Upload 4-bit GPTQ model
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- chat_template.jinja +54 -0
- config.json +102 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quant_log.csv +337 -0
- quantize_config.json +24 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
chat_template.jinja
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{%- if tools %}
|
2 |
+
{{- '<|im_start|>system\n' }}
|
3 |
+
{%- if messages[0]['role'] == 'system' %}
|
4 |
+
{{- messages[0]['content'] }}
|
5 |
+
{%- else %}
|
6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
7 |
+
{%- endif %}
|
8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
9 |
+
{%- for tool in tools %}
|
10 |
+
{{- "\n" }}
|
11 |
+
{{- tool | tojson }}
|
12 |
+
{%- endfor %}
|
13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
14 |
+
{%- else %}
|
15 |
+
{%- if messages[0]['role'] == 'system' %}
|
16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
17 |
+
{%- else %}
|
18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
19 |
+
{%- endif %}
|
20 |
+
{%- endif %}
|
21 |
+
{%- for message in messages %}
|
22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
24 |
+
{%- elif message.role == "assistant" %}
|
25 |
+
{{- '<|im_start|>' + message.role }}
|
26 |
+
{%- if message.content %}
|
27 |
+
{{- '\n' + message.content }}
|
28 |
+
{%- endif %}
|
29 |
+
{%- for tool_call in message.tool_calls %}
|
30 |
+
{%- if tool_call.function is defined %}
|
31 |
+
{%- set tool_call = tool_call.function %}
|
32 |
+
{%- endif %}
|
33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
34 |
+
{{- tool_call.name }}
|
35 |
+
{{- '", "arguments": ' }}
|
36 |
+
{{- tool_call.arguments | tojson }}
|
37 |
+
{{- '}\n</tool_call>' }}
|
38 |
+
{%- endfor %}
|
39 |
+
{{- '<|im_end|>\n' }}
|
40 |
+
{%- elif message.role == "tool" %}
|
41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
42 |
+
{{- '<|im_start|>user' }}
|
43 |
+
{%- endif %}
|
44 |
+
{{- '\n<tool_response>\n' }}
|
45 |
+
{{- message.content }}
|
46 |
+
{{- '\n</tool_response>' }}
|
47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
48 |
+
{{- '<|im_end|>\n' }}
|
49 |
+
{%- endif %}
|
50 |
+
{%- endif %}
|
51 |
+
{%- endfor %}
|
52 |
+
{%- if add_generation_prompt %}
|
53 |
+
{{- '<|im_start|>assistant\n' }}
|
54 |
+
{%- endif %}
|
config.json
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 5120,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 13824,
|
12 |
+
"layer_types": [
|
13 |
+
"full_attention",
|
14 |
+
"full_attention",
|
15 |
+
"full_attention",
|
16 |
+
"full_attention",
|
17 |
+
"full_attention",
|
18 |
+
"full_attention",
|
19 |
+
"full_attention",
|
20 |
+
"full_attention",
|
21 |
+
"full_attention",
|
22 |
+
"full_attention",
|
23 |
+
"full_attention",
|
24 |
+
"full_attention",
|
25 |
+
"full_attention",
|
26 |
+
"full_attention",
|
27 |
+
"full_attention",
|
28 |
+
"full_attention",
|
29 |
+
"full_attention",
|
30 |
+
"full_attention",
|
31 |
+
"full_attention",
|
32 |
+
"full_attention",
|
33 |
+
"full_attention",
|
34 |
+
"full_attention",
|
35 |
+
"full_attention",
|
36 |
+
"full_attention",
|
37 |
+
"full_attention",
|
38 |
+
"full_attention",
|
39 |
+
"full_attention",
|
40 |
