root
commited on
Commit
•
e92ee14
1
Parent(s):
99d9b93
fine-tuned
Browse files- outputs/qlora-out/README.md +159 -0
- outputs/qlora-out/adapter_config.json +34 -0
- outputs/qlora-out/adapter_model.bin +3 -0
- outputs/qlora-out/added_tokens.json +66 -0
- outputs/qlora-out/checkpoint-1770/README.md +202 -0
- outputs/qlora-out/checkpoint-1770/adapter_config.json +34 -0
- outputs/qlora-out/checkpoint-1770/adapter_model.safetensors +3 -0
- outputs/qlora-out/checkpoint-1770/added_tokens.json +66 -0
- outputs/qlora-out/checkpoint-1770/optimizer.pt +3 -0
- outputs/qlora-out/checkpoint-1770/rng_state.pth +3 -0
- outputs/qlora-out/checkpoint-1770/scheduler.pt +3 -0
- outputs/qlora-out/checkpoint-1770/special_tokens_map.json +95 -0
- outputs/qlora-out/checkpoint-1770/tokenizer.json +0 -0
- outputs/qlora-out/checkpoint-1770/tokenizer.model +3 -0
- outputs/qlora-out/checkpoint-1770/tokenizer_config.json +624 -0
- outputs/qlora-out/checkpoint-1770/trainer_state.json +0 -0
- outputs/qlora-out/checkpoint-1770/training_args.bin +3 -0
- outputs/qlora-out/checkpoint-2655/README.md +202 -0
- outputs/qlora-out/checkpoint-2655/adapter_config.json +34 -0
- outputs/qlora-out/checkpoint-2655/adapter_model.safetensors +3 -0
- outputs/qlora-out/checkpoint-2655/added_tokens.json +66 -0
- outputs/qlora-out/checkpoint-2655/optimizer.pt +3 -0
- outputs/qlora-out/checkpoint-2655/rng_state.pth +3 -0
- outputs/qlora-out/checkpoint-2655/scheduler.pt +3 -0
- outputs/qlora-out/checkpoint-2655/special_tokens_map.json +95 -0
- outputs/qlora-out/checkpoint-2655/tokenizer.json +0 -0
- outputs/qlora-out/checkpoint-2655/tokenizer.model +3 -0
- outputs/qlora-out/checkpoint-2655/tokenizer_config.json +624 -0
- outputs/qlora-out/checkpoint-2655/trainer_state.json +0 -0
- outputs/qlora-out/checkpoint-2655/training_args.bin +3 -0
- outputs/qlora-out/checkpoint-885/README.md +202 -0
- outputs/qlora-out/checkpoint-885/adapter_config.json +34 -0
- outputs/qlora-out/checkpoint-885/adapter_model.safetensors +3 -0
- outputs/qlora-out/checkpoint-885/added_tokens.json +66 -0
- outputs/qlora-out/checkpoint-885/optimizer.pt +3 -0
- outputs/qlora-out/checkpoint-885/rng_state.pth +3 -0
- outputs/qlora-out/checkpoint-885/scheduler.pt +3 -0
- outputs/qlora-out/checkpoint-885/special_tokens_map.json +95 -0
- outputs/qlora-out/checkpoint-885/tokenizer.json +0 -0
- outputs/qlora-out/checkpoint-885/tokenizer.model +3 -0
- outputs/qlora-out/checkpoint-885/tokenizer_config.json +624 -0
- outputs/qlora-out/checkpoint-885/trainer_state.json +0 -0
- outputs/qlora-out/checkpoint-885/training_args.bin +3 -0
- outputs/qlora-out/config.json +46 -0
- outputs/qlora-out/special_tokens_map.json +95 -0
- outputs/qlora-out/tokenizer.json +0 -0
- outputs/qlora-out/tokenizer.model +3 -0
- outputs/qlora-out/tokenizer_config.json +624 -0
outputs/qlora-out/README.md
ADDED
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: pints-ai/1.5-Pints-16K-v0.1
|
3 |
+
library_name: peft
|
4 |
+
license: mit
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: outputs/qlora-out
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
16 |
+
<details><summary>See axolotl config</summary>
|
17 |
+
|
18 |
+
axolotl version: `0.4.1`
|
19 |
+
```yaml
|
20 |
+
base_model: pints-ai/1.5-Pints-16K-v0.1
|
21 |
+
model_type: AutoModelForCausalLM
|
22 |
+
tokenizer_type: AutoTokenizer
|
23 |
+
|
24 |
+
load_in_8bit: false
|
25 |
+
load_in_4bit: true
|
26 |
+
strict: false
|
27 |
+
|
28 |
+
datasets:
|
29 |
+
- path: tangledgroup/tangled-llama-pints-1.5b-v0.2-dataset
|
30 |
+
type: sharegpt
|
31 |
+
conversation: chatml
|
32 |
+
chat_template: chatml
|
33 |
+
dataset_prepared_path:
|
34 |
+
val_set_size: 0.05
|
35 |
+
output_dir: ./outputs/qlora-out
|
36 |
+
|
37 |
+
adapter: qlora
|
38 |
+
lora_model_dir:
|
39 |
+
|
40 |
+
sequence_len: 16384
|
41 |
+
sample_packing: true
|
42 |
+
pad_to_sequence_len: true
|
43 |
+
|
44 |
+
lora_r: 32
|
45 |
+
lora_alpha: 16
|
46 |
+
lora_dropout: 0.05
|
47 |
+
lora_target_modules:
|
48 |
+
lora_target_linear: true
|
49 |
+
lora_fan_in_fan_out:
|
50 |
+
|
51 |
+
wandb_project:
|
52 |
+
wandb_entity:
|
53 |
+
wandb_watch:
|
54 |
+
wandb_name:
|
55 |
+
wandb_log_model:
|
56 |
+
|
57 |
+
gradient_accumulation_steps: 4
|
58 |
+
micro_batch_size: 2
|
59 |
+
num_epochs: 3
|
60 |
+
optimizer: paged_adamw_32bit
|
61 |
+
# optimizer: adamw_torch_fused
|
62 |
+
lr_scheduler: cosine
|
63 |
+
learning_rate: 0.0002
|
64 |
+
|
65 |
+
train_on_inputs: false
|
66 |
+
group_by_length: false
|
67 |
+
bf16: auto
|
68 |
+
fp16:
|
69 |
+
tf32: false
|
70 |
+
|
71 |
+
gradient_checkpointing: true
|
72 |
+
early_stopping_patience:
|
73 |
+
resume_from_checkpoint:
|
74 |
+
local_rank:
|
75 |
+
logging_steps: 1
|
76 |
+
xformers_attention:
|
77 |
+
flash_attention: true
|
78 |
+
|
79 |
+
loss_watchdog_threshold: 15.0
|
80 |
+
loss_watchdog_patience: 3
|
81 |
+
|
82 |
+
warmup_steps: 10
|
83 |
+
evals_per_epoch: 3
|
84 |
+
eval_table_size:
|
85 |
+
saves_per_epoch: 1
|
86 |
+
debug:
|
87 |
+
deepspeed:
|
88 |
+
weight_decay: 0.0
|
89 |
+
fsdp:
|
90 |
+
fsdp_config:
|
91 |
+
special_tokens:
|
92 |
+
|
93 |
+
plugins:
|
94 |
+
- axolotl.integrations.liger.LigerPlugin
|
95 |
+
liger_rope: true
|
96 |
+
liger_rms_norm: true
|
97 |
+
liger_swiglu: true
|
98 |
+
liger_fused_linear_cross_entropy: true
|
99 |
+
```
|
100 |
+
|
101 |
+
</details><br>
|
102 |
+
|
103 |
+
# outputs/qlora-out
|
104 |
+
|
105 |
+
This model is a fine-tuned version of [pints-ai/1.5-Pints-16K-v0.1](https://huggingface.co/pints-ai/1.5-Pints-16K-v0.1) on the None dataset.
