.181818181818181e-06,
16
+ "loss": 10.7988,
17
+ "step": 10
18
+ }
19
+ ],
20
+ "logging_steps": 10,
21
+ "max_steps": 12,
22
+ "num_input_tokens_seen": 0,
23
+ "num_train_epochs": 3,
24
+ "save_steps": 500,
25
+ "stateful_callbacks": {
26
+ "TrainerControl": {
27
+ "args": {
28
+ "should_epoch_stop": false,
29
+ "should_evaluate": false,
30
+ "should_log": false,
31
+ "should_save": true,
32
+ "should_training_stop": true
33
+ },
34
+ "attributes": {}
35
+ }
36
+ },
37
+ "total_flos": 2950494714593280.0,
38
+ "train_batch_size": 8,
39
+ "trial_name": null,
40
+ "trial_params": null
41
+ }
bigscience_T0_3B_ssml/checkpoint-12/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd9b4ba5089d80878af9bca2c808e0f55547e09bb122f57fa5e9f8d95f10db55
3
+ size 5713
bigscience_T0_3B_ssml/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 5120,
7
+ "d_kv": 64,
8
+ "d_model": 2048,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "gradient_checkpointing": false,
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 32,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.52.2",
30
+ "use_cache": true,
31
+ "vocab_size": 32103
32
+ }
bigscience_T0_3B_ssml/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.52.2"
7
+ }
bigscience_T0_3B_ssml/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf8bbd564f313c9a94957b19a284ed4d29b10f8fdd5120debc85e3d602c6c17
3
+ size 4994608408
bigscience_T0_3B_ssml/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed198d9e7699a55889472809014cd70a2d15ca93914e3bdc233b01bc196efcb7
3
+ size 4974952864
bigscience_T0_3B_ssml/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0fc95b10c186424f1c43b2f01a19094cfe80c8c8ec21c2c097a9915b54266c
3
+ size 1429126552
bigscience_T0_3B_ssml/model.safetensors.index.json ADDED
@@ -0,0 +1,565 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11398619136
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00001-of-00003.safetensors",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00001-of-00003.safetensors",
15
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
16
+ "decoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
17
+ "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
18
+ "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
19
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
20
+ "decoder.block.0.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
21
+ "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
22
+ "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
23
+ "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
24
+ "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
25
+ "decoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
26
+ "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
27
+ "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
28
+ "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
29
+ "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
30
+ "decoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
31
+ "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
32
+ "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
33
+ "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
34
+ "decoder.block.1.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
35
+ "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
36
+ "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
37
+ "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
38
+ "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
39
+ "decoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
40
+ "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
41
+ "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
42
+ "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
43
+ "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
44
+ "decoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
45
+ "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
46
+ "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
47
+ "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
48
+ "decoder.block.10.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
49
+ "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
50
+ "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
51
+ "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
52
+ "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
53
+ "decoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
54
+ "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
55
+ "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
56
+ "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
57
+ "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
58
+ "decoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
59
+ "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
60
+ "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
61
+ "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
62
+ "decoder.block.11.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
63
+ "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
64
+ "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
65
+ "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
66
+ "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
67
+ "decoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
68
+ "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
69
+ "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
70
+ "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
71
+ "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
72
+ "decoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
73
+ "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
74
+ "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
75
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
76
+ "decoder.block.12.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
77
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
78
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
79
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
80
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
81
+ "decoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
82
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
83
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
84
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
85
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
86
+ "decoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
87
+ "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
88
+ "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
89
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
90
+ "decoder.block.13.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
91
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
92
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
93
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
94
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
95
+ "decoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
96
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
97
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
98
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
99
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
100
+ "decoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
101
+ "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
102
+ "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
103
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
104
+ "decoder.block.14.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
105
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
106
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
107
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
108
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
109
+ "decoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
110
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
111
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
112
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
113
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