+
"full_attention",
|
41 |
+
"full_attention",
|
42 |
+
"full_attention",
|
43 |
+
"full_attention",
|
44 |
+
"full_attention",
|
45 |
+
"full_attention",
|
46 |
+
"full_attention",
|
47 |
+
"full_attention",
|
48 |
+
"full_attention",
|
49 |
+
"full_attention",
|
50 |
+
"full_attention",
|
51 |
+
"full_attention",
|
52 |
+
"full_attention",
|
53 |
+
"full_attention",
|
54 |
+
"full_attention",
|
55 |
+
"full_attention",
|
56 |
+
"full_attention",
|
57 |
+
"full_attention",
|
58 |
+
"full_attention",
|
59 |
+
"full_attention",
|
60 |
+
"full_attention"
|
61 |
+
],
|
62 |
+
"max_position_embeddings": 32768,
|
63 |
+
"max_window_layers": 70,
|
64 |
+
"model_type": "qwen2",
|
65 |
+
"num_attention_heads": 40,
|
66 |
+
"num_hidden_layers": 48,
|
67 |
+
"num_key_value_heads": 8,
|
68 |
+
"quantization_config": {
|
69 |
+
"bits": 4,
|
70 |
+
"checkpoint_format": "gptq",
|
71 |
+
"desc_act": true,
|
72 |
+
"group_size": 128,
|
73 |
+
"hyb_act": false,
|
74 |
+
"lm_head": false,
|
75 |
+
"meta": {
|
76 |
+
"damp_auto_increment": 0.01,
|
77 |
+
"damp_percent": 0.05,
|
78 |
+
"mse": 0.0,
|
79 |
+
"quantizer": [
|
80 |
+
"gptqmodel:4.0.0"
|
81 |
+
],
|
82 |
+
"static_groups": false,
|
83 |
+
"true_sequential": true,
|
84 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
85 |
+
"v2": false,
|
86 |
+
"v2_alpha": 0.25
|
87 |
+
},
|
88 |
+
"pack_dtype": "int32",
|
89 |
+
"quant_method": "gptq",
|
90 |
+
"sym": true
|
91 |
+
},
|
92 |
+
"rms_norm_eps": 1e-06,
|
93 |
+
"rope_scaling": null,
|
94 |
+
"rope_theta": 1000000.0,
|
95 |
+
"sliding_window": null,
|
96 |
+
"tie_word_embeddings": false,
|
97 |
+
"torch_dtype": "bfloat16",
|
98 |
+
"transformers_version": "4.55.4",
|
99 |
+
"use_cache": true,
|
100 |
+
"use_sliding_window": false,
|
101 |
+
"vocab_size": 152064
|
102 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 151645,
|
5 |
+
"max_new_tokens": 2048,
|
6 |
+
"pad_token_id": 151643,
|
7 |
+
"repetition_penalty": 1.05,
|
8 |
+
"temperature": 0.7,
|
9 |
+
"top_k": 20,
|
10 |
+
"top_p": 0.8,
|
11 |
+
"transformers_version": "4.55.4"
|
12 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e708fcc22191d69a9acb871680ea934760a2ec6caf773fc199e63c019569040
|
3 |
+
size 3991846296
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2c143c36456dfdb9fa3380c142d88ee5da2284bd8bec51c1696e9c4f5554345
|
3 |
+
size 3973264384
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8634bc4198b18484fa0aa8e17b231eacc27eba526598214d6f54e149d778e68c
|
3 |
+
size 2023648928
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
quant_log.csv
ADDED
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
layer,module,loss,samples,damp,time
|
2 |
+
0,self_attn.k_proj,0.0000003836,0.05000,1.015
|
3 |
+
0,self_attn.v_proj,0.0000000782,0.05000,0.726
|
4 |
+
0,self_attn.q_proj,0.0000010448,0.05000,0.754
|
5 |
+
0,self_attn.o_proj,0.0000005473,0.05000,0.760
|
6 |
+
0,mlp.gate_proj,0.0000007420,0.05000,0.766
|
7 |
+
0,mlp.up_proj,0.0000006467,0.05000,0.736
|
8 |
+
0,mlp.down_proj,0.0000005687,0.05000,2.183
|
9 |
+
1,self_attn.k_proj,0.0000000137,0.05000,0.758
|
10 |
+
1,self_attn.v_proj,0.0000000057,0.05000,0.770
|
11 |
+
1,self_attn.q_proj,0.0000000513,0.05000,0.827