|
106 |
+
It achieves the following results on the evaluation set:
|
107 |
+
- Loss: 0.9847
|
108 |
+
|
109 |
+
## Model description
|
110 |
+
|
111 |
+
More information needed
|
112 |
+
|
113 |
+
## Intended uses & limitations
|
114 |
+
|
115 |
+
More information needed
|
116 |
+
|
117 |
+
## Training and evaluation data
|
118 |
+
|
119 |
+
More information needed
|
120 |
+
|
121 |
+
## Training procedure
|
122 |
+
|
123 |
+
### Training hyperparameters
|
124 |
+
|
125 |
+
The following hyperparameters were used during training:
|
126 |
+
- learning_rate: 0.0002
|
127 |
+
- train_batch_size: 2
|
128 |
+
- eval_batch_size: 2
|
129 |
+
- seed: 42
|
130 |
+
- gradient_accumulation_steps: 4
|
131 |
+
- total_train_batch_size: 8
|
132 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
133 |
+
- lr_scheduler_type: cosine
|
134 |
+
- lr_scheduler_warmup_steps: 10
|
135 |
+
- num_epochs: 3
|
136 |
+
|
137 |
+
### Training results
|
138 |
+
|
139 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
140 |
+
|:-------------:|:------:|:----:|:---------------:|
|
141 |
+
| 1.1396 | 0.0011 | 1 | 1.1313 |
|
142 |
+
| 1.0777 | 0.3332 | 295 | 1.0278 |
|
143 |
+
| 1.0219 | 0.6665 | 590 | 1.0119 |
|
144 |
+
| 1.0006 | 0.9997 | 885 | 1.0020 |
|
145 |
+
| 1.0385 | 1.3307 | 1180 | 0.9954 |
|
146 |
+
| 0.9405 | 1.6639 | 1475 | 0.9902 |
|
147 |
+
| 0.9249 | 1.9972 | 1770 | 0.9867 |
|
148 |
+
| 0.9951 | 2.3282 | 2065 | 0.9856 |
|
149 |
+
| 0.9713 | 2.6616 | 2360 | 0.9848 |
|
150 |
+
| 0.9576 | 2.9949 | 2655 | 0.9847 |
|
151 |
+
|
152 |
+
|
153 |
+
### Framework versions
|
154 |
+
|
155 |
+
- PEFT 0.12.0
|
156 |
+
- Transformers 4.45.0.dev0
|
157 |
+
- Pytorch 2.4.1
|
158 |
+
- Datasets 2.21.0
|
159 |
+
- Tokenizers 0.19.1
|
outputs/qlora-out/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "pints-ai/1.5-Pints-16K-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"down_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
outputs/qlora-out/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e69c90d5aaeb434093315607097f73fdef43b5d1d7d29a042a7e27efd6fa1121
|
3 |
+
size 133814794
|
outputs/qlora-out/added_tokens.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 32003,
|
3 |
+
"<</SYS>>": 32007,
|
4 |
+
"<<SYS>>": 32006,
|
5 |
+
"<|assistant|>": 32010,
|
6 |
+
"<|begin_of_text|>": 32011,
|
7 |
+
"<|end_header_id|>": 32013,
|
8 |
+
"<|end_of_turn|>": 32000,
|
9 |
+
"<|eot_id|>": 32014,
|
10 |
+
"<|im_start|>": 32002,
|
11 |
+
"<|pad|>": 32001,
|
12 |
+
"<|reserved_0|>": 32015,
|
13 |
+
"<|reserved_10|>": 32025,
|
14 |
+
"<|reserved_11|>": 32026,
|
15 |
+
"<|reserved_12|>": 32027,
|
16 |
+
"<|reserved_13|>": 32028,
|
17 |
+
"<|reserved_14|>": 32029,
|
18 |
+
"<|reserved_15|>": 32030,
|
19 |
+
"<|reserved_16|>": 32031,
|
20 |
+
"<|reserved_17|>": 32032,
|
21 |
+
"<|reserved_18|>": 32033,
|
22 |
+
"<|reserved_19|>": 32034,
|
23 |
+
"<|reserved_1|>": 32016,
|
24 |
+
"<|reserved_20|>": 32035,
|
25 |
+
"<|reserved_21|>": 32036,
|
26 |
+
"<|reserved_22|>": 32037,
|
27 |
+
"<|reserved_23|>": 32038,
|
28 |
+
"<|reserved_24|>": 32039,
|
29 |
+
"<|reserved_25|>": 32040,
|
30 |
+
"<|reserved_26|>": 32041,
|
31 |
+
"<|reserved_27|>": 32042,
|
32 |
+
"<|reserved_28|>": 32043,
|
33 |
+
"<|reserved_29|>": 32044,
|
34 |
+
"<|reserved_2|>": 32017,
|
35 |
+
"<|reserved_30|>": 32045,
|
36 |
+
"<|reserved_31|>": 32046,
|
37 |
+
"<|reserved_32|>": 32047,
|
38 |
+
"<|reserved_33|>": 32048,
|
39 |
+
"<|reserved_34|>": 32049,
|
40 |
+
"<|reserved_35|>": 32050,
|
41 |
+
"<|reserved_36|>": 32051,
|
42 |
+
"<|reserved_37|>": 32052,
|
43 |
+
"<|reserved_38|>": 32053,
|
44 |
+
"<|reserved_39|>": 32054,
|
45 |
+
"<|reserved_3|>": 32018,
|
46 |
+
"<|reserved_40|>": 32055,
|
47 |
+
"<|reserved_41|>": 32056,
|
48 |
+
"<|reserved_42|>": 32057,
|
49 |
+
"<|reserved_43|>": 32058,
|
50 |
+
"<|reserved_44|>": 32059,
|
51 |
+
"<|reserved_45|>": 32060,
|
52 |
+
"<|reserved_46|>": 32061,
|
53 |
+
"<|reserved_47|>": 32062,
|
54 |
+
"<|reserved_48|>": 32063,
|
55 |
+
"<|reserved_4|>": 32019,
|
56 |
+
"<|reserved_5|>": 32020,
|
57 |
+
"<|reserved_6|>": 32021,
|
58 |
+
"<|reserved_7|>": 32022,
|
59 |
+
"<|reserved_8|>": 32023,
|
60 |
+
"<|reserved_9|>": 32024,
|
61 |
+
"<|start_header_id|>": 32012,
|
62 |
+
"<|system|>": 32009,
|
63 |
+
"<|user|>": 32008,
|
64 |
+
"[/INST]": 32005,
|
65 |
+
"[INST]": 32004
|
66 |
+
}
|
outputs/qlora-out/checkpoint-1770/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: pints-ai/1.5-Pints-16K-v0.1
|
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 0.12.0
|
outputs/qlora-out/checkpoint-1770/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "pints-ai/1.5-Pints-16K-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"down_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
outputs/qlora-out/checkpoint-1770/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d3f6cfd4acc6d90b3ebd846da78785c422fbf5297507ad24cc8bf794ea29622
|
3 |
+
size 133738248
|
outputs/qlora-out/checkpoint-1770/added_tokens.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 32003,
|
3 |
+
"<</SYS>>": 32007,
|
4 |
+
"<<SYS>>": 32006,
|
5 |
+
"<|assistant|>": 32010,
|
6 |
+
"<|begin_of_text|>": 32011,
|
7 |
+
"<|end_header_id|>": 32013,
|
8 |
+
"<|end_of_turn|>": 32000,
|
9 |
+
"<|eot_id|>": 32014,
|
10 |
+
"<|im_start|>": 32002,
|
11 |
+
"<|pad|>": 32001,
|
12 |
+
"<|reserved_0|>": 32015,
|
13 |
+
"<|reserved_10|>": 32025,
|
14 |
+
"<|reserved_11|>": 32026,
|
15 |
+
"<|reserved_12|>": 32027,
|
16 |
+
"<|reserved_13|>": 32028,
|
17 |
+
"<|reserved_14|>": 32029,
|
18 |
+
"<|reserved_15|>": 32030,
|
19 |
+
"<|reserved_16|>": 32031,
|
20 |
+
"<|reserved_17|>": 32032,
|
21 |
+
"<|reserved_18|>": 32033,
|
22 |
+
"<|reserved_19|>": 32034,
|
23 |
+
"<|reserved_1|>": 32016,
|
24 |
+
"<|reserved_20|>": 32035,
|
25 |
+
"<|reserved_21|>": 32036,
|
26 |
+
"<|reserved_22|>": 32037,
|
27 |
+
"<|reserved_23|>": 32038,
|
28 |
+
"<|reserved_24|>": 32039,
|
29 |
+
"<|reserved_25|>": 32040,
|
30 |
+
"<|reserved_26|>": 32041,
|
31 |
+
"<|reserved_27|>": 32042,
|
32 |
+
"<|reserved_28|>": 32043,
|
33 |
+
"<|reserved_29|>": 32044,
|
34 |
+
"<|reserved_2|>": 32017,
|
35 |
+
"<|reserved_30|>": 32045,
|
36 |
+
"<|reserved_31|>": 32046,
|
37 |
+
"<|reserved_32|>": 32047,
|
38 |
+
"<|reserved_33|>": 32048,
|
39 |
+
"<|reserved_34|>": 32049,
|
40 |
+
"<|reserved_35|>": 32050,
|
41 |
+
"<|reserved_36|>": 32051,
|
42 |
+
"<|reserved_37|>": 32052,
|
43 |
+
"<|reserved_38|>": 32053,
|
44 |
+
"<|reserved_39|>": 32054,
|
45 |
+
"<|reserved_3|>": 32018,
|
46 |
+
"<|reserved_40|>": 32055,
|
47 |
+
"<|reserved_41|>": 32056,
|
48 |
+
"<|reserved_42|>": 32057,
|
49 |
+
"<|reserved_43|>": 32058,
|
50 |
+
"<|reserved_44|>": 32059,
|
51 |
+
"<|reserved_45|>": 32060,
|
52 |
+
"<|reserved_46|>": 32061,
|
53 |
+
"<|reserved_47|>": 32062,
|
54 |
+
"<|reserved_48|>": 32063,
|
55 |
+
"<|reserved_4|>": 32019,
|
56 |
+
"<|reserved_5|>": 32020,
|
57 |
+
"<|reserved_6|>": 32021,
|
58 |
+
"<|reserved_7|>": 32022,
|
59 |
+
"<|reserved_8|>": 32023,
|
60 |
+
"<|reserved_9|>": 32024,
|
61 |
+
"<|start_header_id|>": 32012,
|
62 |
+
"<|system|>": 32009,
|
63 |
+
"<|user|>": 32008,
|
64 |
+
"[/INST]": 32005,
|
65 |
+
"[INST]": 32004
|
66 |
+
}
|
outputs/qlora-out/checkpoint-1770/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b556bdf23411dd79ef7932f09af007b6182396dd9f084078ddcea7ca4e02864d
|
3 |
+
size 267588602
|
outputs/qlora-out/checkpoint-1770/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e19eed6ccdff65c8328192415eeed52a6272dd6ac2c44fdac8311d21e184ed12
|
3 |
+
size 14244
|
outputs/qlora-out/checkpoint-1770/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1aede9b7596887b57f2060be4a0df18b4c81589b5af9f4bf019ac98bf6cd60e
|
3 |
+
size 1064
|
outputs/qlora-out/checkpoint-1770/special_tokens_map.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|end_of_turn|>",
|
4 |
+
"<|im_start|>",
|
5 |
+
"</s>",
|
6 |
+
"[INST]",
|
7 |
+
"[/INST]",
|
8 |
+
"<<SYS>>",
|
9 |
+
"<</SYS>>",
|
10 |
+
"<|user|>",
|
11 |
+
"<|system|>",
|
12 |
+
"<|assistant|>",
|
13 |
+
"<|begin_of_text|>",
|
14 |
+
"<|start_header_id|>",
|
15 |
+
"<|end_header_id|>",
|
16 |
+
"<|eot_id|>",
|
17 |
+
"<|reserved_0|>",
|
18 |
+
"<|reserved_1|>",
|
19 |
+
"<|reserved_2|>",
|
20 |
+
"<|reserved_3|>",
|
21 |
+
"<|reserved_4|>",
|
22 |
+
"<|reserved_5|>",
|
23 |
+
"<|reserved_6|>",
|
24 |
+
"<|reserved_7|>",
|
25 |
+
"<|reserved_8|>",
|
26 |
+
"<|reserved_9|>",
|
27 |
+
"<|reserved_10|>",
|
28 |
+
"<|reserved_11|>",
|
29 |
+
"<|reserved_12|>",
|
30 |
+
"<|reserved_13|>",
|
31 |
+
"<|reserved_14|>",
|
32 |
+
"<|reserved_15|>",
|
33 |
+
"<|reserved_16|>",
|
34 |
+
"<|reserved_17|>",
|
35 |
+
"<|reserved_18|>",
|
36 |
+
"<|reserved_19|>",
|
37 |
+
"<|reserved_20|>",
|
38 |
+
"<|reserved_21|>",
|
39 |
+
"<|reserved_22|>",
|
40 |
+
"<|reserved_23|>",
|
41 |
+
"<|reserved_24|>",
|
42 |
+
