Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- chat_template.jinja +89 -0
- config.json +101 -0
- generation_config.json +6 -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 +23 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -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 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</think>": 151668,
|
3 |
+
"</tool_call>": 151658,
|
4 |
+
"</tool_response>": 151666,
|
5 |
+
"<think>": 151667,
|
6 |
+
"<tool_call>": 151657,
|
7 |
+
"<tool_response>": 151665,
|
8 |
+
"<|box_end|>": 151649,
|
9 |
+
"<|box_start|>": 151648,
|
10 |
+
"<|endoftext|>": 151643,
|
11 |
+
"<|file_sep|>": 151664,
|
12 |
+
"<|fim_middle|>": 151660,
|
13 |
+
"<|fim_pad|>": 151662,
|
14 |
+
"<|fim_prefix|>": 151659,
|
15 |
+
"<|fim_suffix|>": 151661,
|
16 |
+
"<|im_end|>": 151645,
|
17 |
+
"<|im_start|>": 151644,
|
18 |
+
"<|image_pad|>": 151655,
|
19 |
+
"<|object_ref_end|>": 151647,
|
20 |
+
"<|object_ref_start|>": 151646,
|
21 |
+
"<|quad_end|>": 151651,
|
22 |
+
"<|quad_start|>": 151650,
|
23 |
+
"<|repo_name|>": 151663,
|
24 |
+
"<|video_pad|>": 151656,
|
25 |
+
"<|vision_end|>": 151653,
|
26 |
+
"<|vision_pad|>": 151654,
|
27 |
+
"<|vision_start|>": 151652
|
28 |
+
}
|
chat_template.jinja
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{%- if tools %}
|
2 |
+
{{- '<|im_start|>system\n' }}
|
3 |
+
{%- if messages[0].role == 'system' %}
|
4 |
+
{{- messages[0].content + '\n\n' }}
|
5 |
+
{%- endif %}
|
6 |
+
{{- "# 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>" }}
|
7 |
+
{%- for tool in tools %}
|
8 |
+
{{- "\n" }}
|
9 |
+
{{- tool | tojson }}
|
10 |
+
{%- endfor %}
|
11 |
+
{{- "\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" }}
|
12 |
+
{%- else %}
|
13 |
+
{%- if messages[0].role == 'system' %}
|
14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
15 |
+
{%- endif %}
|
16 |
+
{%- endif %}
|
17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
18 |
+
{%- for message in messages[::-1] %}
|
19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
21 |
+
{%- set ns.multi_step_tool = false %}
|
22 |
+
{%- set ns.last_query_index = index %}
|
23 |
+
{%- endif %}
|
24 |
+
{%- endfor %}
|
25 |
+
{%- for message in messages %}
|
26 |
+
{%- if message.content is string %}
|
27 |
+
{%- set content = message.content %}
|
28 |
+
{%- else %}
|
29 |
+
{%- set content = '' %}
|
30 |
+
{%- endif %}
|
31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
33 |
+
{%- elif message.role == "assistant" %}
|
34 |
+
{%- set reasoning_content = '' %}
|
35 |
+
{%- if message.reasoning_content is string %}
|
36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
37 |
+
{%- else %}
|
38 |
+
{%- if '</think>' in content %}
|
39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
41 |
+
{%- endif %}
|
42 |
+
{%- endif %}
|
43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
46 |
+
{%- else %}
|
47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
48 |
+
{%- endif %}
|
49 |
+
{%- else %}
|
50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
51 |
+
{%- endif %}
|
52 |
+
{%- if message.tool_calls %}
|
53 |
+
{%- for tool_call in message.tool_calls %}
|
54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
55 |
+
{{- '\n' }}
|
56 |
+
{%- endif %}
|
57 |
+
{%- if tool_call.function %}
|
58 |
+