|
12 |
+
1,self_attn.o_proj,0.0000000077,0.05000,0.815
|
13 |
+
1,mlp.gate_proj,0.0000066293,0.05000,0.778
|
14 |
+
1,mlp.up_proj,0.0000029132,0.05000,0.833
|
15 |
+
1,mlp.down_proj,0.0000000930,0.05000,2.140
|
16 |
+
2,self_attn.k_proj,0.0000000650,0.05000,0.752
|
17 |
+
2,self_attn.v_proj,0.0000000226,0.05000,0.731
|
18 |
+
2,self_attn.q_proj,0.0000001794,0.05000,0.745
|
19 |
+
2,self_attn.o_proj,0.0000000498,0.05000,0.739
|
20 |
+
2,mlp.gate_proj,0.0000135490,0.05000,0.736
|
21 |
+
2,mlp.up_proj,0.0000079025,0.05000,0.731
|
22 |
+
2,mlp.down_proj,0.0000003571,0.05000,2.234
|
23 |
+
3,self_attn.k_proj,0.0000003933,0.05000,0.732
|
24 |
+
3,self_attn.v_proj,0.0000001049,0.05000,0.713
|
25 |
+
3,self_attn.q_proj,0.0000010451,0.05000,0.721
|
26 |
+
3,self_attn.o_proj,0.0000001377,0.05000,0.727
|
27 |
+
3,mlp.gate_proj,0.0000162165,0.05000,0.741
|
28 |
+
3,mlp.up_proj,0.0000082294,0.05000,0.730
|
29 |
+
3,mlp.down_proj,0.0000006188,0.05000,2.142
|
30 |
+
4,self_attn.k_proj,0.0000004112,0.05000,0.735
|
31 |
+
4,self_attn.v_proj,0.0000001402,0.05000,0.713
|
32 |
+
4,self_attn.q_proj,0.0000011218,0.05000,0.718
|
33 |
+
4,self_attn.o_proj,0.0000002406,0.05000,0.750
|
34 |
+
4,mlp.gate_proj,0.0000267092,0.05000,0.803
|
35 |
+
4,mlp.up_proj,0.0000151525,0.05000,0.815
|
36 |
+
4,mlp.down_proj,0.0000964310,0.05000,2.161
|
37 |
+
5,self_attn.k_proj,0.0000013297,0.05000,0.733
|
38 |
+
5,self_attn.v_proj,0.0000005998,0.05000,0.724
|
39 |
+
5,self_attn.q_proj,0.0000043050,0.05000,0.728
|
40 |
+
5,self_attn.o_proj,0.0000002593,0.05000,0.729
|
41 |
+
5,mlp.gate_proj,0.0000366176,0.05000,0.748
|
42 |
+
5,mlp.up_proj,0.0000200382,0.05000,0.734
|
43 |
+
5,mlp.down_proj,0.0000034205,0.05000,2.164
|
44 |
+
6,self_attn.k_proj,0.0000013150,0.05000,0.738
|
45 |
+
6,self_attn.v_proj,0.0000007459,0.05000,0.728
|
46 |
+
6,self_attn.q_proj,0.0000045390,0.05000,0.726
|
47 |
+
6,self_attn.o_proj,0.0000002721,0.05000,0.727
|
48 |
+
6,mlp.gate_proj,0.0000514023,0.05000,0.741
|
49 |
+
6,mlp.up_proj,0.0000293805,0.05000,0.732
|
50 |
+
6,mlp.down_proj,0.0000023108,0.05000,2.140
|
51 |
+
7,self_attn.k_proj,0.0000017118,0.05000,0.738
|
52 |
+
7,self_attn.v_proj,0.0000010427,0.05000,0.719
|
53 |
+
7,self_attn.q_proj,0.0000061210,0.05000,0.726
|
54 |
+
7,self_attn.o_proj,0.0000002765,0.05000,0.734
|
55 |
+
7,mlp.gate_proj,0.0000617160,0.05000,0.748
|
56 |
+
7,mlp.up_proj,0.0000353903,0.05000,0.735
|
57 |
+
7,mlp.down_proj,0.0000016504,0.05000,2.157
|
58 |
+
8,self_attn.k_proj,0.0000018246,0.05000,0.732
|
59 |
+
8,self_attn.v_proj,0.0000009054,0.05000,0.718
|
60 |
+
8,self_attn.q_proj,0.0000061746,0.05000,0.727
|
61 |
+
8,self_attn.o_proj,0.0000003254,0.05000,0.730
|
62 |
+
8,mlp.gate_proj,0.0000366315,0.05000,0.759
|
63 |
+
8,mlp.up_proj,0.0000218339,0.05000,0.745
|
64 |
+
8,mlp.down_proj,0.0000022364,0.05000,2.214
|
65 |
+
9,self_attn.k_proj,0.0000015798,0.05000,0.779
|
66 |
+
9,self_attn.v_proj,0.0000009709,0.05000,0.780
|
67 |
+
9,self_attn.q_proj,0.0000055324,0.05000,0.792
|
68 |
+
9,self_attn.o_proj,0.0000005803,0.05000,0.735
|
69 |
+
9,mlp.gate_proj,0.0000134546,0.05000,0.759
|
70 |
+
9,mlp.up_proj,0.0000123509,0.05000,0.757
|
71 |
+
9,mlp.down_proj,0.0000025098,0.05000,2.140