"<|reserved_25|>",
|
43 |
+
"<|reserved_26|>",
|
44 |
+
"<|reserved_27|>",
|
45 |
+
"<|reserved_28|>",
|
46 |
+
"<|reserved_29|>",
|
47 |
+
"<|reserved_30|>",
|
48 |
+
"<|reserved_31|>",
|
49 |
+
"<|reserved_32|>",
|
50 |
+
"<|reserved_33|>",
|
51 |
+
"<|reserved_34|>",
|
52 |
+
"<|reserved_35|>",
|
53 |
+
"<|reserved_36|>",
|
54 |
+
"<|reserved_37|>",
|
55 |
+
"<|reserved_38|>",
|
56 |
+
"<|reserved_39|>",
|
57 |
+
"<|reserved_40|>",
|
58 |
+
"<|reserved_41|>",
|
59 |
+
"<|reserved_42|>",
|
60 |
+
"<|reserved_43|>",
|
61 |
+
"<|reserved_44|>",
|
62 |
+
"<|reserved_45|>",
|
63 |
+
"<|reserved_46|>",
|
64 |
+
"<|reserved_47|>",
|
65 |
+
"<|reserved_48|>"
|
66 |
+
],
|
67 |
+
"bos_token": {
|
68 |
+
"content": "<s>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false
|
73 |
+
},
|
74 |
+
"eos_token": {
|
75 |
+
"content": "<|im_end|>",
|
76 |
+
"lstrip": false,
|
77 |
+
"normalized": false,
|
78 |
+
"rstrip": false,
|
79 |
+
"single_word": false
|
80 |
+
},
|
81 |
+
"pad_token": {
|
82 |
+
"content": "<|pad|>",
|
83 |
+
"lstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"rstrip": false,
|
86 |
+
"single_word": false
|
87 |
+
},
|
88 |
+
"unk_token": {
|
89 |
+
"content": "<unk>",
|
90 |
+
"lstrip": false,
|
91 |
+
"normalized": false,
|
92 |
+
"rstrip": false,
|
93 |
+
"single_word": false
|
94 |
+
}
|
95 |
+
}
|
outputs/qlora-out/checkpoint-1770/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
outputs/qlora-out/checkpoint-1770/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
outputs/qlora-out/checkpoint-1770/tokenizer_config.json
ADDED
@@ -0,0 +1,624 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<|im_end|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|end_of_turn|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|pad|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|im_start|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "</s>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "[INST]",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "[/INST]",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<<SYS>>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<</SYS>>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|user|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|system|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|assistant|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32011": {
|
119 |
+
"content": "<|begin_of_text|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": true
|
125 |
+
},
|
126 |
+
"32012": {
|
127 |
+
"content": "<|start_header_id|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"32013": {
|
135 |
+
"content": "<|end_header_id|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"32014": {
|
143 |
+
"content": "<|eot_id|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"32015": {
|
151 |
+
"content": "<|reserved_0|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"32016": {
|
159 |
+
"content": "<|reserved_1|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"32017": {
|
167 |
+
"content": "<|reserved_2|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"32018": {
|
175 |
+
"content": "<|reserved_3|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"32019": {
|
183 |
+
"content": "<|reserved_4|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"32020": {
|
191 |
+
"content": "<|reserved_5|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"32021": {
|
199 |
+
"content": "<|reserved_6|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"32022": {
|
207 |
+
"content": "<|reserved_7|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"32023": {
|
215 |
+
"content": "<|reserved_8|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"32024": {
|
223 |
+
"content": "<|reserved_9|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"32025": {
|
231 |
+
"content": "<|reserved_10|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"32026": {
|
239 |
+
"content": "<|reserved_11|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"32027": {
|
247 |
+
"content": "<|reserved_12|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"32028": {
|
255 |
+
"content": "<|reserved_13|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"32029": {
|
263 |
+
"content": "<|reserved_14|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"32030": {
|
271 |
+
"content": "<|reserved_15|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"32031": {
|
279 |
+
"content": "<|reserved_16|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"32032": {
|
287 |
+
"content": "<|reserved_17|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"32033": {
|
295 |
+
"content": "<|reserved_18|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"32034": {
|
303 |
+
"content": "<|reserved_19|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"32035": {
|
311 |
+
"content": "<|reserved_20|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"32036": {
|
319 |
+
"content": "<|reserved_21|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"32037": {
|
327 |
+
"content": "<|reserved_22|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"32038": {
|
335 |
+
"content": "<|reserved_23|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"32039": {
|
343 |
+
"content": "<|reserved_24|>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"32040": {
|
351 |
+
"content": "<|reserved_25|>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"32041": {
|
359 |
+
"content": "<|reserved_26|>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"32042": {
|
367 |
+
"content": "<|reserved_27|>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"32043": {
|
375 |
+
"content": "<|reserved_28|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"32044": {
|
383 |
+
"content": "<|reserved_29|>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"32045": {
|
391 |
+
"content": "<|reserved_30|>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"32046": {
|
399 |
+
"content": "<|reserved_31|>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"32047": {
|
407 |
+
"content": "<|reserved_32|>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"32048": {
|
415 |
+
"content": "<|reserved_33|>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"32049": {
|
423 |
+
"content": "<|reserved_34|>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"32050": {
|
431 |
+
"content": "<|reserved_35|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"32051": {
|
439 |
+
"content": "<|reserved_36|>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"32052": {
|
447 |
+
"content": "<|reserved_37|>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"32053": {
|
455 |
+
"content": "<|reserved_38|>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"32054": {
|
463 |
+
"content": "<|reserved_39|>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"32055": {
|
471 |
+
"content": "<|reserved_40|>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"32056": {
|
479 |
+
"content": "<|reserved_41|>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"32057": {
|
487 |
+
"content": "<|reserved_42|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"32058": {
|
495 |
+
"content": "<|reserved_43|>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"32059": {
|
503 |
+
"content": "<|reserved_44|>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"32060": {
|
511 |
+
"content": "<|reserved_45|>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"32061": {
|
519 |
+
"content": "<|reserved_46|>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"32062": {
|
527 |
+
"content": "<|reserved_47|>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"32063": {
|
535 |
+
"content": "<|reserved_48|>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
}
|
542 |
+
},
|
543 |
+
"additional_special_tokens": [
|
544 |
+
"<|end_of_turn|>",
|
545 |
+
"<|im_start|>",
|
546 |
+
"</s>",
|
547 |
+
"[INST]",
|
548 |
+
"[/INST]",
|
549 |
+
"<<SYS>>",
|
550 |
+
"<</SYS>>",
|
551 |
+
"<|user|>",
|
552 |
+
"<|system|>",
|
553 |
+
"<|assistant|>",
|
554 |
+
"<|begin_of_text|>",
|
555 |
+
"<|start_header_id|>",
|
556 |
+
"<|end_header_id|>",
|
557 |
+
"<|eot_id|>",
|
558 |
+
"<|reserved_0|>",
|
559 |
+
"<|reserved_1|>",
|
560 |
+
"<|reserved_2|>",
|
561 |
+
"<|reserved_3|>",
|
562 |
+
"<|reserved_4|>",
|
563 |
+
"<|reserved_5|>",
|
564 |
+
"<|reserved_6|>",
|
565 |
+
"<|reserved_7|>",
|
566 |
+
"<|reserved_8|>",
|
567 |
+
"<|reserved_9|>",
|
568 |
+
"<|reserved_10|>",
|
569 |
+
"<|reserved_11|>",
|
570 |
+
"<|reserved_12|>",
|
571 |
+
"<|reserved_13|>",
|
572 |
+
"<|reserved_14|>",
|
573 |
+
"<|reserved_15|>",
|
574 |
+
"<|reserved_16|>",
|
575 |
+
"<|reserved_17|>",
|
576 |
+
"<|reserved_18|>",
|
577 |
+
"<|reserved_19|>",
|
578 |
+
"<|reserved_20|>",
|
579 |
+
"<|reserved_21|>",
|
580 |
+
"<|reserved_22|>",
|
581 |
+
"<|reserved_23|>",
|
582 |
+