{%- set tool_call = tool_call.function %}
|
59 |
+
{%- endif %}
|
60 |
+
{{- '<tool_call>\n{"name": "' }}
|
61 |
+
{{- tool_call.name }}
|
62 |
+
{{- '", "arguments": ' }}
|
63 |
+
{%- if tool_call.arguments is string %}
|
64 |
+
{{- tool_call.arguments }}
|
65 |
+
{%- else %}
|
66 |
+
{{- tool_call.arguments | tojson }}
|
67 |
+
{%- endif %}
|
68 |
+
{{- '}\n</tool_call>' }}
|
69 |
+
{%- endfor %}
|
70 |
+
{%- endif %}
|
71 |
+
{{- '<|im_end|>\n' }}
|
72 |
+
{%- elif message.role == "tool" %}
|
73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
74 |
+
{{- '<|im_start|>user' }}
|
75 |
+
{%- endif %}
|
76 |
+
{{- '\n<tool_response>\n' }}
|
77 |
+
{{- content }}
|
78 |
+
{{- '\n</tool_response>' }}
|
79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
80 |
+
{{- '<|im_end|>\n' }}
|
81 |
+
{%- endif %}
|
82 |
+
{%- endif %}
|
83 |
+
{%- endfor %}
|
84 |
+
{%- if add_generation_prompt %}
|
85 |
+
{{- '<|im_start|>assistant\n' }}
|
86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
88 |
+
{%- endif %}
|
89 |
+
{%- endif %}
|
config.json
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"lm_head": false,
|
74 |
+
"meta": {
|
75 |
+
"damp_auto_increment": 0.01,
|
76 |
+
"damp_percent": 0.05,
|
77 |
+
"mse": 0.0,
|
78 |
+
"quantizer": [
|
79 |
+
"gptqmodel:4.0.0-dev"
|
80 |
+
],
|
81 |
+
"static_groups": false,
|
82 |
+
"true_sequential": true,
|
83 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
84 |
+
"v2": false,
|
85 |
+
"v2_alpha": 0.25
|
86 |
+
},
|
87 |
+
"pack_dtype": "int32",
|
88 |
+
"quant_method": "gptq",
|
89 |
+
"sym": true
|
90 |
+
},
|
91 |
+
"rms_norm_eps": 1e-06,
|
92 |
+
"rope_scaling": null,
|
93 |
+
"rope_theta": 1000000.0,
|
94 |
+
"sliding_window": null,
|
95 |
+
"tie_word_embeddings": false,
|
96 |
+
"torch_dtype": "bfloat16",
|
97 |
+
"transformers_version": "4.53.1",
|
98 |
+
"use_cache": true,
|
99 |
+
"use_sliding_window": false,
|
100 |
+
"vocab_size": 151669
|
101 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 151643,
|
4 |
+
"eos_token_id": 151645,
|
5 |
+
"transformers_version": "4.53.1"
|
6 |
+
}
|
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:eb7ec0f908cb376a9182da4fd0c90ec12b8a2f6252ba7b5dacaf81d4654e77ef
|
3 |
+
size 3987801496
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02755d728a7fc560efbe8bd8ee175e0c7d67f3e4e391f38b3b5231ef0d3f6d64
|
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:b2e204b393ad831aa9eee5cf84e5b79d03887f1e3e2d93738fb4a2e5d492ddb8
|
3 |
+
size 2019604128
|
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,0.0000010345,0.05000,0.890
|
3 |
+
0,self_attn.v_proj,0.0000002105,0.05000,0.713
|
4 |
+
0,self_attn.q_proj,0.0000028005,0.05000,0.734
|
5 |
+
0,self_attn.o_proj,0.0000011810,0.05000,0.708
|
6 |
+
0,mlp.gate_proj,0.0000014312,0.05000,0.728
|
7 |
+
0,mlp.up_proj,0.0000012446,0.05000,0.723
|
8 |
+
0,mlp.down_proj,0.0000018967,0.05000,2.076
|
9 |
+
1,self_attn.k_proj,0.0000000372,0.05000,0.703
|
10 |
+
1,self_attn.v_proj,0.0000000142,0.05000,0.698
|
11 |
+
1,self_attn.q_proj,0.0000001447,0.05000,0.712
|
12 |
+
1,self_attn.o_proj,0.0000000181,0.05000,0.718
|
13 |
+
1,mlp.gate_proj,0.0000151709,0.05000,0.726
|
14 |
+
1,mlp.up_proj,0.0000062952,0.05000,0.732
|
15 |
+
1,mlp.down_proj,0.0000002049,0.05000,2.205
|
16 |
+
2,self_attn.k_proj,0.0000001718,0.05000,0.770