|
72 |
+
10,self_attn.k_proj,0.0000021740,0.05000,0.754
|
73 |
+
10,self_attn.v_proj,0.0000012504,0.05000,0.730
|
74 |
+
10,self_attn.q_proj,0.0000078099,0.05000,0.732
|
75 |
+
10,self_attn.o_proj,0.0000005121,0.05000,0.733
|
76 |
+
10,mlp.gate_proj,0.0000144171,0.05000,0.746
|
77 |
+
10,mlp.up_proj,0.0000132418,0.05000,0.744
|
78 |
+
10,mlp.down_proj,0.0000028267,0.05000,2.207
|
79 |
+
11,self_attn.k_proj,0.0000016604,0.05000,0.734
|
80 |
+
11,self_attn.v_proj,0.0000008726,0.05000,0.722
|
81 |
+
11,self_attn.q_proj,0.0000059258,0.05000,0.732
|
82 |
+
11,self_attn.o_proj,0.0000009211,0.05000,0.731
|
83 |
+
11,mlp.gate_proj,0.0000186690,0.05000,0.759
|
84 |
+
11,mlp.up_proj,0.0000150442,0.05000,0.784
|
85 |
+
11,mlp.down_proj,0.0000025569,0.05000,2.264
|
86 |
+
12,self_attn.k_proj,0.0000019593,0.05000,0.751
|
87 |
+
12,self_attn.v_proj,0.0000009936,0.05000,0.725
|
88 |
+
12,self_attn.q_proj,0.0000070199,0.05000,0.727
|
89 |
+
12,self_attn.o_proj,0.0000009910,0.05000,0.792
|
90 |
+
12,mlp.gate_proj,0.0000164469,0.05000,0.761
|
91 |
+
12,mlp.up_proj,0.0000155571,0.05000,0.738
|
92 |
+
12,mlp.down_proj,0.0000030347,0.05000,2.153
|
93 |
+
13,self_attn.k_proj,0.0000020996,0.05000,0.737
|
94 |
+
13,self_attn.v_proj,0.0000012002,0.05000,0.733
|
95 |
+
13,self_attn.q_proj,0.0000074697,0.05000,0.725
|
96 |
+
13,self_attn.o_proj,0.0000012893,0.05000,0.729
|
97 |
+
13,mlp.gate_proj,0.0000188491,0.05000,0.746
|
98 |
+
13,mlp.up_proj,0.0000178457,0.05000,0.738
|
99 |
+
13,mlp.down_proj,0.0000037568,0.05000,2.205
|
100 |
+
14,self_attn.k_proj,0.0000025165,0.05000,0.747
|
101 |
+
14,self_attn.v_proj,0.0000012607,0.05000,0.723
|
102 |
+
14,self_attn.q_proj,0.0000088147,0.05000,0.734
|
103 |
+
14,self_attn.o_proj,0.0000012709,0.05000,0.739
|
104 |
+
14,mlp.gate_proj,0.0000193264,0.05000,0.767
|
105 |
+
14,mlp.up_proj,0.0000183729,0.05000,0.745
|
106 |
+
14,mlp.down_proj,0.0000039256,0.05000,2.143
|
107 |
+
15,self_attn.k_proj,0.0000021721,0.05000,0.753
|
108 |
+
15,self_attn.v_proj,0.0000014329,0.05000,0.739
|
109 |
+
15,self_attn.q_proj,0.0000079258,0.05000,0.728
|
110 |
+
15,self_attn.o_proj,0.0000014436,0.05000,0.729
|
111 |
+
15,mlp.gate_proj,0.0000211392,0.05000,0.770
|
112 |
+
15,mlp.up_proj,0.0000192754,0.05000,0.818
|
113 |
+
15,mlp.down_proj,0.0000039555,0.05000,2.196
|
114 |
+
16,self_attn.k_proj,0.0000022858,0.05000,0.739
|
115 |
+
16,self_attn.v_proj,0.0000010207,0.05000,0.734
|
116 |
+
16,self_attn.q_proj,0.0000073921,0.05000,0.730
|
117 |
+
16,self_attn.o_proj,0.0000014224,0.05000,0.757
|
118 |
+
16,mlp.gate_proj,0.0000179755,0.05000,0.749
|
119 |
+
16,mlp.up_proj,0.0000177250,0.05000,0.739
|
120 |
+
16,mlp.down_proj,0.0000040355,0.05000,2.223
|
121 |
+
17,self_attn.k_proj,0.0000025309,0.05000,0.805
|
122 |
+
17,self_attn.v_proj,0.0000011885,0.05000,0.807
|
123 |
+
17,self_attn.q_proj,0.0000087249,0.05000,0.795
|
124 |
+
17,self_attn.o_proj,0.0000015970,0.05000,0.733
|
125 |
+
17,mlp.gate_proj,0.0000173575,0.05000,0.785
|
126 |
+
17,mlp.up_proj,0.0000176120,0.05000,0.752
|
127 |
+
17,mlp.down_proj,0.0000037880,0.05000,2.169
|
128 |
+
18,self_attn.k_proj,0.0000025784,0.05000,0.741
|
129 |
+
18,self_attn.v_proj,0.0000013703,0.05000,0.721