"<|reserved_24|>",
|
583 |
+
"<|reserved_25|>",
|
584 |
+
"<|reserved_26|>",
|
585 |
+
"<|reserved_27|>",
|
586 |
+
"<|reserved_28|>",
|
587 |
+
"<|reserved_29|>",
|
588 |
+
"<|reserved_30|>",
|
589 |
+
"<|reserved_31|>",
|
590 |
+
"<|reserved_32|>",
|
591 |
+
"<|reserved_33|>",
|
592 |
+
"<|reserved_34|>",
|
593 |
+
"<|reserved_35|>",
|
594 |
+
"<|reserved_36|>",
|
595 |
+
"<|reserved_37|>",
|
596 |
+
"<|reserved_38|>",
|
597 |
+
"<|reserved_39|>",
|
598 |
+
"<|reserved_40|>",
|
599 |
+
"<|reserved_41|>",
|
600 |
+
"<|reserved_42|>",
|
601 |
+
"<|reserved_43|>",
|
602 |
+
"<|reserved_44|>",
|
603 |
+
"<|reserved_45|>",
|
604 |
+
"<|reserved_46|>",
|
605 |
+
"<|reserved_47|>",
|
606 |
+
"<|reserved_48|>"
|
607 |
+
],
|
608 |
+
"bos_token": "<s>",
|
609 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
610 |
+
"clean_up_tokenization_spaces": false,
|
611 |
+
"eos_token": "<|im_end|>",
|
612 |
+
"kwargs": {
|
613 |
+
"eos_token": "<|im_end|>",
|
614 |
+
"pad_token": "<|pad|>",
|
615 |
+
"padding_side": "right"
|
616 |
+
},
|
617 |
+
"legacy": true,
|
618 |
+
"model_max_length": 1000000000000000019884624838656,
|
619 |
+
"pad_token": "<|pad|>",
|
620 |
+
"padding_side": "right",
|
621 |
+
"tokenizer_class": "LlamaTokenizer",
|
622 |
+
"unk_token": "<unk>",
|
623 |
+
"use_default_system_prompt": false
|
624 |
+
}
|
outputs/qlora-out/checkpoint-1770/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
outputs/qlora-out/checkpoint-1770/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:089334a0922ad97e570f8826b20779ffd6329eb41dd74a6eac13cb0480334265
|
3 |
+
size 6136
|
outputs/qlora-out/checkpoint-2655/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: pints-ai/1.5-Pints-16K-v0.1
|
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 0.12.0
|
outputs/qlora-out/checkpoint-2655/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "pints-ai/1.5-Pints-16K-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"down_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
outputs/qlora-out/checkpoint-2655/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fbffc182382229140b094cff219a39a41edac05309339ebe6a3ecf67b90a949
|
3 |
+
size 133738248
|
outputs/qlora-out/checkpoint-2655/added_tokens.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 32003,
|
3 |
+
"<</SYS>>": 32007,
|
4 |
+
"<<SYS>>": 32006,
|
5 |
+
"<|assistant|>": 32010,
|
6 |
+
"<|begin_of_text|>": 32011,
|
7 |
+
"<|end_header_id|>": 32013,
|
8 |
+
"<|end_of_turn|>": 32000,
|
9 |
+
"<|eot_id|>": 32014,
|
10 |
+
"<|im_start|>": 32002,
|
11 |
+
"<|pad|>": 32001,
|
12 |
+
"<|reserved_0|>": 32015,
|
13 |
+
"<|reserved_10|>": 32025,
|
14 |
+
"<|reserved_11|>": 32026,
|
15 |
+
"<|reserved_12|>": 32027,
|
16 |
+
"<|reserved_13|>": 32028,
|
17 |
+
"<|reserved_14|>": 32029,
|
18 |
+
"<|reserved_15|>": 32030,
|
19 |
+
"<|reserved_16|>": 32031,
|
20 |
+
"<|reserved_17|>": 32032,
|
21 |
+
"<|reserved_18|>": 32033,
|
22 |
+
"<|reserved_19|>": 32034,
|
23 |
+
"<|reserved_1|>": 32016,
|
24 |
+
"<|reserved_20|>": 32035,
|
25 |
+
"<|reserved_21|>": 32036,
|
26 |
+
"<|reserved_22|>": 32037,
|
27 |
+
"<|reserved_23|>": 32038,
|
28 |
+
"<|reserved_24|>": 32039,
|
29 |
+
"<|reserved_25|>": 32040,
|
30 |
+
"<|reserved_26|>": 32041,
|
31 |
+
"<|reserved_27|>": 32042,
|
32 |
+
"<|reserved_28|>": 32043,
|
33 |
+
"<|reserved_29|>": 32044,
|
34 |
+
"<|reserved_2|>": 32017,
|
35 |
+
"<|reserved_30|>": 32045,
|
36 |
+
"<|reserved_31|>": 32046,
|
37 |
+
"<|reserved_32|>": 32047,
|
38 |
+
"<|reserved_33|>": 32048,
|
39 |
+
"<|reserved_34|>": 32049,
|
40 |
+
"<|reserved_35|>": 32050,
|
41 |
+
"<|reserved_36|>": 32051,
|
42 |
+
"<|reserved_37|>": 32052,
|
43 |
+
"<|reserved_38|>": 32053,
|
44 |
+
"<|reserved_39|>": 32054,
|
45 |
+
"<|reserved_3|>": 32018,
|
46 |
+
"<|reserved_40|>": 32055,
|
47 |
+
"<|reserved_41|>": 32056,
|
48 |
+
"<|reserved_42|>": 32057,
|
49 |
+
"<|reserved_43|>": 32058,
|
50 |
+
"<|reserved_44|>": 32059,
|
51 |
+
"<|reserved_45|>": 32060,
|
52 |
+
"<|reserved_46|>": 32061,
|
53 |
+
"<|reserved_47|>": 32062,
|
54 |
+
"<|reserved_48|>": 32063,
|
55 |
+
"<|reserved_4|>": 32019,
|
56 |
+
"<|reserved_5|>": 32020,
|
57 |
+
"<|reserved_6|>": 32021,
|
58 |
+
"<|reserved_7|>": 32022,
|
59 |
+
"<|reserved_8|>": 32023,
|
60 |
+
"<|reserved_9|>": 32024,
|
61 |
+
"<|start_header_id|>": 32012,
|
62 |
+
"<|system|>": 32009,
|
63 |
+
"<|user|>": 32008,
|
64 |
+
"[/INST]": 32005,
|
65 |
+
"[INST]": 32004
|
66 |
+
}
|
outputs/qlora-out/checkpoint-2655/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fea9e4e7ab1743c9420a3c25690441525b3a39a61bde2fe1c2886a625f693936
|
3 |
+
size 267588602
|
outputs/qlora-out/checkpoint-2655/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e78bbba3eb8eb8984d3755d22e323caba264ef35e573d480b8ed95c403ccda4
|
3 |
+
size 14244
|
outputs/qlora-out/checkpoint-2655/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28ffcd1421447d082b0ae5e9499c34bfd6f4073d881994bbc20b3ae8983d1dcf
|
3 |
+
size 1064
|
outputs/qlora-out/checkpoint-2655/special_tokens_map.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|end_of_turn|>",
|
4 |
+
"<|im_start|>",
|
5 |
+
"</s>",
|
6 |
+
"[INST]",
|
7 |
+
"[/INST]",
|
8 |
+
"<<SYS>>",
|
9 |
+
"<</SYS>>",
|
10 |
+
"<|user|>",
|
11 |
+
"<|system|>",
|
12 |
+
"<|assistant|>",
|
13 |
+
"<|begin_of_text|>",
|
14 |
+
"<|start_header_id|>",
|
15 |
+
"<|end_header_id|>",
|
16 |
+
"<|eot_id|>",
|
17 |
+
"<|reserved_0|>",
|
18 |
+
"<|reserved_1|>",
|
19 |
+
"<|reserved_2|>",
|
20 |
+
"<|reserved_3|>",
|
21 |
+
"<|reserved_4|>",
|
22 |
+
"<|reserved_5|>",
|
23 |
+
"<|reserved_6|>",
|
24 |
+
"<|reserved_7|>",
|
25 |
+
"<|reserved_8|>",
|
26 |
+
"<|reserved_9|>",
|
27 |
+
"<|reserved_10|>",
|
28 |
+
"<|reserved_11|>",
|
29 |
+
"<|reserved_12|>",
|
30 |
+
"<|reserved_13|>",
|
31 |
+
"<|reserved_14|>",
|
32 |
+
"<|reserved_15|>",
|
33 |
+
"<|reserved_16|>",
|
34 |
+
"<|reserved_17|>",
|
35 |
+
"<|reserved_18|>",
|
36 |
+
"<|reserved_19|>",
|
37 |
+
"<|reserved_20|>",
|
38 |
+
"<|reserved_21|>",
|
39 |
+
"<|reserved_22|>",
|
40 |
+
"<|reserved_23|>",
|
41 |
+
"<|reserved_24|>",
|
42 |
+
"<|reserved_25|>",
|
43 |
+
"<|reserved_26|>",
|
44 |
+
"<|reserved_27|>",
|
45 |
+
"<|reserved_28|>",
|
46 |
+
"<|reserved_29|>",
|
47 |
+
"<|reserved_30|>",
|
48 |
+
"<|reserved_31|>",
|
49 |
+
"<|reserved_32|>",
|
50 |
+
"<|reserved_33|>",
|
51 |
+
"<|reserved_34|>",
|
52 |
+
"<|reserved_35|>",
|
53 |
+
"<|reserved_36|>",
|
54 |
+
"<|reserved_37|>",
|
55 |
+
"<|reserved_38|>",
|
56 |
+
"<|reserved_39|>",
|
57 |
+
"<|reserved_40|>",
|
58 |
+
"<|reserved_41|>",
|
59 |
+
"<|reserved_42|>",
|
60 |
+
"<|reserved_43|>",
|
61 |
+
"<|reserved_44|>",
|
62 |
+
"<|reserved_45|>",
|
63 |
+
"<|reserved_46|>",
|
64 |
+
"<|reserved_47|>",
|
65 |
+
"<|reserved_48|>"
|
66 |
+
],
|
67 |
+
"bos_token": {
|
68 |
+
"content": "<s>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false
|
73 |
+
},
|
74 |
+
"eos_token": {
|
75 |
+
"content": "<|im_end|>",
|
76 |
+
"lstrip": false,
|
77 |
+
"normalized": false,
|
78 |
+
"rstrip": false,
|
79 |
+
"single_word": false
|
80 |
+
},
|
81 |
+
"pad_token": {
|
82 |
+
"content": "<|pad|>",
|
83 |
+
"lstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"rstrip": false,
|
86 |
+
"single_word": false
|
87 |
+
},
|
88 |
+
"unk_token": {
|
89 |
+
"content": "<unk>",
|
90 |
+
"lstrip": false,
|
91 |
+
"normalized": false,
|
92 |
+
"rstrip": false,
|
93 |
+
"single_word": false
|
94 |
+
}
|
95 |
+
}
|
outputs/qlora-out/checkpoint-2655/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
outputs/qlora-out/checkpoint-2655/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
outputs/qlora-out/checkpoint-2655/tokenizer_config.json
ADDED
@@ -0,0 +1,624 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<|im_end|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|end_of_turn|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|pad|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|im_start|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "</s>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "[INST]",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "[/INST]",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<<SYS>>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<</SYS>>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|user|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|system|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|assistant|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32011": {
|
119 |
+
"content": "<|begin_of_text|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": true
|
125 |
+
},
|
126 |
+
"32012": {
|
127 |
+
"content": "<|start_header_id|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"32013": {
|
135 |
+
"content": "<|end_header_id|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"32014": {
|
143 |
+