114
+ "decoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
115
+ "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
116
+ "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
117
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
118
+ "decoder.block.15.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
119
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
120
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
121
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
122
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
123
+ "decoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
124
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
125
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
126
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
127
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
128
+ "decoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
129
+ "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
130
+ "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
131
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
132
+ "decoder.block.16.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
133
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
134
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
135
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
136
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
137
+ "decoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
138
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
139
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
140
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
141
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
142
+ "decoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
143
+ "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
144
+ "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
145
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
146
+ "decoder.block.17.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
147
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
148
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
149
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
150
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
151
+ "decoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
152
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
153
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
154
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
155
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
156
+ "decoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
157
+ "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
158
+ "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
159
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
160
+ "decoder.block.18.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
161
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
162
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
163
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
164
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
165
+ "decoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
166
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
167
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
168
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
169
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
170
+ "decoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
171
+ "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
172
+ "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
173
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
174
+ "decoder.block.19.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
175
+ "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
176
+ "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
177
+ "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
178
+ "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
179
+ "decoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
180
+ "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
181
+ "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
182
+ "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
183
+ "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
184
+ "decoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
185
+ "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
186
+ "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
187
+ "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
188
+ "decoder.block.2.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
189
+ "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
190
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
191
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
192
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
193
+ "decoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
194
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
195
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
196
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
197
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
198
+ "decoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
199
+ "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
200
+ "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
201
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
202
+ "decoder.block.20.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
203
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
204
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
205
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
206
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
207
+ "decoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
208
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
209
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
210
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
211
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
212
+ "decoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
213
+ "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
214
+ "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
215
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
216
+ "decoder.block.21.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
217
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
218
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
219
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
220
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
221
+ "decoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
222
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
223
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
224
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
225
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
226
+ "decoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
227
+ "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
228
+ "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
229
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
230
+ "decoder.block.22.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
231
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
232
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
233
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
234
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
235
+ "decoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
236
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
237
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
238
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
239
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
240
+ "decoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
241
+ "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
242
+ "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
243
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
244
+ "decoder.block.23.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