|
130 |
+
18,self_attn.q_proj,0.0000089820,0.05000,0.723
|
131 |
+
18,self_attn.o_proj,0.0000020961,0.05000,0.751
|
132 |
+
18,mlp.gate_proj,0.0000169104,0.05000,0.759
|
133 |
+
18,mlp.up_proj,0.0000176954,0.05000,0.741
|
134 |
+
18,mlp.down_proj,0.0000038492,0.05000,2.194
|
135 |
+
19,self_attn.k_proj,0.0000028707,0.05000,0.753
|
136 |
+
19,self_attn.v_proj,0.0000014709,0.05000,0.742
|
137 |
+
19,self_attn.q_proj,0.0000108252,0.05000,0.732
|
138 |
+
19,self_attn.o_proj,0.0000017332,0.05000,0.730
|
139 |
+
19,mlp.gate_proj,0.0000177889,0.05000,0.790
|
140 |
+
19,mlp.up_proj,0.0000186258,0.05000,0.760
|
141 |
+
19,mlp.down_proj,0.0000041158,0.05000,2.156
|
142 |
+
20,self_attn.k_proj,0.0000030751,0.05000,0.754
|
143 |
+
20,self_attn.v_proj,0.0000013982,0.05000,0.721
|
144 |
+
20,self_attn.q_proj,0.0000107140,0.05000,0.767
|
145 |
+
20,self_attn.o_proj,0.0000024387,0.05000,0.806
|
146 |
+
20,mlp.gate_proj,0.0000162837,0.05000,0.757
|
147 |
+
20,mlp.up_proj,0.0000179382,0.05000,0.742
|
148 |
+
20,mlp.down_proj,0.0000044658,0.05000,2.153
|
149 |
+
21,self_attn.k_proj,0.0000029271,0.05000,0.758
|
150 |
+
21,self_attn.v_proj,0.0000013779,0.05000,0.737
|
151 |
+
21,self_attn.q_proj,0.0000100324,0.05000,0.735
|
152 |
+
21,self_attn.o_proj,0.0000019044,0.05000,0.741
|
153 |
+
21,mlp.gate_proj,0.0000166225,0.05000,0.753
|
154 |
+
21,mlp.up_proj,0.0000184214,0.05000,0.754
|
155 |
+
21,mlp.down_proj,0.0000041782,0.05000,2.331
|
156 |
+
22,self_attn.k_proj,0.0000032301,0.05000,0.805
|
157 |
+
22,self_attn.v_proj,0.0000020764,0.05000,0.792
|
158 |
+
22,self_attn.q_proj,0.0000112834,0.05000,0.754
|
159 |
+
22,self_attn.o_proj,0.0000028200,0.05000,0.753
|
160 |
+
22,mlp.gate_proj,0.0000175082,0.05000,0.764
|
161 |
+
22,mlp.up_proj,0.0000194985,0.05000,0.773
|
162 |
+
22,mlp.down_proj,0.0000046281,0.05000,2.258
|
163 |
+
23,self_attn.k_proj,0.0000030540,0.05000,0.742
|
164 |
+
23,self_attn.v_proj,0.0000020901,0.05000,0.735
|
165 |
+
23,self_attn.q_proj,0.0000114107,0.05000,0.728
|
166 |
+
23,self_attn.o_proj,0.0000027048,0.05000,0.736
|
167 |
+
23,mlp.gate_proj,0.0000191307,0.05000,0.806
|
168 |
+
23,mlp.up_proj,0.0000202188,0.05000,0.796
|
169 |
+
23,mlp.down_proj,0.0000047198,0.05000,2.213
|
170 |
+
24,self_attn.k_proj,0.0000042195,0.05000,0.745
|
171 |
+
24,self_attn.v_proj,0.0000018628,0.05000,0.723
|
172 |
+
24,self_attn.q_proj,0.0000135178,0.05000,0.735
|
173 |
+
24,self_attn.o_proj,0.0000032197,0.05000,0.766
|
174 |
+
24,mlp.gate_proj,0.0000182919,0.05000,0.749
|
175 |
+
24,mlp.up_proj,0.0000195997,0.05000,0.739
|
176 |
+
24,mlp.down_proj,0.0000044227,0.05000,2.184
|
177 |
+
25,self_attn.k_proj,0.0000043229,0.05000,0.743
|
178 |
+
25,self_attn.v_proj,0.0000025822,0.05000,0.727
|
179 |
+
25,self_attn.q_proj,0.0000154015,0.05000,0.743
|
180 |
+
25,self_attn.o_proj,0.0000030529,0.05000,0.739
|
181 |
+
25,mlp.gate_proj,0.0000188421,0.05000,0.764
|
182 |
+
25,mlp.up_proj,0.0000209068,0.05000,0.753
|
183 |
+
25,mlp.down_proj,0.0000051917,0.05000,2.159
|
184 |
+
26,self_attn.k_proj,0.0000039396,0.05000,0.737
|
185 |
+
26,self_attn.v_proj,0.0000017195,0.05000,0.725
|
186 |
+
26,self_attn.q_proj,0.0000140131,0.05000,0.735
|
187 |
+