|
17 |
+
2,self_attn.v_proj,0.0000000505,0.05000,0.741
|
18 |
+
2,self_attn.q_proj,0.0000004803,0.05000,0.745
|
19 |
+
2,self_attn.o_proj,0.0000001290,0.05000,0.760
|
20 |
+
2,mlp.gate_proj,0.0000314005,0.05000,0.793
|
21 |
+
2,mlp.up_proj,0.0000175286,0.05000,0.772
|
22 |
+
2,mlp.down_proj,0.0000007901,0.05000,2.255
|
23 |
+
3,self_attn.k_proj,0.0000010903,0.05000,0.767
|
24 |
+
3,self_attn.v_proj,0.0000002457,0.05000,0.777
|
25 |
+
3,self_attn.q_proj,0.0000028919,0.05000,0.757
|
26 |
+
3,self_attn.o_proj,0.0000003798,0.05000,0.765
|
27 |
+
3,mlp.gate_proj,0.0000401692,0.05000,0.784
|
28 |
+
3,mlp.up_proj,0.0000193787,0.05000,0.777
|
29 |
+
3,mlp.down_proj,0.0000016605,0.05000,2.277
|
30 |
+
4,self_attn.k_proj,0.0000012013,0.05000,0.750
|
31 |
+
4,self_attn.v_proj,0.0000003660,0.05000,0.773
|
32 |
+
4,self_attn.q_proj,0.0000032377,0.05000,0.754
|
33 |
+
4,self_attn.o_proj,0.0000006876,0.05000,0.760
|
34 |
+
4,mlp.gate_proj,0.0000665692,0.05000,0.797
|
35 |
+
4,mlp.up_proj,0.0000360474,0.05000,0.797
|
36 |
+
4,mlp.down_proj,0.0003383170,0.05000,2.296
|
37 |
+
5,self_attn.k_proj,0.0000039737,0.05000,0.788
|
38 |
+
5,self_attn.v_proj,0.0000016558,0.05000,0.761
|
39 |
+
5,self_attn.q_proj,0.0000126068,0.05000,0.768
|
40 |
+
5,self_attn.o_proj,0.0000008714,0.05000,0.770
|
41 |
+
5,mlp.gate_proj,0.0000997196,0.05000,0.799
|
42 |
+
5,mlp.up_proj,0.0000517149,0.05000,0.790
|
43 |
+
5,mlp.down_proj,0.0000093353,0.05000,2.252
|
44 |
+
6,self_attn.k_proj,0.0000039945,0.05000,0.760
|
45 |
+
6,self_attn.v_proj,0.0000021285,0.05000,0.760
|
46 |
+
6,self_attn.q_proj,0.0000136984,0.05000,0.768
|
47 |
+
6,self_attn.o_proj,0.0000009256,0.05000,0.769
|
48 |
+
6,mlp.gate_proj,0.0001461390,0.05000,0.787
|
49 |
+
6,mlp.up_proj,0.0000788555,0.05000,0.769
|
50 |
+
6,mlp.down_proj,0.0000059479,0.05000,2.259
|
51 |
+
7,self_attn.k_proj,0.0000054761,0.05000,0.791
|
52 |
+
7,self_attn.v_proj,0.0000031289,0.05000,0.755
|
53 |
+
7,self_attn.q_proj,0.0000191049,0.05000,0.787
|
54 |
+
7,self_attn.o_proj,0.0000010236,0.05000,0.785
|
55 |
+
7,mlp.gate_proj,0.0001826673,0.05000,0.807
|
56 |
+
7,mlp.up_proj,0.0000967049,0.05000,0.811
|
57 |
+
7,mlp.down_proj,0.0000050637,0.05000,2.332
|
58 |
+
8,self_attn.k_proj,0.0000061526,0.05000,0.743
|
59 |
+
8,self_attn.v_proj,0.0000026682,0.05000,0.749
|
60 |
+
8,self_attn.q_proj,0.0000203355,0.05000,0.743
|
61 |
+
8,self_attn.o_proj,0.0000009448,0.05000,0.760
|
62 |
+
8,mlp.gate_proj,0.0001155897,0.05000,0.764
|
63 |
+
8,mlp.up_proj,0.0000636666,0.05000,0.760
|
64 |
+
8,mlp.down_proj,0.0000066151,0.05000,2.208
|
65 |
+
9,self_attn.k_proj,0.0000054034,0.05000,0.764
|
66 |
+
9,self_attn.v_proj,0.0000030490,0.05000,0.754
|
67 |
+
9,self_attn.q_proj,0.0000183273,0.05000,0.763
|
68 |
+
9,self_attn.o_proj,0.0000017297,0.05000,0.790
|
69 |
+
9,mlp.gate_proj,0.0000433400,0.05000,0.786
|
70 |
+
9,mlp.up_proj,0.0000393703,0.05000,0.774
|
71 |
+
9,mlp.down_proj,0.0000097124,0.05000,2.207
|
72 |
+
10,self_attn.k_proj,0.0000075722,0.05000,0.764
|
73 |
+
10,self_attn.v_proj,0.0000041700,0.05000,0.763
|
74 |
+
10,self_attn.q_proj,0.0000266967,0.05000,0.763
|
75 |
+
10,self_attn.o_proj,0.0000018300,0.05000,0.766
|
76 |
+
10,mlp.gate_proj,0.0000491168,0.05000,0.782
|
77 |
+
10,mlp.up_proj,0.0000445106,0.05000,0.773
|
78 |
+
10,mlp.down_proj,0.0000119973,0.05000,2.279
