ModelCloud.AI/Qwen2.5-0.5B-Instruct-gptqmodel-w4a16
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: ModelCloud.AI/Qwen2.5-0.5B-Instruct-gptqmodel-w4a16
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-11 19:59:13 +08:00
commit c066424ddd
15 changed files with 775 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
.gitattributes vendored Normal file
View File

@@ -0,0 +1,52 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
vocab.json filter=lfs diff=lfs merge=lfs -text
model.safetensors filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
merges.txt filter=lfs diff=lfs merge=lfs -text

115
README.md Normal file
View File

@@ -0,0 +1,115 @@
---
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/blob/main/LICENSE
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
base_model: Qwen/Qwen2.5-0.5B
pipeline_tag: text-generation
tags:
- gptqmodel
- modelcloud
- chat
- qwen2
- instruct
- int4
- gptq
- 4bit
- W4A16
---
GPT-QModel quantized: [GPT-QModel](https://github.com/ModelCloud/GPTQModel).
```
| Metric | MARLIN |
|--------------------------------|----------|
| arc_challenge :: acc,none | 0.2884 |
| arc_challenge :: acc_norm,none | 0.3208 |
| mmlu :: acc,none | 0.442 |
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|----------------------------------------|------:|------|-----:|--------|---|-----:|---|-----:|
|arc_challenge | 1|none | 0|acc |↑ |0.2884|± |0.0132|
| | |none | 0|acc_norm|↑ |0.3208|± |0.0136|
|mmlu | 2|none | |acc |↑ |0.4420|± |0.0041|
|mmlu_humanities | 2|none | |acc |↑ |0.4066|± |0.0070|
|mmlu_formal_logic | 1|none | 0|acc |↑ |0.3413|± |0.0424|
|mmlu_high_school_european_history | 1|none | 0|acc |↑ |0.5576|± |0.0388|
|mmlu_high_school_us_history | 1|none | 0|acc |↑ |0.4804|± |0.0351|
|mmlu_high_school_world_history | 1|none | 0|acc |↑ |0.5612|± |0.0323|
|mmlu_international_law | 1|none | 0|acc |↑ |0.6364|± |0.0439|
|mmlu_jurisprudence | 1|none | 0|acc |↑ |0.5556|± |0.0480|
|mmlu_logical_fallacies | 1|none | 0|acc |↑ |0.4785|± |0.0392|
|mmlu_moral_disputes | 1|none | 0|acc |↑ |0.5289|± |0.0269|
|mmlu_moral_scenarios | 1|none | 0|acc |↑ |0.2380|± |0.0142|
|mmlu_philosophy | 1|none | 0|acc |↑ |0.4469|± |0.0282|
|mmlu_prehistory | 1|none | 0|acc |↑ |0.5062|± |0.0278|
|mmlu_professional_law | 1|none | 0|acc |↑ |0.3514|± |0.0122|
|mmlu_world_religions | 1|none | 0|acc |↑ |0.5497|± |0.0382|
|mmlu_other | 2|none | |acc |↑ |0.4841|± |0.0088|
|mmlu_business_ethics | 1|none | 0|acc |↑ |0.5000|± |0.0503|
|mmlu_clinical_knowledge | 1|none | 0|acc |↑ |0.4717|± |0.0307|
|mmlu_college_medicine | 1|none | 0|acc |↑ |0.4624|± |0.0380|
|mmlu_global_facts | 1|none | 0|acc |↑ |0.3000|± |0.0461|
|mmlu_human_aging | 1|none | 0|acc |↑ |0.4933|± |0.0336|
|mmlu_management | 1|none | 0|acc |↑ |0.6408|± |0.0475|
|mmlu_marketing | 1|none | 0|acc |↑ |0.7051|± |0.0299|
|mmlu_medical_genetics | 1|none | 0|acc |↑ |0.5000|± |0.0503|
|mmlu_miscellaneous | 1|none | 0|acc |↑ |0.5147|± |0.0179|
|mmlu_nutrition | 1|none | 0|acc |↑ |0.5196|± |0.0286|
|mmlu_professional_accounting | 1|none | 0|acc |↑ |0.3617|± |0.0287|
|mmlu_professional_medicine | 1|none | 0|acc |↑ |0.3419|± |0.0288|
|mmlu_virology | 1|none | 0|acc |↑ |0.4277|± |0.0385|
|mmlu_social_sciences | 2|none | |acc |↑ |0.5044|± |0.0089|
|mmlu_econometrics | 1|none | 0|acc |↑ |0.3158|± |0.0437|
|mmlu_high_school_geography | 1|none | 0|acc |↑ |0.5404|± |0.0355|
|mmlu_high_school_government_and_politics| 1|none | 0|acc |↑ |0.5130|± |0.0361|
|mmlu_high_school_macroeconomics | 1|none | 0|acc |↑ |0.4410|± |0.0252|
|mmlu_high_school_microeconomics | 1|none | 0|acc |↑ |0.4370|± |0.0322|
|mmlu_high_school_psychology | 1|none | 0|acc |↑ |0.6055|± |0.0210|
|mmlu_human_sexuality | 1|none | 0|acc |↑ |0.4580|± |0.0437|
|mmlu_professional_psychology | 1|none | 0|acc |↑ |0.4314|± |0.0200|
|mmlu_public_relations | 1|none | 0|acc |↑ |0.5273|± |0.0478|
|mmlu_security_studies | 1|none | 0|acc |↑ |0.5224|± |0.0320|
|mmlu_sociology | 1|none | 0|acc |↑ |0.6070|± |0.0345|
|mmlu_us_foreign_policy | 1|none | 0|acc |↑ |0.7200|± |0.0451|
|mmlu_stem | 2|none | |acc |↑ |0.3923|± |0.0086|
|mmlu_abstract_algebra | 1|none | 0|acc |↑ |0.3100|± |0.0465|
|mmlu_anatomy | 1|none | 0|acc |↑ |0.4519|± |0.0430|
|mmlu_astronomy | 1|none | 0|acc |↑ |0.5132|± |0.0407|
|mmlu_college_biology | 1|none | 0|acc |↑ |0.4167|± |0.0412|
|mmlu_college_chemistry | 1|none | 0|acc |↑ |0.3000|± |0.0461|
|mmlu_college_computer_science | 1|none | 0|acc |↑ |0.4200|± |0.0496|
|mmlu_college_mathematics | 1|none | 0|acc |↑ |0.3400|± |0.0476|
|mmlu_college_physics | 1|none | 0|acc |↑ |0.3039|± |0.0458|
|mmlu_computer_security | 1|none | 0|acc |↑ |0.6000|± |0.0492|
|mmlu_conceptual_physics | 1|none | 0|acc |↑ |0.3532|± |0.0312|
|mmlu_electrical_engineering | 1|none | 0|acc |↑ |0.5586|± |0.0414|
|mmlu_elementary_mathematics | 1|none | 0|acc |↑ |0.3386|± |0.0244|
|mmlu_high_school_biology | 1|none | 0|acc |↑ |0.5226|± |0.0284|
|mmlu_high_school_chemistry | 1|none | 0|acc |↑ |0.3941|± |0.0344|
|mmlu_high_school_computer_science | 1|none | 0|acc |↑ |0.4100|± |0.0494|
|mmlu_high_school_mathematics | 1|none | 0|acc |↑ |0.2926|± |0.0277|
|mmlu_high_school_physics | 1|none | 0|acc |↑ |0.2781|± |0.0366|
|mmlu_high_school_statistics | 1|none | 0|acc |↑ |0.3056|± |0.0314|
|mmlu_machine_learning | 1|none | 0|acc |↑ |0.4286|± |0.0470|
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|--------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu | 2|none | |acc |↑ |0.4420|± |0.0041|
|mmlu_humanities | 2|none | |acc |↑ |0.4066|± |0.0070|
|mmlu_other | 2|none | |acc |↑ |0.4841|± |0.0088|
|mmlu_social_sciences| 2|none | |acc |↑ |0.5044|± |0.0089|
|mmlu_stem | 2|none | |acc |↑ |0.3923|± |0.0086|
```