26,self_attn.o_proj,0.0000025629,0.05000,0.744
|
188 |
+
26,mlp.gate_proj,0.0000200527,0.05000,0.749
|
189 |
+
26,mlp.up_proj,0.0000231107,0.05000,0.760
|
190 |
+
26,mlp.down_proj,0.0000059867,0.05000,2.163
|
191 |
+
27,self_attn.k_proj,0.0000042207,0.05000,0.740
|
192 |
+
27,self_attn.v_proj,0.0000021844,0.05000,0.718
|
193 |
+
27,self_attn.q_proj,0.0000140871,0.05000,0.722
|
194 |
+
27,self_attn.o_proj,0.0000030243,0.05000,0.728
|
195 |
+
27,mlp.gate_proj,0.0000213445,0.05000,0.746
|
196 |
+
27,mlp.up_proj,0.0000247833,0.05000,0.765
|
197 |
+
27,mlp.down_proj,0.0000070833,0.05000,2.175
|
198 |
+
28,self_attn.k_proj,0.0000034175,0.05000,0.793
|
199 |
+
28,self_attn.v_proj,0.0000030988,0.05000,0.782
|
200 |
+
28,self_attn.q_proj,0.0000138590,0.05000,0.786
|
201 |
+
28,self_attn.o_proj,0.0000040915,0.05000,0.733
|
202 |
+
28,mlp.gate_proj,0.0000215709,0.05000,0.755
|
203 |
+
28,mlp.up_proj,0.0000255722,0.05000,0.750
|
204 |
+
28,mlp.down_proj,0.0000078348,0.05000,2.175
|
205 |
+
29,self_attn.k_proj,0.0000045058,0.05000,0.736
|
206 |
+
29,self_attn.v_proj,0.0000032128,0.05000,0.715
|
207 |
+
29,self_attn.q_proj,0.0000166073,0.05000,0.717
|
208 |
+
29,self_attn.o_proj,0.0000047115,0.05000,0.740
|
209 |
+
29,mlp.gate_proj,0.0000226059,0.05000,0.753
|
210 |
+
29,mlp.up_proj,0.0000267313,0.05000,0.750
|
211 |
+
29,mlp.down_proj,0.0000088983,0.05000,2.230
|
212 |
+
30,self_attn.k_proj,0.0000038593,0.05000,0.750
|
213 |
+
30,self_attn.v_proj,0.0000034925,0.05000,0.730
|
214 |
+
30,self_attn.q_proj,0.0000152342,0.05000,0.721
|
215 |
+
30,self_attn.o_proj,0.0000048734,0.05000,0.739
|
216 |
+
30,mlp.gate_proj,0.0000232500,0.05000,0.746
|
217 |
+
30,mlp.up_proj,0.0000273514,0.05000,0.741
|
218 |
+
30,mlp.down_proj,0.0000097457,0.05000,2.166
|
219 |
+
31,self_attn.k_proj,0.0000038229,0.05000,0.741
|
220 |
+
31,self_attn.v_proj,0.0000032801,0.05000,0.718
|
221 |
+
31,self_attn.q_proj,0.0000150417,0.05000,0.725
|
222 |
+
31,self_attn.o_proj,0.0000039066,0.05000,0.782
|
223 |
+
31,mlp.gate_proj,0.0000263491,0.05000,0.763
|
224 |
+
31,mlp.up_proj,0.0000302772,0.05000,0.742
|
225 |
+
31,mlp.down_proj,0.0000114387,0.05000,2.172
|
226 |
+
32,self_attn.k_proj,0.0000040586,0.05000,0.797
|
227 |
+
32,self_attn.v_proj,0.0000040552,0.05000,0.761
|
228 |
+
32,self_attn.q_proj,0.0000162478,0.05000,0.783
|
229 |
+
32,self_attn.o_proj,0.0000036017,0.05000,0.793
|
230 |
+
32,mlp.gate_proj,0.0000282540,0.05000,0.758
|
231 |
+
32,mlp.up_proj,0.0000316693,0.05000,0.738
|
232 |
+
32,mlp.down_proj,0.0000129634,0.05000,2.251
|
233 |
+
33,self_attn.k_proj,0.0000041616,0.05000,0.776
|
234 |
+
33,self_attn.v_proj,0.0000040587,0.05000,0.751
|
235 |
+
33,self_attn.q_proj,0.0000171991,0.05000,0.744
|
236 |
+
33,self_attn.o_proj,0.0000042980,0.05000,0.749
|
237 |
+
33,mlp.gate_proj,0.0000341107,0.05000,0.749
|
238 |
+
33,mlp.up_proj,0.0000376710,0.05000,0.742
|
239 |
+
33,mlp.down_proj,0.0000190934,0.05000,2.153
|
240 |
+
34,self_attn.k_proj,0.0000043125,0.05000,0.737
|
241 |
+
34,self_attn.v_proj,0.0000048270,0.05000,0.731
|
242 |
+
34,self_attn.q_proj,0.0000189533,0.05000,0.726
|
243 |
+
34,self_attn.o_proj,0.0000045642,0.05000,0.731
|
244 |
+
34,mlp.gate_proj,0.0000401084,0.05000,0.760
|
245 |