245
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
246
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
247
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
248
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
249
+ "decoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
250
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
251
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
252
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
253
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
254
+ "decoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
255
+ "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
256
+ "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
257
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
258
+ "decoder.block.3.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
259
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
260
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
261
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
262
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
263
+ "decoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
264
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
265
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
266
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
267
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
268
+ "decoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
269
+ "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
270
+ "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
271
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
272
+ "decoder.block.4.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
273
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
274
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
275
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
276
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
277
+ "decoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
278
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
279
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
280
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
281
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
282
+ "decoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
283
+ "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
284
+ "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
285
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
286
+ "decoder.block.5.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
287
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
288
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
289
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
290
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
291
+ "decoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
292
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
293
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
294
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
295
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
296
+ "decoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
297
+ "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
298
+ "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
299
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
300
+ "decoder.block.6.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
301
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
302
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
303
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
304
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
305
+ "decoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
306
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
307
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
308
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
309
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
310
+ "decoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
311
+ "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
312
+ "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
313
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
314
+ "decoder.block.7.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
315
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
316
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
317
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
318
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
319
+ "decoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
320
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
321
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
322
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
323
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
324
+ "decoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
325
+ "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
326
+ "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
327
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
328
+ "decoder.block.8.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
329
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
330
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
331
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
332
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
333
+ "decoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
334
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
335
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
336
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
337
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
338
+ "decoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
339
+ "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
340
+ "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
341
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
342
+ "decoder.block.9.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
343
+ "decoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
344
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
345
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
346
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
347
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
348
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
349
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
350
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
351
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
352
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
353
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
354
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
355
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
356
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
357
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
358
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
359
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
360
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
361
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
362
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
363
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
364
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
365
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
366
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
367
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
368
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
369
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
370
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
371
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
372
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
373
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
374
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
375
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
376
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
377
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