"content": "<|eot_id|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"32015": {
|
151 |
+
"content": "<|reserved_0|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"32016": {
|
159 |
+
"content": "<|reserved_1|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"32017": {
|
167 |
+
"content": "<|reserved_2|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"32018": {
|
175 |
+
"content": "<|reserved_3|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"32019": {
|
183 |
+
"content": "<|reserved_4|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"32020": {
|
191 |
+
"content": "<|reserved_5|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"32021": {
|
199 |
+
"content": "<|reserved_6|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"32022": {
|
207 |
+
"content": "<|reserved_7|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"32023": {
|
215 |
+
"content": "<|reserved_8|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"32024": {
|
223 |
+
"content": "<|reserved_9|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"32025": {
|
231 |
+
"content": "<|reserved_10|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"32026": {
|
239 |
+
"content": "<|reserved_11|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"32027": {
|
247 |
+
"content": "<|reserved_12|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"32028": {
|
255 |
+
"content": "<|reserved_13|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"32029": {
|
263 |
+
"content": "<|reserved_14|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"32030": {
|
271 |
+
"content": "<|reserved_15|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"32031": {
|
279 |
+
"content": "<|reserved_16|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"32032": {
|
287 |
+
"content": "<|reserved_17|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"32033": {
|
295 |
+
"content": "<|reserved_18|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"32034": {
|
303 |
+
"content": "<|reserved_19|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"32035": {
|
311 |
+
"content": "<|reserved_20|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"32036": {
|
319 |
+
"content": "<|reserved_21|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"32037": {
|
327 |
+
"content": "<|reserved_22|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"32038": {
|
335 |
+
"content": "<|reserved_23|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"32039": {
|
343 |
+
"content": "<|reserved_24|>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"32040": {
|
351 |
+
"content": "<|reserved_25|>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"32041": {
|
359 |
+
"content": "<|reserved_26|>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"32042": {
|
367 |
+
"content": "<|reserved_27|>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"32043": {
|
375 |
+
"content": "<|reserved_28|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"32044": {
|
383 |
+
"content": "<|reserved_29|>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"32045": {
|
391 |
+
"content": "<|reserved_30|>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"32046": {
|
399 |
+
"content": "<|reserved_31|>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"32047": {
|
407 |
+
"content": "<|reserved_32|>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"32048": {
|
415 |
+
"content": "<|reserved_33|>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"32049": {
|
423 |
+
"content": "<|reserved_34|>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"32050": {
|
431 |
+
"content": "<|reserved_35|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"32051": {
|
439 |
+
"content": "<|reserved_36|>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"32052": {
|
447 |
+
"content": "<|reserved_37|>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"32053": {
|
455 |
+
"content": "<|reserved_38|>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"32054": {
|
463 |
+
"content": "<|reserved_39|>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"32055": {
|
471 |
+
"content": "<|reserved_40|>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"32056": {
|
479 |
+
"content": "<|reserved_41|>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"32057": {
|
487 |
+
"content": "<|reserved_42|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"32058": {
|
495 |
+
"content": "<|reserved_43|>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"32059": {
|
503 |
+
"content": "<|reserved_44|>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"32060": {
|
511 |
+
"content": "<|reserved_45|>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"32061": {
|
519 |
+
"content": "<|reserved_46|>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"32062": {
|
527 |
+
"content": "<|reserved_47|>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"32063": {
|
535 |
+
"content": "<|reserved_48|>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
}
|
542 |
+
},
|
543 |
+
"additional_special_tokens": [
|
544 |
+
"<|end_of_turn|>",
|
545 |
+
"<|im_start|>",
|
546 |
+
"</s>",
|
547 |
+
"[INST]",
|
548 |
+
"[/INST]",
|
549 |
+
"<<SYS>>",
|
550 |
+
"<</SYS>>",
|
551 |
+
"<|user|>",
|
552 |
+
"<|system|>",
|
553 |
+
"<|assistant|>",
|
554 |
+
"<|begin_of_text|>",
|
555 |
+
"<|start_header_id|>",
|
556 |
+
"<|end_header_id|>",
|
557 |
+
"<|eot_id|>",
|
558 |
+
"<|reserved_0|>",
|
559 |
+
"<|reserved_1|>",
|
560 |
+
"<|reserved_2|>",
|
561 |
+
"<|reserved_3|>",
|
562 |
+
"<|reserved_4|>",
|
563 |
+
"<|reserved_5|>",
|
564 |
+
"<|reserved_6|>",
|
565 |
+
"<|reserved_7|>",
|
566 |
+
"<|reserved_8|>",
|
567 |
+
"<|reserved_9|>",
|
568 |
+
"<|reserved_10|>",
|
569 |
+
"<|reserved_11|>",
|
570 |
+
"<|reserved_12|>",
|
571 |
+
"<|reserved_13|>",
|
572 |
+
"<|reserved_14|>",
|
573 |
+
"<|reserved_15|>",
|
574 |
+
"<|reserved_16|>",
|
575 |
+
"<|reserved_17|>",
|
576 |
+
"<|reserved_18|>",
|
577 |
+
"<|reserved_19|>",
|
578 |
+
"<|reserved_20|>",
|
579 |
+
"<|reserved_21|>",
|
580 |
+
"<|reserved_22|>",
|
581 |
+
"<|reserved_23|>",
|
582 |
+
"<|reserved_24|>",
|
583 |
+
"<|reserved_25|>",
|
584 |
+
"<|reserved_26|>",
|
585 |
+
"<|reserved_27|>",
|
586 |
+
"<|reserved_28|>",
|
587 |
+
"<|reserved_29|>",
|
588 |
+
"<|reserved_30|>",
|
589 |
+
"<|reserved_31|>",
|
590 |
+
"<|reserved_32|>",
|
591 |
+
"<|reserved_33|>",
|
592 |
+
"<|reserved_34|>",
|
593 |
+
"<|reserved_35|>",
|
594 |
+
"<|reserved_36|>",
|
595 |
+
"<|reserved_37|>",
|
596 |
+
"<|reserved_38|>",
|
597 |
+
"<|reserved_39|>",
|
598 |
+
"<|reserved_40|>",
|
599 |
+
"<|reserved_41|>",
|
600 |
+
"<|reserved_42|>",
|
601 |
+
"<|reserved_43|>",
|
602 |
+
"<|reserved_44|>",
|
603 |
+
"<|reserved_45|>",
|
604 |
+
"<|reserved_46|>",
|
605 |
+
"<|reserved_47|>",
|
606 |
+
"<|reserved_48|>"
|
607 |
+
],
|
608 |
+
"bos_token": "<s>",
|
609 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
610 |
+
"clean_up_tokenization_spaces": false,
|
611 |
+
"eos_token": "<|im_end|>",
|
612 |
+
"kwargs": {
|
613 |
+
"eos_token": "<|im_end|>",
|
614 |
+
"pad_token": "<|pad|>",
|
615 |
+
"padding_side": "right"
|
616 |
+
},
|
617 |
+
"legacy": true,
|
618 |
+
"model_max_length": 1000000000000000019884624838656,
|
619 |
+
"pad_token": "<|pad|>",
|
620 |
+
"padding_side": "right",
|
621 |
+
"tokenizer_class": "LlamaTokenizer",
|
622 |
+
"unk_token": "<unk>",
|
623 |
+
"use_default_system_prompt": false
|
624 |
+
}
|
outputs/qlora-out/checkpoint-2655/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
outputs/qlora-out/checkpoint-2655/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:089334a0922ad97e570f8826b20779ffd6329eb41dd74a6eac13cb0480334265
|
3 |
+
size 6136
|
outputs/qlora-out/checkpoint-885/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: pints-ai/1.5-Pints-16K-v0.1
|
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 0.12.0
|
outputs/qlora-out/checkpoint-885/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "pints-ai/1.5-Pints-16K-v0.1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"down_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"o_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
outputs/qlora-out/checkpoint-885/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0b36e4e2f980133e716b0b138e4857b76b8b12ea3a3a7ffd686d6bd230e76b1
|
3 |
+
size 133738248
|
outputs/qlora-out/checkpoint-885/added_tokens.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 32003,
|
3 |
+
"<</SYS>>": 32007,
|
4 |
+
"<<SYS>>": 32006,
|
5 |
+
"<|assistant|>": 32010,
|
6 |
+
"<|begin_of_text|>": 32011,
|
7 |
+
"<|end_header_id|>": 32013,
|
8 |
+
"<|end_of_turn|>": 32000,
|
9 |
+
"<|eot_id|>": 32014,
|
10 |
+
"<|im_start|>": 32002,
|
11 |
+
"<|pad|>": 32001,
|
12 |
+
"<|reserved_0|>": 32015,
|
13 |
+
"<|reserved_10|>": 32025,
|
14 |
+
"<|reserved_11|>": 32026,
|
15 |
+