+
34,mlp.up_proj,0.0000429217,0.05000,0.740
|
246 |
+
34,mlp.down_proj,0.0000224412,0.05000,2.151
|
247 |
+
35,self_attn.k_proj,0.0000041633,0.05000,0.734
|
248 |
+
35,self_attn.v_proj,0.0000042589,0.05000,0.722
|
249 |
+
35,self_attn.q_proj,0.0000169748,0.05000,0.723
|
250 |
+
35,self_attn.o_proj,0.0000073256,0.05000,0.734
|
251 |
+
35,mlp.gate_proj,0.0000451130,0.05000,0.776
|
252 |
+
35,mlp.up_proj,0.0000470624,0.05000,0.740
|
253 |
+
35,mlp.down_proj,0.0000268825,0.05000,2.152
|
254 |
+
36,self_attn.k_proj,0.0000046333,0.05000,0.746
|
255 |
+
36,self_attn.v_proj,0.0000074812,0.05000,0.726
|
256 |
+
36,self_attn.q_proj,0.0000211151,0.05000,0.741
|
257 |
+
36,self_attn.o_proj,0.0000063130,0.05000,0.786
|
258 |
+
36,mlp.gate_proj,0.0000486521,0.05000,0.754
|
259 |
+
36,mlp.up_proj,0.0000513203,0.05000,0.742
|
260 |
+
36,mlp.down_proj,0.0000342591,0.05000,2.181
|
261 |
+
37,self_attn.k_proj,0.0000050801,0.05000,0.752
|
262 |
+
37,self_attn.v_proj,0.0000068690,0.05000,0.727
|
263 |
+
37,self_attn.q_proj,0.0000210885,0.05000,0.727
|
264 |
+
37,self_attn.o_proj,0.0000079530,0.05000,0.748
|
265 |
+
37,mlp.gate_proj,0.0000523901,0.05000,0.762
|
266 |
+
37,mlp.up_proj,0.0000550565,0.05000,0.746
|
267 |
+
37,mlp.down_proj,0.0000368927,0.05000,2.235
|
268 |
+
38,self_attn.k_proj,0.0000047046,0.05000,0.850
|
269 |
+
38,self_attn.v_proj,0.0000067587,0.05000,0.736
|
270 |
+
38,self_attn.q_proj,0.0000202120,0.05000,0.724
|
271 |
+
38,self_attn.o_proj,0.0000061420,0.05000,0.729
|
272 |
+
38,mlp.gate_proj,0.0000566031,0.05000,0.771
|
273 |
+
38,mlp.up_proj,0.0000601863,0.05000,0.756
|
274 |
+
38,mlp.down_proj,0.0000401681,0.05000,2.196
|
275 |
+
39,self_attn.k_proj,0.0000043822,0.05000,0.738
|
276 |
+
39,self_attn.v_proj,0.0000071958,0.05000,0.739
|
277 |
+
39,self_attn.q_proj,0.0000199039,0.05000,0.743
|
278 |
+
39,self_attn.o_proj,0.0000075891,0.05000,0.742
|
279 |
+
39,mlp.gate_proj,0.0000607342,0.05000,0.815
|
280 |
+
39,mlp.up_proj,0.0000651528,0.05000,0.820
|
281 |
+
39,mlp.down_proj,0.0000479669,0.05000,2.146
|
282 |
+
40,self_attn.k_proj,0.0000049208,0.05000,0.745
|
283 |
+
40,self_attn.v_proj,0.0000095758,0.05000,0.754
|
284 |
+
40,self_attn.q_proj,0.0000219568,0.05000,0.759
|
285 |
+
40,self_attn.o_proj,0.0000064147,0.05000,0.744
|
286 |
+
40,mlp.gate_proj,0.0000638470,0.05000,0.760
|
287 |
+
40,mlp.up_proj,0.0000689741,0.05000,0.744
|
288 |
+
40,mlp.down_proj,0.0000523432,0.05000,2.166
|
289 |
+
41,self_attn.k_proj,0.0000045001,0.05000,0.827
|
290 |
+
41,self_attn.v_proj,0.0000094180,0.05000,0.758
|
291 |
+
41,self_attn.q_proj,0.0000212548,0.05000,0.730
|
292 |
+
41,self_attn.o_proj,0.0000054054,0.05000,0.738
|
293 |
+
41,mlp.gate_proj,0.0000669373,0.05000,0.772
|
294 |
+
41,mlp.up_proj,0.0000732278,0.05000,0.770
|
295 |
+
41,mlp.down_proj,0.0000576096,0.05000,2.163
|
296 |
+
42,self_attn.k_proj,0.0000048940,0.05000,0.789
|
297 |
+
42,self_attn.v_proj,0.0000106496,0.05000,0.776
|
298 |
+
42,self_attn.q_proj,0.0000218831,0.05000,0.742
|
299 |
+
42,self_attn.o_proj,0.0000062110,0.05000,0.749
|
300 |
+
42,mlp.gate_proj,0.0000708179,0.05000,0.813
|
301 |
+
42,mlp.up_proj,0.0000786422,0.05000,0.821
|
302 |
+
42,mlp.down_proj,0.0000692101,0.05000,2.212