|
79 |
+
11,self_attn.k_proj,0.0000058302,0.05000,0.794
|
80 |
+
11,self_attn.v_proj,0.0000028397,0.05000,0.766
|
81 |
+
11,self_attn.q_proj,0.0000204721,0.05000,0.774
|
82 |
+
11,self_attn.o_proj,0.0000026513,0.05000,0.793
|
83 |
+
11,mlp.gate_proj,0.0000638938,0.05000,0.786
|
84 |
+
11,mlp.up_proj,0.0000507965,0.05000,0.794
|
85 |
+
11,mlp.down_proj,0.0000096449,0.05000,2.229
|
86 |
+
12,self_attn.k_proj,0.0000069046,0.05000,0.783
|
87 |
+
12,self_attn.v_proj,0.0000030947,0.05000,0.878
|
88 |
+
12,self_attn.q_proj,0.0000244664,0.05000,0.777
|
89 |
+
12,self_attn.o_proj,0.0000026981,0.05000,0.767
|
90 |
+
12,mlp.gate_proj,0.0000555484,0.05000,0.784
|
91 |
+
12,mlp.up_proj,0.0000520922,0.05000,0.791
|
92 |
+
12,mlp.down_proj,0.0000114576,0.05000,2.340
|
93 |
+
13,self_attn.k_proj,0.0000074464,0.05000,0.780
|
94 |
+
13,self_attn.v_proj,0.0000037448,0.05000,0.782
|
95 |
+
13,self_attn.q_proj,0.0000257437,0.05000,0.803
|
96 |
+
13,self_attn.o_proj,0.0000030890,0.05000,0.791
|
97 |
+
13,mlp.gate_proj,0.0000620614,0.05000,0.793
|
98 |
+
13,mlp.up_proj,0.0000581586,0.05000,0.786
|
99 |
+
13,mlp.down_proj,0.0000134533,0.05000,2.318
|
100 |
+
14,self_attn.k_proj,0.0000088659,0.05000,0.753
|
101 |
+
14,self_attn.v_proj,0.0000039831,0.05000,0.768
|
102 |
+
14,self_attn.q_proj,0.0000300158,0.05000,0.798
|
103 |
+
14,self_attn.o_proj,0.0000031933,0.05000,0.777
|
104 |
+
14,mlp.gate_proj,0.0000633648,0.05000,0.812
|
105 |
+
14,mlp.up_proj,0.0000597147,0.05000,0.801
|
106 |
+
14,mlp.down_proj,0.0000143671,0.05000,2.256
|
107 |
+
15,self_attn.k_proj,0.0000074085,0.05000,0.790
|
108 |
+
15,self_attn.v_proj,0.0000044317,0.05000,0.786
|
109 |
+
15,self_attn.q_proj,0.0000262538,0.05000,0.808
|
110 |
+
15,self_attn.o_proj,0.0000041149,0.05000,0.786
|
111 |
+
15,mlp.gate_proj,0.0000688258,0.05000,0.913
|
112 |
+
15,mlp.up_proj,0.0000624603,0.05000,0.794
|
113 |
+
15,mlp.down_proj,0.0000152924,0.05000,2.393
|
114 |
+
16,self_attn.k_proj,0.0000077834,0.05000,0.797
|
115 |
+
16,self_attn.v_proj,0.0000031221,0.05000,0.810
|
116 |
+
16,self_attn.q_proj,0.0000243524,0.05000,0.829
|
117 |
+
16,self_attn.o_proj,0.0000036495,0.05000,0.725
|
118 |
+
16,mlp.gate_proj,0.0000598356,0.05000,0.742
|
119 |
+
16,mlp.up_proj,0.0000587959,0.05000,0.762
|
120 |
+
16,mlp.down_proj,0.0000148449,0.05000,2.141
|
121 |
+
17,self_attn.k_proj,0.0000084560,0.05000,0.740
|
122 |
+
17,self_attn.v_proj,0.0000037563,0.05000,0.748
|
123 |
+
17,self_attn.q_proj,0.0000286677,0.05000,0.753
|
124 |
+
17,self_attn.o_proj,0.0000037051,0.05000,0.741
|
125 |
+
17,mlp.gate_proj,0.0000578213,0.05000,0.745
|
126 |
+
17,mlp.up_proj,0.0000585330,0.05000,0.764
|
127 |
+
17,mlp.down_proj,0.0000138345,0.05000,2.159
|
128 |
+
18,self_attn.k_proj,0.0000084084,0.05000,0.727
|
129 |
+
18,self_attn.v_proj,0.0000041656,0.05000,0.730
|
130 |
+
18,self_attn.q_proj,0.0000288625,0.05000,0.732
|
131 |
+
18,self_attn.o_proj,0.0000046708,0.05000,0.738
|
132 |
+
18,mlp.gate_proj,0.0000558453,0.05000,0.763
|
133 |
+
18,mlp.up_proj,0.0000582194,0.05000,0.764
|
134 |
+
18,mlp.down_proj,0.0000137017,0.05000,2.182
|
135 |
+
19,self_attn.k_proj,0.0000092760,0.05000,0.737
|
136 |
+
19,self_attn.v_proj,0.0000043924,0.05000,0.738
|
137 |
+
19,self_attn.q_proj,0.0000349181,0.05000,0.742
|
138 |
+
19,self_attn.o_proj,0.0000035104,0.05000,0.724