"<|reserved_12|>": 32027,
|
16 |
+
"<|reserved_13|>": 32028,
|
17 |
+
"<|reserved_14|>": 32029,
|
18 |
+
"<|reserved_15|>": 32030,
|
19 |
+
"<|reserved_16|>": 32031,
|
20 |
+
"<|reserved_17|>": 32032,
|
21 |
+
"<|reserved_18|>": 32033,
|
22 |
+
"<|reserved_19|>": 32034,
|
23 |
+
"<|reserved_1|>": 32016,
|
24 |
+
"<|reserved_20|>": 32035,
|
25 |
+
"<|reserved_21|>": 32036,
|
26 |
+
"<|reserved_22|>": 32037,
|
27 |
+
"<|reserved_23|>": 32038,
|
28 |
+
"<|reserved_24|>": 32039,
|
29 |
+
"<|reserved_25|>": 32040,
|
30 |
+
"<|reserved_26|>": 32041,
|
31 |
+
"<|reserved_27|>": 32042,
|
32 |
+
"<|reserved_28|>": 32043,
|
33 |
+
"<|reserved_29|>": 32044,
|
34 |
+
"<|reserved_2|>": 32017,
|
35 |
+
"<|reserved_30|>": 32045,
|
36 |
+
"<|reserved_31|>": 32046,
|
37 |
+
"<|reserved_32|>": 32047,
|
38 |
+
"<|reserved_33|>": 32048,
|
39 |
+
"<|reserved_34|>": 32049,
|
40 |
+
"<|reserved_35|>": 32050,
|
41 |
+
"<|reserved_36|>": 32051,
|
42 |
+
"<|reserved_37|>": 32052,
|
43 |
+
"<|reserved_38|>": 32053,
|
44 |
+
"<|reserved_39|>": 32054,
|
45 |
+
"<|reserved_3|>": 32018,
|
46 |
+
"<|reserved_40|>": 32055,
|
47 |
+
"<|reserved_41|>": 32056,
|
48 |
+
"<|reserved_42|>": 32057,
|
49 |
+
"<|reserved_43|>": 32058,
|
50 |
+
"<|reserved_44|>": 32059,
|
51 |
+
"<|reserved_45|>": 32060,
|
52 |
+
"<|reserved_46|>": 32061,
|
53 |
+
"<|reserved_47|>": 32062,
|
54 |
+
"<|reserved_48|>": 32063,
|
55 |
+
"<|reserved_4|>": 32019,
|
56 |
+
"<|reserved_5|>": 32020,
|
57 |
+
"<|reserved_6|>": 32021,
|
58 |
+
"<|reserved_7|>": 32022,
|
59 |
+
"<|reserved_8|>": 32023,
|
60 |
+
"<|reserved_9|>": 32024,
|
61 |
+
"<|start_header_id|>": 32012,
|
62 |
+
"<|system|>": 32009,
|
63 |
+
"<|user|>": 32008,
|
64 |
+
"[/INST]": 32005,
|
65 |
+
"[INST]": 32004
|
66 |
+
}
|
outputs/qlora-out/checkpoint-885/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4b43eb65158dc64f4f36a4a4acf41a7698b3caad16ba97da113814e3fc59d67
|
3 |
+
size 267588602
|
outputs/qlora-out/checkpoint-885/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cccf684fffae258855c59b72c743d37f78e5613387f4e385b6b1ca2bfcee05f
|
3 |
+
size 14244
|
outputs/qlora-out/checkpoint-885/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9b0e6fdc025a3e4124d17d280499710742dfe4665858ba49221bacc11285e28
|
3 |
+
size 1064
|
outputs/qlora-out/checkpoint-885/special_tokens_map.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|end_of_turn|>",
|
4 |
+
"<|im_start|>",
|
5 |
+
"</s>",
|
6 |
+
"[INST]",
|
7 |
+
"[/INST]",
|
8 |
+
"<<SYS>>",
|
9 |
+
"<</SYS>>",
|
10 |
+
"<|user|>",
|
11 |
+
"<|system|>",
|
12 |
+
"<|assistant|>",
|
13 |
+
"<|begin_of_text|>",
|
14 |
+
"<|start_header_id|>",
|
15 |
+
"<|end_header_id|>",
|
16 |
+
"<|eot_id|>",
|
17 |
+
"<|reserved_0|>",
|
18 |
+
"<|reserved_1|>",
|
19 |
+
"<|reserved_2|>",
|
20 |
+
"<|reserved_3|>",
|
21 |
+
"<|reserved_4|>",
|
22 |
+
"<|reserved_5|>",
|
23 |
+
"<|reserved_6|>",
|
24 |
+
"<|reserved_7|>",
|
25 |
+
"<|reserved_8|>",
|
26 |
+
"<|reserved_9|>",
|
27 |
+
"<|reserved_10|>",
|
28 |
+
"<|reserved_11|>",
|
29 |
+
"<|reserved_12|>",
|
30 |
+
"<|reserved_13|>",
|
31 |
+
"<|reserved_14|>",
|
32 |
+
"<|reserved_15|>",
|
33 |
+
"<|reserved_16|>",
|
34 |
+
"<|reserved_17|>",
|
35 |
+
"<|reserved_18|>",
|
36 |
+
"<|reserved_19|>",
|
37 |
+
"<|reserved_20|>",
|
38 |
+
"<|reserved_21|>",
|
39 |
+
"<|reserved_22|>",
|
40 |
+
"<|reserved_23|>",
|
41 |
+
"<|reserved_24|>",
|
42 |
+
"<|reserved_25|>",
|
43 |
+
"<|reserved_26|>",
|
44 |
+
"<|reserved_27|>",
|
45 |
+
"<|reserved_28|>",
|
46 |
+
"<|reserved_29|>",
|
47 |
+
"<|reserved_30|>",
|
48 |
+
"<|reserved_31|>",
|
49 |
+
"<|reserved_32|>",
|
50 |
+
"<|reserved_33|>",
|
51 |
+
"<|reserved_34|>",
|
52 |
+
"<|reserved_35|>",
|
53 |
+
"<|reserved_36|>",
|
54 |
+
"<|reserved_37|>",
|
55 |
+
"<|reserved_38|>",
|
56 |
+
"<|reserved_39|>",
|
57 |
+
"<|reserved_40|>",
|
58 |
+
"<|reserved_41|>",
|
59 |
+
"<|reserved_42|>",
|
60 |
+
"<|reserved_43|>",
|
61 |
+
"<|reserved_44|>",
|
62 |
+
"<|reserved_45|>",
|
63 |
+
"<|reserved_46|>",
|
64 |
+
"<|reserved_47|>",
|
65 |
+
"<|reserved_48|>"
|
66 |
+
],
|
67 |
+
"bos_token": {
|
68 |
+
"content": "<s>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false
|
73 |
+
},
|
74 |
+
"eos_token": {
|
75 |
+
"content": "<|im_end|>",
|
76 |
+
"lstrip": false,
|
77 |
+
"normalized": false,
|
78 |
+
"rstrip": false,
|
79 |
+
"single_word": false
|
80 |
+
},
|
81 |
+
"pad_token": {
|
82 |
+
"content": "<|pad|>",
|
83 |
+
"lstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"rstrip": false,
|
86 |
+
"single_word": false
|
87 |
+
},
|
88 |
+
"unk_token": {
|
89 |
+
"content": "<unk>",
|
90 |
+
"lstrip": false,
|
91 |
+
"normalized": false,
|
92 |
+
"rstrip": false,
|
93 |
+
"single_word": false
|
94 |
+
}
|
95 |
+
}
|
outputs/qlora-out/checkpoint-885/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
outputs/qlora-out/checkpoint-885/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
outputs/qlora-out/checkpoint-885/tokenizer_config.json
ADDED
@@ -0,0 +1,624 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<|im_end|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|end_of_turn|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|pad|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|im_start|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "</s>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "[INST]",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "[/INST]",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<<SYS>>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<</SYS>>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|user|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|system|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|assistant|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32011": {
|
119 |
+
"content": "<|begin_of_text|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": true
|
125 |
+
},
|
126 |
+
"32012": {
|
127 |
+
"content": "<|start_header_id|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"32013": {
|
135 |
+
"content": "<|end_header_id|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"32014": {
|
143 |
+
"content": "<|eot_id|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"32015": {
|
151 |
+
"content": "<|reserved_0|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"32016": {
|
159 |
+
"content": "<|reserved_1|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"32017": {
|
167 |
+
"content": "<|reserved_2|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"32018": {
|
175 |
+
"content": "<|reserved_3|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"32019": {
|
183 |
+
"content": "<|reserved_4|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"32020": {
|
191 |
+
"content": "<|reserved_5|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"32021": {
|
199 |
+
"content": "<|reserved_6|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"32022": {
|
207 |
+
"content": "<|reserved_7|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"32023": {
|
215 |
+
"content": "<|reserved_8|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"32024": {
|
223 |
+
"content": "<|reserved_9|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"32025": {
|
231 |
+
"content": "<|reserved_10|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"32026": {
|
239 |
+
"content": "<|reserved_11|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"32027": {
|
247 |
+
"content": "<|reserved_12|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"32028": {
|
255 |
+
"content": "<|reserved_13|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"32029": {
|
263 |
+
"content": "<|reserved_14|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"32030": {
|
271 |
+
"content": "<|reserved_15|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"32031": {
|
279 |
+
"content": "<|reserved_16|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"32032": {
|
287 |
+
"content": "<|reserved_17|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"32033": {
|
295 |
+
"content": "<|reserved_18|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"32034": {
|
303 |
+
"content": "<|reserved_19|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"32035": {
|
311 |
+
"content": "<|reserved_20|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"32036": {
|
319 |
+
"content": "<|reserved_21|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"32037": {
|
327 |
+
"content": "<|reserved_22|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"32038": {
|
335 |
+
"content": "<|reserved_23|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"32039": {
|
343 |
+
"content": "<|reserved_24|>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"32040": {
|
351 |
+
"content": "<|reserved_25|>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"32041": {
|
359 |
+