378
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
379
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
380
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
381
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
382
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
383
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
384
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
385
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
386
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
387
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
388
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
389
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
390
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
391
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
392
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
393
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
394
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
395
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
396
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
397
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
398
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
399
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
400
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
401
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
402
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
403
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
404
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
405
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
406
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
407
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
408
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
409
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
410
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
411
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
412
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
413
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
414
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
415
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
416
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
417
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
418
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
419
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
420
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
421
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
422
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
423
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
424
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
425
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
426
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
427
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
428
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
429
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
430
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
431
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
432
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
433
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
434
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
435
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
436
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
437
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
438
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
439
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
440
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
441
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
442
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
443
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
444
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
445
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
446
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
447
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
448
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
449
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
450
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
451
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
452
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
453
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
454
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
455
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
456
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
457
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
458
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
459
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
460
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
461
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
462
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
463
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
464
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
465
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
466
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
467
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
468
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
469
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
470
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
471
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
472
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
473
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
474
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
475
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
476
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
477
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
478
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
479
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
480
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
481
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
482
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
483
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
484
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
485
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
486
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
487
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
488
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
489
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
490
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
491
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
492
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
493
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
494
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
495
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
496
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
497
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
498
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
499
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
500
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
501
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
502
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
503
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
504
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
505
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
506
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
507
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
508
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
509
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
510
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
511
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
512
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
513
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
514
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
515
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
516