|
139 |
+
19,mlp.gate_proj,0.0000577134,0.05000,0.801
|
140 |
+
19,mlp.up_proj,0.0000601438,0.05000,0.736
|
141 |
+
19,mlp.down_proj,0.0000141060,0.05000,2.143
|
142 |
+
20,self_attn.k_proj,0.0000099261,0.05000,0.717
|
143 |
+
20,self_attn.v_proj,0.0000040569,0.05000,0.732
|
144 |
+
20,self_attn.q_proj,0.0000341077,0.05000,0.730
|
145 |
+
20,self_attn.o_proj,0.0000044676,0.05000,0.750
|
146 |
+
20,mlp.gate_proj,0.0000520009,0.05000,0.741
|
147 |
+
20,mlp.up_proj,0.0000570655,0.05000,0.748
|
148 |
+
20,mlp.down_proj,0.0000139291,0.05000,2.276
|
149 |
+
21,self_attn.k_proj,0.0000087641,0.05000,0.760
|
150 |
+
21,self_attn.v_proj,0.0000039525,0.05000,0.765
|
151 |
+
21,self_attn.q_proj,0.0000297285,0.05000,0.765
|
152 |
+
21,self_attn.o_proj,0.0000044091,0.05000,0.807
|
153 |
+
21,mlp.gate_proj,0.0000513103,0.05000,0.797
|
154 |
+
21,mlp.up_proj,0.0000566967,0.05000,0.768
|
155 |
+
21,mlp.down_proj,0.0000128298,0.05000,2.276
|
156 |
+
22,self_attn.k_proj,0.0000097624,0.05000,0.741
|
157 |
+
22,self_attn.v_proj,0.0000058217,0.05000,0.717
|
158 |
+
22,self_attn.q_proj,0.0000330026,0.05000,0.733
|
159 |
+
22,self_attn.o_proj,0.0000053421,0.05000,0.730
|
160 |
+
22,mlp.gate_proj,0.0000517052,0.05000,0.765
|
161 |
+
22,mlp.up_proj,0.0000574648,0.05000,0.746
|
162 |
+
22,mlp.down_proj,0.0000163017,0.05000,2.181
|
163 |
+
23,self_attn.k_proj,0.0000091015,0.05000,0.735
|
164 |
+
23,self_attn.v_proj,0.0000058541,0.05000,0.755
|
165 |
+
23,self_attn.q_proj,0.0000333629,0.05000,0.771
|
166 |
+
23,self_attn.o_proj,0.0000059910,0.05000,0.743
|
167 |
+
23,mlp.gate_proj,0.0000558644,0.05000,0.747
|
168 |
+
23,mlp.up_proj,0.0000587899,0.05000,0.765
|
169 |
+
23,mlp.down_proj,0.0000146186,0.05000,2.239
|
170 |
+
24,self_attn.k_proj,0.0000124702,0.05000,0.735
|
171 |
+
24,self_attn.v_proj,0.0000050404,0.05000,0.722
|
172 |
+
24,self_attn.q_proj,0.0000385022,0.05000,0.740
|
173 |
+
24,self_attn.o_proj,0.0000055796,0.05000,0.765
|
174 |
+
24,mlp.gate_proj,0.0000534254,0.05000,0.765
|
175 |
+
24,mlp.up_proj,0.0000571216,0.05000,0.766
|
176 |
+
24,mlp.down_proj,0.0000131968,0.05000,2.224
|
177 |
+
25,self_attn.k_proj,0.0000123175,0.05000,0.781
|
178 |
+
25,self_attn.v_proj,0.0000069963,0.05000,0.761
|
179 |
+
25,self_attn.q_proj,0.0000430898,0.05000,0.782
|
180 |
+
25,self_attn.o_proj,0.0000045160,0.05000,0.762
|
181 |
+
25,mlp.gate_proj,0.0000526878,0.05000,0.785
|
182 |
+
25,mlp.up_proj,0.0000582908,0.05000,0.789
|
183 |
+
25,mlp.down_proj,0.0000140003,0.05000,2.231
|
184 |
+
26,self_attn.k_proj,0.0000107024,0.05000,0.763
|
185 |
+
26,self_attn.v_proj,0.0000044477,0.05000,0.751
|
186 |
+
26,self_attn.q_proj,0.0000376036,0.05000,0.771
|
187 |
+
26,self_attn.o_proj,0.0000049176,0.05000,0.769
|
188 |
+
26,mlp.gate_proj,0.0000533945,0.05000,0.783
|
189 |
+
26,mlp.up_proj,0.0000615110,0.05000,0.774
|
190 |
+
26,mlp.down_proj,0.0000153276,0.05000,2.146
|
191 |
+
27,self_attn.k_proj,0.0000109775,0.05000,0.719
|
192 |
+
27,self_attn.v_proj,0.0000054582,0.05000,0.718
|
193 |
+
27,self_attn.q_proj,0.0000362237,0.05000,0.731
|
194 |
+
27,self_attn.o_proj,0.0000067432,0.05000,0.747
|
195 |
+
27,mlp.gate_proj,0.0000555439,0.05000,0.743
|
196 |
+
27,mlp.up_proj,0.0000643386,0.05000,0.737
|
197 |
+
27,mlp.down_proj,0.0000185142,0.05000,2.128
|
198 |
+
28,self_attn.k_proj,0.0000090640,0.05000,0.728