"content": "<|reserved_26|>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"32042": {
|
367 |
+
"content": "<|reserved_27|>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"32043": {
|
375 |
+
"content": "<|reserved_28|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"32044": {
|
383 |
+
"content": "<|reserved_29|>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"32045": {
|
391 |
+
"content": "<|reserved_30|>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"32046": {
|
399 |
+
"content": "<|reserved_31|>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"32047": {
|
407 |
+
"content": "<|reserved_32|>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"32048": {
|
415 |
+
"content": "<|reserved_33|>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"32049": {
|
423 |
+
"content": "<|reserved_34|>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"32050": {
|
431 |
+
"content": "<|reserved_35|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"32051": {
|
439 |
+
"content": "<|reserved_36|>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"32052": {
|
447 |
+
"content": "<|reserved_37|>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"32053": {
|
455 |
+
"content": "<|reserved_38|>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"32054": {
|
463 |
+
"content": "<|reserved_39|>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"32055": {
|
471 |
+
"content": "<|reserved_40|>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"32056": {
|
479 |
+
"content": "<|reserved_41|>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"32057": {
|
487 |
+
"content": "<|reserved_42|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"32058": {
|
495 |
+
"content": "<|reserved_43|>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"32059": {
|
503 |
+
"content": "<|reserved_44|>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"32060": {
|
511 |
+
"content": "<|reserved_45|>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"32061": {
|
519 |
+
"content": "<|reserved_46|>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"32062": {
|
527 |
+
"content": "<|reserved_47|>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"32063": {
|
535 |
+
"content": "<|reserved_48|>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
}
|
542 |
+
},
|
543 |
+
"additional_special_tokens": [
|
544 |
+
"<|end_of_turn|>",
|
545 |
+
"<|im_start|>",
|
546 |
+
"</s>",
|
547 |
+
"[INST]",
|
548 |
+
"[/INST]",
|
549 |
+
"<<SYS>>",
|
550 |
+
"<</SYS>>",
|
551 |
+
"<|user|>",
|
552 |
+
"<|system|>",
|
553 |
+
"<|assistant|>",
|
554 |
+
"<|begin_of_text|>",
|
555 |
+
"<|start_header_id|>",
|
556 |
+
"<|end_header_id|>",
|
557 |
+
"<|eot_id|>",
|
558 |
+
"<|reserved_0|>",
|
559 |
+
"<|reserved_1|>",
|
560 |
+
"<|reserved_2|>",
|
561 |
+
"<|reserved_3|>",
|
562 |
+
"<|reserved_4|>",
|
563 |
+
"<|reserved_5|>",
|
564 |
+
"<|reserved_6|>",
|
565 |
+
"<|reserved_7|>",
|
566 |
+
"<|reserved_8|>",
|
567 |
+
"<|reserved_9|>",
|
568 |
+
"<|reserved_10|>",
|
569 |
+
"<|reserved_11|>",
|
570 |
+
"<|reserved_12|>",
|
571 |
+
"<|reserved_13|>",
|
572 |
+
"<|reserved_14|>",
|
573 |
+
"<|reserved_15|>",
|
574 |
+
"<|reserved_16|>",
|
575 |
+
"<|reserved_17|>",
|
576 |
+
"<|reserved_18|>",
|
577 |
+
"<|reserved_19|>",
|
578 |
+
"<|reserved_20|>",
|
579 |
+
"<|reserved_21|>",
|
580 |
+
"<|reserved_22|>",
|
581 |
+
"<|reserved_23|>",
|
582 |
+
"<|reserved_24|>",
|
583 |
+
"<|reserved_25|>",
|
584 |
+
"<|reserved_26|>",
|
585 |
+
"<|reserved_27|>",
|
586 |
+
"<|reserved_28|>",
|
587 |
+
"<|reserved_29|>",
|
588 |
+
"<|reserved_30|>",
|
589 |
+
"<|reserved_31|>",
|
590 |
+
"<|reserved_32|>",
|
591 |
+
"<|reserved_33|>",
|
592 |
+
"<|reserved_34|>",
|
593 |
+
"<|reserved_35|>",
|
594 |
+
"<|reserved_36|>",
|
595 |
+
"<|reserved_37|>",
|
596 |
+
"<|reserved_38|>",
|
597 |
+
"<|reserved_39|>",
|
598 |
+
"<|reserved_40|>",
|
599 |
+
"<|reserved_41|>",
|
600 |
+
"<|reserved_42|>",
|
601 |
+
"<|reserved_43|>",
|
602 |
+
"<|reserved_44|>",
|
603 |
+
"<|reserved_45|>",
|
604 |
+
"<|reserved_46|>",
|
605 |
+
"<|reserved_47|>",
|
606 |
+
"<|reserved_48|>"
|
607 |
+
],
|
608 |
+
"bos_token": "<s>",
|
609 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
610 |
+
"clean_up_tokenization_spaces": false,
|
611 |
+
"eos_token": "<|im_end|>",
|
612 |
+
"kwargs": {
|
613 |
+
"eos_token": "<|im_end|>",
|
614 |
+
"pad_token": "<|pad|>",
|
615 |
+
"padding_side": "right"
|
616 |
+
},
|
617 |
+
"legacy": true,
|
618 |
+
"model_max_length": 1000000000000000019884624838656,
|
619 |
+
"pad_token": "<|pad|>",
|
620 |
+
"padding_side": "right",
|
621 |
+
"tokenizer_class": "LlamaTokenizer",
|
622 |
+
"unk_token": "<unk>",
|
623 |
+
"use_default_system_prompt": false
|
624 |
+
}
|
outputs/qlora-out/checkpoint-885/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
outputs/qlora-out/checkpoint-885/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:089334a0922ad97e570f8826b20779ffd6329eb41dd74a6eac13cb0480334265
|
3 |
+
size 6136
|
outputs/qlora-out/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pints-ai/1.5-Pints-16K-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"head_dim": 64,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 2048,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 8192,
|
15 |
+
"max_position_embeddings": 16384,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "llama",
|
18 |
+
"num_attention_heads": 32,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"num_key_value_heads": 4,
|
21 |
+
"pad_token_id": 32001,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"quantization_config": {
|
24 |
+
"_load_in_4bit": true,
|
25 |
+
"_load_in_8bit": false,
|
26 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
27 |
+
"bnb_4bit_quant_storage": "bfloat16",
|
28 |
+
"bnb_4bit_quant_type": "nf4",
|
29 |
+
"bnb_4bit_use_double_quant": true,
|
30 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
31 |
+
"llm_int8_has_fp16_weight": false,
|
32 |
+
"llm_int8_skip_modules": null,
|
33 |
+
"llm_int8_threshold": 6.0,
|
34 |
+
"load_in_4bit": true,
|
35 |
+
"load_in_8bit": false,
|
36 |
+
"quant_method": "bitsandbytes"
|
37 |
+
},
|
38 |
+
"rms_norm_eps": 1e-05,
|
39 |
+
"rope_scaling": null,
|
40 |
+
"rope_theta": 10000.0,
|
41 |
+
"tie_word_embeddings": false,
|
42 |
+
"torch_dtype": "bfloat16",
|
43 |
+
"transformers_version": "4.45.0.dev0",
|
44 |
+
"use_cache": false,
|
45 |
+
"vocab_size": 32064
|
46 |
+
}
|
outputs/qlora-out/special_tokens_map.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|end_of_turn|>",
|
4 |
+
"<|im_start|>",
|
5 |
+
"</s>",
|
6 |
+
"[INST]",
|
7 |
+
"[/INST]",
|
8 |
+
"<<SYS>>",
|
9 |
+
"<</SYS>>",
|
10 |
+
"<|user|>",
|
11 |
+
"<|system|>",
|
12 |
+
"<|assistant|>",
|
13 |
+
"<|begin_of_text|>",
|
14 |
+
"<|start_header_id|>",
|
15 |
+
"<|end_header_id|>",
|
16 |
+
"<|eot_id|>",
|
17 |
+
"<|reserved_0|>",
|
18 |
+
"<|reserved_1|>",
|
19 |
+
"<|reserved_2|>",
|
20 |
+
"<|reserved_3|>",
|
21 |
+
"<|reserved_4|>",
|
22 |
+
"<|reserved_5|>",
|
23 |
+
"<|reserved_6|>",
|
24 |
+
"<|reserved_7|>",
|
25 |
+
"<|reserved_8|>",
|
26 |
+
"<|reserved_9|>",
|
27 |
+
"<|reserved_10|>",
|
28 |
+
"<|reserved_11|>",
|
29 |
+
"<|reserved_12|>",
|
30 |
+
"<|reserved_13|>",
|
31 |
+
"<|reserved_14|>",
|
32 |
+
"<|reserved_15|>",
|
33 |
+
"<|reserved_16|>",
|
34 |
+
"<|reserved_17|>",
|
35 |
+
"<|reserved_18|>",
|
36 |
+
"<|reserved_19|>",
|
37 |
+
"<|reserved_20|>",
|
38 |
+
"<|reserved_21|>",
|
39 |
+
"<|reserved_22|>",
|
40 |
+
"<|reserved_23|>",
|
41 |
+
"<|reserved_24|>",
|
42 |
+
"<|reserved_25|>",
|
43 |
+
"<|reserved_26|>",
|
44 |
+
"<|reserved_27|>",
|
45 |
+
"<|reserved_28|>",
|
46 |
+
"<|reserved_29|>",
|
47 |
+
"<|reserved_30|>",
|
48 |
+
"<|reserved_31|>",
|
49 |
+
"<|reserved_32|>",
|
50 |
+
"<|reserved_33|>",
|
51 |
+
"<|reserved_34|>",
|
52 |
+
"<|reserved_35|>",
|
53 |
+
"<|reserved_36|>",
|
54 |
+
"<|reserved_37|>",
|
55 |
+
"<|reserved_38|>",
|
56 |
+
"<|reserved_39|>",
|
57 |
+
"<|reserved_40|>",
|
58 |
+
"<|reserved_41|>",
|
59 |
+
"<|reserved_42|>",
|
60 |
+
"<|reserved_43|>",
|
61 |
+
"<|reserved_44|>",
|
62 |
+
"<|reserved_45|>",
|
63 |
+
"<|reserved_46|>",
|
64 |
+
"<|reserved_47|>",
|
65 |
+
"<|reserved_48|>"
|
66 |
+
],
|
67 |
+
"bos_token": {
|
68 |
+
"content": "<s>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false
|
73 |
+
},
|
74 |
+
"eos_token": {
|
75 |
+
"content": "<|im_end|>",
|
76 |
+
"lstrip": false,
|
77 |
+
"normalized": false,
|
78 |
+
"rstrip": false,
|
79 |
+
"single_word": false
|
80 |
+
},
|
81 |
+
"pad_token": {
|
82 |
+
"content": "<|pad|>",
|
83 |
+
"lstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"rstrip": false,
|
86 |
+
"single_word": false
|
87 |
+
},
|
88 |
+
"unk_token": {
|
89 |
+
"content": "<unk>",
|
90 |
+
"lstrip": false,
|
91 |
+
"normalized": false,
|
92 |
+
"rstrip": false,
|
93 |