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
517
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
518
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
519
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
520
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
521
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
522
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
523
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
524
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
525
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
526
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
527
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
528
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
529
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
530
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
531
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
532
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
533
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
534
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
535
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
536
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
537
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
538
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
539
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
540
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
541
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
542
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
543
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
544
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
545
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
546
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
547
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
548
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
549
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
550
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
551
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
552
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
553
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
554
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
555
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
556
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
557
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
558
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
559
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
560
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
561
+ "encoder.final_layer_norm.weight": "model-00001-of-00003.safetensors",
562
+ "lm_head.weight": "model-00003-of-00003.safetensors",
563
+ "shared.weight": "model-00001-of-00003.safetensors"
564
+ }
565
+ }
bigscience_T0_3B_ssml/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
bigscience_T0_3B_ssml/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
bigscience_T0_3B_ssml/tokenizer_config.json ADDED
@@ -0,0 +1,965 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": true,
783
+ "normalized": false,
784
+ "rstrip": true,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": true,
791
+ "normalized": false,
792
+ "rstrip": true,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": true,
799
+ "normalized": false,
800
+ "rstrip": true,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": true,
807
+ "normalized": false,
808
+ "rstrip": true,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": true,
815
+ "normalized": false,
816
+ "rstrip": true,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": true,
823
+ "normalized": false,
824
+ "rstrip": true,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32100": {
829
+ "content": "<prosody>",
830
+ "lstrip": false,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": false
835
+ },
836
+ "32101": {
837
+ "content": "</prosody>",
838
+ "lstrip": false,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": false
843
+ },
844
+ "32102": {
845
+ "content": "<break/>",
846
+ "lstrip": false,
847
+ "normalized": true,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": false
851
+ }
852
+ },
853
+ "additional_special_tokens": [
854
+ "<extra_id_0>",
855
+ "<extra_id_1>",
856
+ "<extra_id_2>",
857
+ "<extra_id_3>",
858
+ "<extra_id_4>",
859
+ "<extra_id_5>",
860
+ "<extra_id_6>",
861
+ "<extra_id_7>",
862
+ "<extra_id_8>",
863
+ "<extra_id_9>",
864
+ "<extra_id_10>",
865
+ "<extra_id_11>",
866
+ "<extra_id_12>",
867
+ "<extra_id_13>",
868
+ "<extra_id_14>",
869
+ "<extra_id_15>",
870
+ "<extra_id_16>",
871
+ "<extra_id_17>",
872
+ "<extra_id_18>",
873
+ "<extra_id_19>",
874
+ "<extra_id_20>",
875
+ "<extra_id_21>",
876
+ "<extra_id_22>",
877
+ "<extra_id_23>",
878
+ "<extra_id_24>",
879
+ "<extra_id_25>",
880
+ "<extra_id_26>",
881
+ "<extra_id_27>",
882
+ "<extra_id_28>",
883
+ "<extra_id_29>",
884
+ "<extra_id_30>",
885
+ "<extra_id_31>",
886
+ "<extra_id_32>",
887
+ "<extra_id_33>",
888
+ "<extra_id_34>",
889
+ "<extra_id_35>",
890
+ "<extra_id_36>",
891
+ "<extra_id_37>",
892
+ "<extra_id_38>",
893
+ "<extra_id_39>",
894
+ "<extra_id_40>",
895
+ "<extra_id_41>",
896
+ "<extra_id_42>",
897
+ "<extra_id_43>",
898
+ "<extra_id_44>",
899
+ "<extra_id_45>",
900
+ "<extra_id_46>",
901
+ "<extra_id_47>",
902
+ "<extra_id_48>",
903
+ "<extra_id_49>",
904
+ "<extra_id_50>",
905
+ "<extra_id_51>",
906
+ "<extra_id_52>",
907
+ "<extra_id_53>",
908
+ "<extra_id_54>",
909
+ "<extra_id_55>",
910
+ "<extra_id_56>",
911
+ "<extra_id_57>",
912
+ "<extra_id_58>",
913
+ "<extra_id_59>",
914
+ "<extra_id_60>",
915
+ "<extra_id_61>",
916
+ "<extra_id_62>",
917
+ "<extra_id_63>",
918
+ "<extra_id_64>",
919
+ "<extra_id_65>",
920
+ "<extra_id_66>",
921
+ "<extra_id_67>",
922
+ "<extra_id_68>",
923
+ "<extra_id_69>",
924
+ "<extra_id_70>",
925
+ "<extra_id_71>",
926
+ "<extra_id_72>",
927
+ "<extra_id_73>",
928
+ "<extra_id_74>",
929
+ "<extra_id_75>",
930
+ "<extra_id_76>",
931
+ "<extra_id_77>",
932
+ "<extra_id_78>",
933
+ "<extra_id_79>",
934
+ "<extra_id_80>",
935
+ "<extra_id_81>",
936
+ "<extra_id_82>",
937
+ "<extra_id_83>",
938
+ "<extra_id_84>",
939
+ "<extra_id_85>",
940
+ "<extra_id_86>",
941
+ "<extra_id_87>",
942
+ "<extra_id_88>",
943
+ "<extra_id_89>",
944
+ "<extra_id_90>",
945
+ "<extra_id_91>",
946
+ "<extra_id_92>",
947
+ "<extra_id_93>",
948
+ "<extra_id_94>",
949
+ "<extra_id_95>",
950
+ "<extra_id_96>",
951
+ "<extra_id_97>",
952
+ "<extra_id_98>",
953
+ "<extra_id_99>"
954
+ ],
955
+ "clean_up_tokenization_spaces": false,
956
+ "eos_token": "</s>",
957
+ "extra_ids": 100,
958
+ "extra_special_tokens": {},
959
+ "legacy": true,
960
+ "model_max_length": 512,
961
+ "pad_token": "<pad>",
962
+ "sp_model_kwargs": {},
963
+ "tokenizer_class": "T5Tokenizer",
964
+ "unk_token": "<unk>"
965
+ }
bigscience_T0_3B_ssml/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd9b4ba5089d80878af9bca2c808e0f55547e09bb122f57fa5e9f8d95f10db55
3
+ size 5713
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-735/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-7B
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-735/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-7B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "o_proj",
29
+ "down_proj",
30
+ "q_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-735/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7236ab3287bb82ebd8c852fa1f4bd67cfe70b56c43a70ad48ba6cf966835560
3
+ size 80792096
checkpoint-735/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
checkpoint-735/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoint-735/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-735/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f86b1f89eca1aef5309fea20190f0a5e46be9d9e8306a9c8212f73e31ad399d
3
+ size 161810747
checkpoint-735/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26053f2e8193dae8c1a7a207d1bd33b906487922a6c48157f6bb3fcc1fdf9f17
3
+ size 14645