|
199 |
+
28,self_attn.v_proj,0.0000076962,0.05000,0.719
|
200 |
+
28,self_attn.q_proj,0.0000360346,0.05000,0.731
|
201 |
+
28,self_attn.o_proj,0.0000078735,0.05000,0.733
|
202 |
+
28,mlp.gate_proj,0.0000557123,0.05000,0.753
|
203 |
+
28,mlp.up_proj,0.0000655429,0.05000,0.785
|
204 |
+
28,mlp.down_proj,0.0000212102,0.05000,2.175
|
205 |
+
29,self_attn.k_proj,0.0000124052,0.05000,0.731
|
206 |
+
29,self_attn.v_proj,0.0000079066,0.05000,0.725
|
207 |
+
29,self_attn.q_proj,0.0000431871,0.05000,0.749
|
208 |
+
29,self_attn.o_proj,0.0000082407,0.05000,0.759
|
209 |
+
29,mlp.gate_proj,0.0000578802,0.05000,0.764
|
210 |
+
29,mlp.up_proj,0.0000678786,0.05000,0.769
|
211 |
+
29,mlp.down_proj,0.0000245273,0.05000,2.176
|
212 |
+
30,self_attn.k_proj,0.0000104293,0.05000,0.738
|
213 |
+
30,self_attn.v_proj,0.0000085223,0.05000,0.729
|
214 |
+
30,self_attn.q_proj,0.0000395843,0.05000,0.741
|
215 |
+
30,self_attn.o_proj,0.0000108496,0.05000,0.743
|
216 |
+
30,mlp.gate_proj,0.0000602590,0.05000,0.760
|
217 |
+
30,mlp.up_proj,0.0000700332,0.05000,0.747
|
218 |
+
30,mlp.down_proj,0.0000283786,0.05000,2.199
|
219 |
+
31,self_attn.k_proj,0.0000104518,0.05000,0.767
|
220 |
+
31,self_attn.v_proj,0.0000081897,0.05000,0.726
|
221 |
+
31,self_attn.q_proj,0.0000394588,0.05000,0.732
|
222 |
+
31,self_attn.o_proj,0.0000096139,0.05000,0.743
|
223 |
+
31,mlp.gate_proj,0.0000703862,0.05000,0.777
|
224 |
+
31,mlp.up_proj,0.0000796129,0.05000,0.779
|
225 |
+
31,mlp.down_proj,0.0000355807,0.05000,2.291
|
226 |
+
32,self_attn.k_proj,0.0000115939,0.05000,0.766
|
227 |
+
32,self_attn.v_proj,0.0000111782,0.05000,0.795
|
228 |
+
32,self_attn.q_proj,0.0000435558,0.05000,0.795
|
229 |
+
32,self_attn.o_proj,0.0000094746,0.05000,0.768
|
230 |
+
32,mlp.gate_proj,0.0000780559,0.05000,0.801
|
231 |
+
32,mlp.up_proj,0.0000864127,0.05000,0.808
|
232 |
+
32,mlp.down_proj,0.0000409517,0.05000,2.330
|
233 |
+
33,self_attn.k_proj,0.0000120175,0.05000,0.767
|
234 |
+
33,self_attn.v_proj,0.0000108337,0.05000,0.782
|
235 |
+
33,self_attn.q_proj,0.0000466797,0.05000,0.830
|
236 |
+
33,self_attn.o_proj,0.0000109753,0.05000,0.781
|
237 |
+
33,mlp.gate_proj,0.0000965948,0.05000,0.784
|
238 |
+
33,mlp.up_proj,0.0001049083,0.05000,0.780
|
239 |
+
33,mlp.down_proj,0.0000591737,0.05000,2.203
|
240 |
+
34,self_attn.k_proj,0.0000126447,0.05000,0.759
|
241 |
+
34,self_attn.v_proj,0.0000134729,0.05000,0.751
|
242 |
+
34,self_attn.q_proj,0.0000514856,0.05000,0.787
|
243 |
+
34,self_attn.o_proj,0.0000105816,0.05000,0.763
|
244 |
+
34,mlp.gate_proj,0.0001163253,0.05000,0.802
|
245 |
+
34,mlp.up_proj,0.0001224971,0.05000,0.784
|
246 |
+
34,mlp.down_proj,0.0000742405,0.05000,2.217
|
247 |
+
35,self_attn.k_proj,0.0000122679,0.05000,0.753
|
248 |
+
35,self_attn.v_proj,0.0000121535,0.05000,0.764
|
249 |
+
35,self_attn.q_proj,0.0000477665,0.05000,0.735
|
250 |
+
35,self_attn.o_proj,0.0000167390,0.05000,0.764
|
251 |
+
35,mlp.gate_proj,0.0001359225,0.05000,0.801
|
252 |
+
35,mlp.up_proj,0.0001399457,0.05000,0.819
|
253 |
+
35,mlp.down_proj,0.0000927378,0.05000,2.227
|
254 |
+
36,self_attn.k_proj,0.0000139044,0.05000,0.758
|
255 |
+
36,self_attn.v_proj,0.0000217828,0.05000,0.760
|
256 |
+
36,self_attn.q_proj,0.0000595772,0.05000,0.770
|
257 |
+
36,self_attn.o_proj,0.0000149434,0.05000,0.777
|
258 |
+