+
"single_word": false
|
94 |
+
}
|
95 |
+
}
|
outputs/qlora-out/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
outputs/qlora-out/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
outputs/qlora-out/tokenizer_config.json
ADDED
@@ -0,0 +1,624 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<|im_end|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|end_of_turn|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|pad|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|im_start|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "</s>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "[INST]",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "[/INST]",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<<SYS>>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<</SYS>>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|user|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|system|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|assistant|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32011": {
|
119 |
+
"content": "<|begin_of_text|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": true
|
125 |
+
},
|
126 |
+
"32012": {
|
127 |
+
"content": "<|start_header_id|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"32013": {
|
135 |
+
"content": "<|end_header_id|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"32014": {
|
143 |
+
"content": "<|eot_id|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"32015": {
|
151 |
+
"content": "<|reserved_0|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"32016": {
|
159 |
+
"content": "<|reserved_1|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"32017": {
|
167 |
+
"content": "<|reserved_2|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"32018": {
|
175 |
+
"content": "<|reserved_3|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"32019": {
|
183 |
+
"content": "<|reserved_4|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"32020": {
|
191 |
+
"content": "<|reserved_5|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"32021": {
|
199 |
+
"content": "<|reserved_6|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"32022": {
|
207 |
+
"content": "<|reserved_7|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"32023": {
|
215 |
+
"content": "<|reserved_8|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"32024": {
|
223 |
+
"content": "<|reserved_9|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"32025": {
|
231 |
+
"content": "<|reserved_10|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"32026": {
|
239 |
+
"content": "<|reserved_11|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"32027": {
|
247 |
+
"content": "<|reserved_12|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"32028": {
|
255 |
+
"content": "<|reserved_13|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"32029": {
|
263 |
+
"content": "<|reserved_14|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"32030": {
|
271 |
+
"content": "<|reserved_15|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"32031": {
|
279 |
+
"content": "<|reserved_16|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"32032": {
|
287 |
+
"content": "<|reserved_17|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"32033": {
|
295 |
+
"content": "<|reserved_18|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"32034": {
|
303 |
+
"content": "<|reserved_19|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"32035": {
|
311 |
+
"content": "<|reserved_20|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"32036": {
|
319 |
+
"content": "<|reserved_21|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"32037": {
|
327 |
+
"content": "<|reserved_22|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"32038": {
|
335 |
+
"content": "<|reserved_23|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"32039": {
|
343 |
+
"content": "<|reserved_24|>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"32040": {
|
351 |
+
"content": "<|reserved_25|>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"32041": {
|
359 |
+
"content": "<|reserved_26|>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"32042": {
|
367 |
+
"content": "<|reserved_27|>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"32043": {
|
375 |
+
"content": "<|reserved_28|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"32044": {
|
383 |
+
"content": "<|reserved_29|>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"32045": {
|
391 |
+
"content": "<|reserved_30|>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"32046": {
|
399 |
+
"content": "<|reserved_31|>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"32047": {
|
407 |
+
"content": "<|reserved_32|>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"32048": {
|
415 |
+
"content": "<|reserved_33|>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"32049": {
|
423 |
+
"content": "<|reserved_34|>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"32050": {
|
431 |
+
"content": "<|reserved_35|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"32051": {
|
439 |
+
"content": "<|reserved_36|>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"32052": {
|
447 |
+
"content": "<|reserved_37|>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"32053": {
|
455 |
+
"content": "<|reserved_38|>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"32054": {
|
463 |
+
"content": "<|reserved_39|>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"32055": {
|
471 |
+
"content": "<|reserved_40|>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"32056": {
|
479 |
+
"content": "<|reserved_41|>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"32057": {
|
487 |
+
"content": "<|reserved_42|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"32058": {
|
495 |
+
"content": "<|reserved_43|>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"32059": {
|
503 |
+
"content": "<|reserved_44|>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"32060": {
|
511 |
+
"content": "<|reserved_45|>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"32061": {
|
519 |
+
"content": "<|reserved_46|>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"32062": {
|
527 |
+
"content": "<|reserved_47|>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"32063": {
|
535 |
+
"content": "<|reserved_48|>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
}
|
542 |
+
},
|
543 |
+
"additional_special_tokens": [
|
544 |
+
"<|end_of_turn|>",
|
545 |
+
"<|im_start|>",
|
546 |
+
"</s>",
|
547 |
+
"[INST]",
|
548 |
+
"[/INST]",
|
549 |
+
"<<SYS>>",
|
550 |
+
"<</SYS>>",
|
551 |
+
"<|user|>",
|
552 |
+
"<|system|>",
|
553 |
+
"<|assistant|>",
|
554 |
+
"<|begin_of_text|>",
|
555 |
+
"<|start_header_id|>",
|
556 |
+
"<|end_header_id|>",
|
557 |
+
"<|eot_id|>",
|
558 |
+
"<|reserved_0|>",
|
559 |
+
"<|reserved_1|>",
|
560 |
+
"<|reserved_2|>",
|
561 |
+
"<|reserved_3|>",
|
562 |
+
"<|reserved_4|>",
|
563 |
+
"<|reserved_5|>",
|
564 |
+
"<|reserved_6|>",
|
565 |
+
"<|reserved_7|>",
|
566 |
+
"<|reserved_8|>",
|
567 |
+
"<|reserved_9|>",
|
568 |
+
"<|reserved_10|>",
|
569 |
+
"<|reserved_11|>",
|
570 |
+
"<|reserved_12|>",
|
571 |
+
"<|reserved_13|>",
|
572 |
+
"<|reserved_14|>",
|
573 |
+
"<|reserved_15|>",
|
574 |
+
"<|reserved_16|>",
|
575 |
+
"<|reserved_17|>",
|
576 |
+
"<|reserved_18|>",
|
577 |
+
"<|reserved_19|>",
|
578 |
+
"<|reserved_20|>",
|
579 |
+
"<|reserved_21|>",
|
580 |
+
"<|reserved_22|>",
|
581 |
+
"<|reserved_23|>",
|
582 |
+
"<|reserved_24|>",
|
583 |
+
"<|reserved_25|>",
|
584 |
+
"<|reserved_26|>",
|
585 |
+
"<|reserved_27|>",
|
586 |
+
"<|reserved_28|>",
|
587 |
+
"<|reserved_29|>",
|
588 |
+
"<|reserved_30|>",
|
589 |
+
"<|reserved_31|>",
|
590 |
+
"<|reserved_32|>",
|
591 |
+
"<|reserved_33|>",
|
592 |
+
"<|reserved_34|>",
|
593 |
+
"<|reserved_35|>",
|
594 |
+
"<|reserved_36|>",
|
595 |
+
"<|reserved_37|>",
|
596 |
+
"<|reserved_38|>",
|
597 |
+
"<|reserved_39|>",
|
598 |
+
"<|reserved_40|>",
|
599 |
+
"<|reserved_41|>",
|
600 |
+
"<|reserved_42|>",
|
601 |
+
"<|reserved_43|>",
|
602 |
+
"<|reserved_44|>",
|
603 |
+
"<|reserved_45|>",
|
604 |
+
"<|reserved_46|>",
|
605 |
+
"<|reserved_47|>",
|
606 |
+
"<|reserved_48|>"
|
607 |
+
],
|
608 |
+
"bos_token": "<s>",
|
609 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
610 |
+
"clean_up_tokenization_spaces": false,
|
611 |
+
"eos_token": "<|im_end|>",
|
612 |
+
"kwargs": {
|
613 |
+
"eos_token": "<|im_end|>",
|
614 |
+
"pad_token": "<|pad|>",
|
615 |
+
"padding_side": "right"
|
616 |
+
},
|
617 |
+
"legacy": true,
|
618 |
+
"model_max_length": 1000000000000000019884624838656,
|
619 |
+
"pad_token": "<|pad|>",
|
620 |
+
"padding_side": "right",
|
621 |
+
"tokenizer_class": "LlamaTokenizer",
|
622 |
+
"unk_token": "<unk>",
|
623 |
+
"use_default_system_prompt": false
|
624 |
+
}
|