checkpoint-735/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a887c75091f60b02f663359ae689cc976e90f6637ad4c62b6df1eb52c4bc68
3
+ size 1465
checkpoint-735/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-735/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoint-735/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|endoftext|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
checkpoint-735/trainer_state.json ADDED
@@ -0,0 +1,286 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 10000,
7
+ "global_step": 735,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.13646055437100213,
14
+ "grad_norm": 0.14500385522842407,
15
+ "learning_rate": 0.00011399999999999999,
16
+ "loss": 0.1268,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.27292110874200426,
21
+ "grad_norm": 0.06265528500080109,
22
+ "learning_rate": 0.000234,
23
+ "loss": 0.0282,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.4093816631130064,
28
+ "grad_norm": 0.03309512510895729,
29
+ "learning_rate": 0.00029987223755234907,
30
+ "loss": 0.0157,
31
+ "step": 60
32
+ },
33
+ {
34
+ "epoch": 0.5458422174840085,
35
+ "grad_norm": 0.03388677537441254,
36
+ "learning_rate": 0.00029867524500941253,
37
+ "loss": 0.0125,
38
+ "step": 80
39
+ },
40
+ {
41
+ "epoch": 0.6823027718550106,
42
+ "grad_norm": 0.038252197206020355,
43
+ "learning_rate": 0.00029622824461983995,
44
+ "loss": 0.0128,
45
+ "step": 100
46
+ },
47
+ {
48
+ "epoch": 0.8187633262260128,
49
+ "grad_norm": 0.06330293416976929,
50
+ "learning_rate": 0.00029255180988050044,
51
+ "loss": 0.0112,
52
+ "step": 120
53
+ },
54
+ {
55
+ "epoch": 0.9552238805970149,
56
+ "grad_norm": 0.03660163655877113,
57
+ "learning_rate": 0.0002876768509289324,
58
+ "loss": 0.0106,
59
+ "step": 140
60
+ },
61
+ {
62
+ "epoch": 1.0886993603411514,
63
+ "grad_norm": 0.028105631470680237,
64
+ "learning_rate": 0.0002816443546620542,
65
+ "loss": 0.0085,
66
+ "step": 160
67
+ },
68
+ {
69
+ "epoch": 1.2251599147121535,
70
+ "grad_norm": 0.04313601925969124,
71
+ "learning_rate": 0.00027450504013311436,
72
+ "loss": 0.007,
73
+ "step": 180
74
+ },
75
+ {
76
+ "epoch": 1.3616204690831557,
77
+ "grad_norm": 0.03731823340058327,
78
+ "learning_rate": 0.00026631893212418224,
79
+ "loss": 0.0056,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 1.4980810234541577,
84
+ "grad_norm": 0.02299409918487072,
85
+ "learning_rate": 0.00025715485647942525,
86
+ "loss": 0.0075,
87
+ "step": 220
88
+ },
89
+ {
90
+ "epoch": 1.63454157782516,
91
+ "grad_norm": 0.03759332001209259,
92
+ "learning_rate": 0.00024708986144223035,
93
+ "loss": 0.0063,
94
+ "step": 240
95
+ },
96
+ {
97
+ "epoch": 1.7710021321961622,
98
+ "grad_norm": 0.013533813878893852,
99
+ "learning_rate": 0.00023620856986135804,
100
+ "loss": 0.0052,
101
+ "step": 260
102
+ },
103
+ {
104
+ "epoch": 1.9074626865671642,
105
+ "grad_norm": 0.0647633746266365,
106
+ "learning_rate": 0.00022460246771254522,
107
+ "loss": 0.0045,
108
+ "step": 280
109
+ },
110
+ {
111
+ "epoch": 2.0409381663113004,
112
+ "grad_norm": 0.022289317101240158,
113
+ "learning_rate": 0.0002123691349174121,
114
+ "loss": 0.003,
115
+ "step": 300
116
+ },
117
+ {
118
+ "epoch": 2.177398720682303,
119
+ "grad_norm": 0.040852464735507965,
120
+ "learning_rate": 0.00019961142492666903,
121
+ "loss": 0.0028,
122
+ "step": 320
123
+ },
124
+ {
125
+ "epoch": 2.313859275053305,
126
+ "grad_norm": 0.04412081092596054,
127
+ "learning_rate": 0.00018643659996539272,
128
+ "loss": 0.0029,
129
+ "step": 340
130
+ },
131
+ {
132
+ "epoch": 2.450319829424307,
133
+ "grad_norm": 0.047590937465429306,
134
+ "learning_rate": 0.00017295542921091727,
135
+ "loss": 0.0025,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 2.5867803837953094,
140
+ "grad_norm": 0.032162390649318695,
141
+ "learning_rate": 0.00015928125748553563,
142
+ "loss": 0.002,
143
+ "step": 380
144
+ },
145
+ {
146
+ "epoch": 2.7232409381663114,
147
+ "grad_norm": 0.02574550174176693,
148
+ "learning_rate": 0.00014552905229410626,
149
+ "loss": 0.0014,
150
+ "step": 400
151
+ },
152
+ {
153
+ "epoch": 2.8597014925373134,
154
+ "grad_norm": 0.014707539230585098,
155
+ "learning_rate": 0.000131814437218731,
156
+ "loss": 0.0012,
157
+ "step": 420
158
+ },
159
+ {
160
+ "epoch": 2.9961620469083154,
161
+ "grad_norm": 0.04477572441101074,
162
+ "learning_rate": 0.0001182527197973709,
163
+ "loss": 0.0011,
164
+ "step": 440
165
+ },
166
+ {
167
+ "epoch": 3.129637526652452,
168
+ "grad_norm": 0.012851215898990631,
169
+ "learning_rate": 0.00010495792205964832,
170
+ "loss": 0.0008,
171
+ "step": 460
172
+ },
173
+ {
174
+ "epoch": 3.266098081023454,
175
+ "grad_norm": 0.02783357724547386,
176
+ "learning_rate": 9.204182187073868e-05,
177
+ "loss": 0.0007,
178
+ "step": 480
179
+ },
180
+ {
181
+ "epoch": 3.402558635394456,
182
+ "grad_norm": 0.004735818598419428,
183
+ "learning_rate": 7.961301314338808e-05,
184
+ "loss": 0.0004,
185
+ "step": 500
186
+ },
187
+ {
188
+ "epoch": 3.539019189765458,
189
+ "grad_norm": 0.003670594422146678,
190
+ "learning_rate": 6.777599281945507e-05,
191
+ "loss": 0.0004,
192
+ "step": 520
193
+ },
194
+ {
195
+ "epoch": 3.6754797441364606,
196
+ "grad_norm": 0.013839378952980042,
197
+ "learning_rate": 5.66302822973053e-05,
198
+ "loss": 0.0004,
199
+ "step": 540
200
+ },
201
+ {
202
+ "epoch": 3.8119402985074626,
203
+ "grad_norm": 0.00302703189663589,
204
+ "learning_rate": 4.626959069178253e-05,
205
+ "loss": 0.0004,
206
+ "step": 560
207
+ },
208
+ {
209
+ "epoch": 3.948400852878465,
210
+ "grad_norm": 0.026532089337706566,
211
+ "learning_rate": 3.6781026961763353e-05,
212
+ "loss": 0.0004,
213
+ "step": 580
214
+ },
215
+ {
216
+ "epoch": 4.081876332622601,
217
+ "grad_norm": 0.001038851565681398,
218
+ "learning_rate": 2.8244367529442822e-05,
219
+ "loss": 0.0002,
220
+ "step": 600
221
+ },
222
+ {
223
+ "epoch": 4.218336886993604,
224
+ "grad_norm": 0.0008404534310102463,
225
+ "learning_rate": 2.0731385548944725e-05,
226
+ "loss": 0.0002,
227
+ "step": 620
228
+ },
229
+ {
230
+ "epoch": 4.354797441364606,
231
+ "grad_norm": 0.0016892015701159835,
232
+ "learning_rate": 1.4305247463523778e-05,
233
+ "loss": 0.0002,
234
+ "step": 640
235
+ },
236
+ {
237
+ "epoch": 4.491257995735608,
238
+ "grad_norm": 0.002141030738130212,
239
+ "learning_rate": 9.019981924888797e-06,
240
+ "loss": 0.0001,
241
+ "step": 660
242
+ },
243
+ {
244
+ "epoch": 4.62771855010661,
245
+ "grad_norm": 0.0017192725790664554,
246
+ "learning_rate": 4.920025539782397e-06,
247
+ "loss": 0.0002,
248
+ "step": 680
249
+ },
250
+ {
251
+ "epoch": 4.764179104477612,
252
+ "grad_norm": 0.002778939437121153,
253
+ "learning_rate": 2.0398492630157303e-06,
254
+ "loss": 0.0002,
255
+ "step": 700
256
+ },
257
+ {
258
+ "epoch": 4.900639658848614,
259
+ "grad_norm": 0.002974987495690584,
260
+ "learning_rate": 4.036685781107329e-07,
261
+ "loss": 0.0001,
262
+ "step": 720
263
+ }
264
+ ],
265
+ "logging_steps": 20,
266
+ "max_steps": 735,
267
+ "num_input_tokens_seen": 0,
268
+ "num_train_epochs": 5,
269
+ "save_steps": 10000,
270
+ "stateful_callbacks": {
271
+ "TrainerControl": {
272
+ "args": {
273
+ "should_epoch_stop": false,
274
+ "should_evaluate": false,
275
+ "should_log": false,
276
+ "should_save": true,
277
+ "should_training_stop": true
278
+ },
279
+ "attributes": {}
280
+ }
281
+ },
282
+ "total_flos": 1.8319121075920896e+17,
283
+ "train_batch_size": 1,
284
+ "trial_name": null,
285
+ "trial_params": null
286
+ }
checkpoint-735/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea8c8e80ab63f86062b99532732587e84926801532774496adb7b92e44238785
3
+ size 5713
checkpoint-735/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
facebook_bart-base_ssml/added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</prosody>": 50266,
3
+ "<break/>": 50267,
4
+ "<break>": 50268,
5
+ "<prosody>": 50265
6
+ }
facebook_bart-base_ssml/checkpoint-120/added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</prosody>": 50266,
3
+ "<break/>": 50267,
4
+ "<break>": 50268,
5
+ "<prosody>": 50265
6
+ }