36,mlp.gate_proj,0.0001476694,0.05000,0.785
|
259 |
+
36,mlp.up_proj,0.0001536171,0.05000,0.790
|
260 |
+
36,mlp.down_proj,0.0001145156,0.05000,2.285
|
261 |
+
37,self_attn.k_proj,0.0000154484,0.05000,0.750
|
262 |
+
37,self_attn.v_proj,0.0000210078,0.05000,0.748
|
263 |
+
37,self_attn.q_proj,0.0000604325,0.05000,0.749
|
264 |
+
37,self_attn.o_proj,0.0000172585,0.05000,0.778
|
265 |
+
37,mlp.gate_proj,0.0001625307,0.05000,0.744
|
266 |
+
37,mlp.up_proj,0.0001688472,0.05000,0.728
|
267 |
+
37,mlp.down_proj,0.0001271528,0.05000,2.139
|
268 |
+
38,self_attn.k_proj,0.0000146148,0.05000,0.733
|
269 |
+
38,self_attn.v_proj,0.0000206341,0.05000,0.746
|
270 |
+
38,self_attn.q_proj,0.0000587113,0.05000,0.750
|
271 |
+
38,self_attn.o_proj,0.0000170992,0.05000,0.754
|
272 |
+
38,mlp.gate_proj,0.0001785287,0.05000,0.787
|
273 |
+
38,mlp.up_proj,0.0001879436,0.05000,0.745
|
274 |
+
38,mlp.down_proj,0.0001442409,0.05000,2.204
|
275 |
+
39,self_attn.k_proj,0.0000137990,0.05000,0.755
|
276 |
+
39,self_attn.v_proj,0.0000218538,0.05000,0.739
|
277 |
+
39,self_attn.q_proj,0.0000598911,0.05000,0.750
|
278 |
+
39,self_attn.o_proj,0.0000223876,0.05000,0.759
|
279 |
+
39,mlp.gate_proj,0.0001947201,0.05000,0.781
|
280 |
+
39,mlp.up_proj,0.0002068335,0.05000,0.764
|
281 |
+
39,mlp.down_proj,0.0001697982,0.05000,2.225
|
282 |
+
40,self_attn.k_proj,0.0000156523,0.05000,0.744
|
283 |
+
40,self_attn.v_proj,0.0000300170,0.05000,0.758
|
284 |
+
40,self_attn.q_proj,0.0000653540,0.05000,0.760
|
285 |
+
40,self_attn.o_proj,0.0000205588,0.05000,0.760
|
286 |
+
40,mlp.gate_proj,0.0002070127,0.05000,0.784
|
287 |
+
40,mlp.up_proj,0.0002211764,0.05000,0.793
|
288 |
+
40,mlp.down_proj,0.0001941007,0.05000,2.267
|
289 |
+
41,self_attn.k_proj,0.0000143720,0.05000,0.749
|
290 |
+
41,self_attn.v_proj,0.0000298829,0.05000,0.775
|
291 |
+
41,self_attn.q_proj,0.0000652320,0.05000,0.767
|
292 |
+
41,self_attn.o_proj,0.0000170312,0.05000,0.763
|
293 |
+
41,mlp.gate_proj,0.0002186584,0.05000,0.778
|
294 |
+
41,mlp.up_proj,0.0002368328,0.05000,0.794
|
295 |
+
41,mlp.down_proj,0.0002126772,0.05000,2.215
|
296 |
+
42,self_attn.k_proj,0.0000154644,0.05000,0.748
|
297 |
+
42,self_attn.v_proj,0.0000335805,0.05000,0.742
|
298 |
+
42,self_attn.q_proj,0.0000643717,0.05000,0.783
|
299 |
+
42,self_attn.o_proj,0.0000202536,0.05000,0.774
|
300 |
+
42,mlp.gate_proj,0.0002305698,0.05000,0.819
|
301 |
+
42,mlp.up_proj,0.0002531587,0.05000,0.791
|
302 |
+
42,mlp.down_proj,0.0002493867,0.05000,2.257
|
303 |
+
43,self_attn.k_proj,0.0000155882,0.05000,0.767
|
304 |
+
43,self_attn.v_proj,0.0000471215,0.05000,0.767
|
305 |
+
43,self_attn.q_proj,0.0000713312,0.05000,0.766
|
306 |
+
43,self_attn.o_proj,0.0000335444,0.05000,0.763
|
307 |
+
43,mlp.gate_proj,0.0002482548,0.05000,0.798
|
308 |
+
43,mlp.up_proj,0.0002779884,0.05000,0.790
|
309 |
+
43,mlp.down_proj,0.0003057672,0.05000,2.334
|
310 |
+
44,self_attn.k_proj,0.0000140329,0.05000,0.801
|
311 |
+
44,self_attn.v_proj,0.0000511863,0.05000,0.807
|
312 |
+
44,self_attn.q_proj,0.0000693652,0.05000,0.801
|
313 |
+
44,self_attn.o_proj,0.0000460818,0.05000,0.818
|
314 |
+
44,mlp.gate_proj,0.0002590544,0.05000,0.802
|
315 |
+
44,mlp.up_proj,0.0002945287,0.05000,0.823
|
316 |
+
44,mlp.down_proj,0.0004848206,0.05000,2.348
|
317 |
+
45,self_attn.k_proj,0.0000146667,0.05000,0.809
|
318 |
+