|
303 |
+
43,self_attn.k_proj,0.0000049360,0.05000,0.769
|
304 |
+
43,self_attn.v_proj,0.0000151946,0.05000,0.767
|
305 |
+
43,self_attn.q_proj,0.0000240280,0.05000,0.763
|
306 |
+
43,self_attn.o_proj,0.0000109670,0.05000,0.768
|
307 |
+
43,mlp.gate_proj,0.0000772213,0.05000,0.843
|
308 |
+
43,mlp.up_proj,0.0000874869,0.05000,1.152
|
309 |
+
43,mlp.down_proj,0.0000823243,0.05000,2.178
|
310 |
+
44,self_attn.k_proj,0.0000045238,0.05000,0.822
|
311 |
+
44,self_attn.v_proj,0.0000168177,0.05000,0.804
|
312 |
+
44,self_attn.q_proj,0.0000236080,0.05000,0.794
|
313 |
+
44,self_attn.o_proj,0.0000180416,0.05000,0.747
|
314 |
+
44,mlp.gate_proj,0.0000815393,0.05000,0.794
|
315 |
+
44,mlp.up_proj,0.0000938600,0.05000,0.751
|
316 |
+
44,mlp.down_proj,0.0001585995,0.05000,2.156
|
317 |
+
45,self_attn.k_proj,0.0000048384,0.05000,0.740
|
318 |
+
45,self_attn.v_proj,0.0000209304,0.05000,0.740
|
319 |
+
45,self_attn.q_proj,0.0000253944,0.05000,0.727
|
320 |
+
45,self_attn.o_proj,0.0000221834,0.05000,0.743
|
321 |
+
45,mlp.gate_proj,0.0000914715,0.05000,0.753
|
322 |
+
45,mlp.up_proj,0.0001040489,0.05000,0.749
|
323 |
+
45,mlp.down_proj,0.0001830558,0.05000,2.216
|
324 |
+
46,self_attn.k_proj,0.0000046951,0.05000,0.749
|
325 |
+
46,self_attn.v_proj,0.0000239839,0.05000,0.734
|
326 |
+
46,self_attn.q_proj,0.0000252321,0.05000,0.737
|
327 |
+
46,self_attn.o_proj,0.0000349532,0.05000,0.732
|
328 |
+
46,mlp.gate_proj,0.0001022066,0.05000,0.748
|
329 |
+
46,mlp.up_proj,0.0001110833,0.05000,0.743
|
330 |
+
46,mlp.down_proj,0.0003265005,0.05000,2.173
|
331 |
+
47,self_attn.k_proj,0.0000042139,0.05000,0.738
|
332 |
+
47,self_attn.v_proj,0.0000151991,0.05000,0.728
|
333 |
+
47,self_attn.q_proj,0.0000205626,0.05000,0.719
|
334 |
+
47,self_attn.o_proj,0.0000162146,0.05000,0.760
|
335 |
+
47,mlp.gate_proj,0.0001253340,0.05000,0.781
|
336 |
+
47,mlp.up_proj,0.0001317324,0.05000,0.740
|
337 |
+
47,mlp.down_proj,0.0007685446,0.05000,2.138
|
quantize_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"desc_act": true,
|
5 |
+
"hyb_act": false,
|
6 |
+
"sym": true,
|
7 |
+
"lm_head": false,
|
8 |
+
"quant_method": "gptq",
|
9 |
+
"checkpoint_format": "gptq",
|
10 |
+
"pack_dtype": "int32",
|
11 |
+
"meta": {
|
12 |
+
"quantizer": [
|
13 |
+
"gptqmodel:4.0.0"
|
14 |
+
],
|
15 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
16 |
+
"damp_percent": 0.05,
|
17 |
+
"damp_auto_increment": 0.01,
|
18 |
+
"static_groups": false,
|
19 |
+
"true_sequential": true,
|
20 |
+
"mse": 0.0,
|
21 |
+
"v2": false,
|
22 |
+
"v2_alpha": 0.25
|
23 |
+
}
|
24 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": "<|fim_pad|>"
|
25 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
ADDED
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"clean_up_tokenization_spaces": false,
|
199 |
+
"eos_token": "<|im_end|>",
|
200 |
+
"errors": "replace",
|
201 |
+
"extra_special_tokens": {},
|
202 |
+
"model_max_length": 131072,
|
203 |
+
"pad_token": "<|fim_pad|>",
|
204 |
+
"split_special_tokens": false,
|
205 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
206 |
+
"unk_token": null,
|
207 |
+
"_commit_hash": null
|
208 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|