45,self_attn.v_proj,0.0000620527,0.05000,0.796
|
319 |
+
45,self_attn.q_proj,0.0000714048,0.05000,0.802
|
320 |
+
45,self_attn.o_proj,0.0000510727,0.05000,0.828
|
321 |
+
45,mlp.gate_proj,0.0002783232,0.05000,0.829
|
322 |
+
45,mlp.up_proj,0.0003127684,0.05000,0.836
|
323 |
+
45,mlp.down_proj,0.0005779806,0.05000,2.360
|
324 |
+
46,self_attn.k_proj,0.0000135154,0.05000,0.756
|
325 |
+
46,self_attn.v_proj,0.0000692934,0.05000,0.770
|
326 |
+
46,self_attn.q_proj,0.0000701570,0.05000,0.782
|
327 |
+
46,self_attn.o_proj,0.0000890966,0.05000,0.776
|
328 |
+
46,mlp.gate_proj,0.0002948091,0.05000,0.778
|
329 |
+
46,mlp.up_proj,0.0003179033,0.05000,0.803
|
330 |
+
46,mlp.down_proj,0.0009762892,0.05000,2.270
|
331 |
+
47,self_attn.k_proj,0.0000116310,0.05000,0.781
|
332 |
+
47,self_attn.v_proj,0.0000427193,0.05000,0.780
|
333 |
+
47,self_attn.q_proj,0.0000536965,0.05000,0.783
|
334 |
+
47,self_attn.o_proj,0.0000413580,0.05000,0.800
|
335 |
+
47,mlp.gate_proj,0.0003372399,0.05000,0.795
|
336 |
+
47,mlp.up_proj,0.0003526463,0.05000,0.810
|
337 |
+
47,mlp.down_proj,0.0019484173,0.05000,2.288
|
quantize_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"desc_act": true,
|
5 |
+
"sym": true,
|
6 |
+
"lm_head": false,
|
7 |
+
"quant_method": "gptq",
|
8 |
+
"checkpoint_format": "gptq",
|
9 |
+
"pack_dtype": "int32",
|
10 |
+
"meta": {
|
11 |
+
"quantizer": [
|
12 |
+
"gptqmodel:4.0.0-dev"
|
13 |
+
],
|
14 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
15 |
+
"damp_percent": 0.05,
|
16 |
+
"damp_auto_increment": 0.01,
|
17 |
+
"static_groups": false,
|
18 |
+
"true_sequential": true,
|
19 |
+
"mse": 0.0,
|
20 |
+
"v2": false,
|
21 |
+
"v2_alpha": 0.25
|
22 |
+
}
|
23 |
+
}
|
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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
3 |
+
size 11422654
|
tokenizer_config.json
ADDED
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"151665": {
|
182 |
+
"content": "<tool_response>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": false
|
188 |
+
},
|
189 |
+
"151666": {
|
190 |
+
"content": "</tool_response>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": false
|
196 |
+
},
|
197 |
+
"151667": {
|
198 |
+
"content": "<think>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": false
|
204 |
+
},
|
205 |
+
"151668": {
|
206 |
+
"content": "</think>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": false
|
212 |
+
}
|
213 |
+
},
|
214 |
+
"additional_special_tokens": [
|
215 |
+
"<|im_start|>",
|
216 |
+
"<|im_end|>",
|
217 |
+
"<|object_ref_start|>",
|
218 |
+
"<|object_ref_end|>",
|
219 |
+
"<|box_start|>",
|
220 |
+
"<|box_end|>",
|
221 |
+
"<|quad_start|>",
|
222 |
+
"<|quad_end|>",
|
223 |
+
"<|vision_start|>",
|
224 |
+
"<|vision_end|>",
|
225 |
+
"<|vision_pad|>",
|
226 |
+
"<|image_pad|>",
|
227 |
+
"<|video_pad|>"
|
228 |
+
],
|
229 |
+
"bos_token": null,
|
230 |
+
"clean_up_tokenization_spaces": false,
|
231 |
+
"eos_token": "<|im_end|>",
|
232 |
+
"errors": "replace",
|
233 |
+
"extra_special_tokens": {},
|
234 |
+
"model_max_length": 131072,
|
235 |
+
"pad_token": "<|fim_pad|>",
|
236 |
+
"split_special_tokens": false,
|
237 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
238 |
+
"unk_token": null,
|
239 |
+
"_commit_hash": null
|
240 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|