24
added_tokens.json Normal file
View File

@@ -0,0 +1,24 @@
{
"</tool_call>": 151658,
"<tool_call>": 151657,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

54
chat_template.jinja Normal file
View File

@@ -0,0 +1,54 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0]['role'] == 'system' %}
{{- messages[0]['content'] }}
{%- else %}
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
{%- endif %}
{{- "\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>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\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" }}
{%- else %}
{%- if messages[0]['role'] == 'system' %}
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
{%- else %}
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role }}
{%- if message.content %}
{{- '\n' + message.content }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{{- tool_call.arguments | tojson }}
{{- '}\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}

80
config.json Normal file
View File

@@ -0,0 +1,80 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"pad_token_id": 151662,
"quantization_config": {
"bits": 4,
"checkpoint_format": "gptq",
"desc_act": false,
"group_size": 32,
"lm_head": false,
"meta": {
"act_group_aware": true,
"damp_auto_increment": 0.01,
"damp_percent": 0.05,
"mse": 0.0,
"quantizer": [
"gptqmodel:5.0.0-dev0"
],
"static_groups": false,
"true_sequential": true,
"uri": "https://github.com/modelcloud/gptqmodel",
"v2": false,
"v2_alpha": 0.25
},
"pack_dtype": "int32",
"pack_impl": "cpu",
"quant_method": "gptq",
"sym": true
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.57.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

11
generation_config.json Normal file
View File

@@ -0,0 +1,11 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"repetition_penalty": 1.1,
"top_k": 20,
"transformers_version": "4.57.1"
}

BIN
merges.txt (Stored with Git LFS) Normal file
View File

Binary file not shown.

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5431a0944d541d6043c2541ccdc041cc5abccb2148eb43433ea55ebe726d0afb
size 480351195

169
quant_log.csv Normal file
View File

@@ -0,0 +1,169 @@
layer,module,loss,samples,damp,time
0,self_attn.k_proj,0.0000001374,0.05000,0.411
0,self_attn.v_proj,0.0000000028,0.05000,0.584
0,self_attn.q_proj,0.0000008549,0.05000,0.584
0,self_attn.o_proj,0.0000000005,0.05000,0.248
0,mlp.up_proj,0.0000120706,0.05000,0.277
0,mlp.gate_proj,0.0000190739,0.05000,0.312
0,mlp.down_proj,0.0000002370,0.05000,1.265
1,self_attn.k_proj,0.0000014250,0.05000,0.297
1,self_attn.q_proj,0.0000049810,0.05000,0.346
1,self_attn.v_proj,0.0000001409,0.05000,0.369
1,self_attn.o_proj,0.0000000737,0.05000,0.239
1,mlp.gate_proj,0.0000336152,0.05000,0.245
1,mlp.up_proj,0.0000177082,0.05000,0.262
1,mlp.down_proj,0.0000002587,0.05000,1.278
2,self_attn.k_proj,0.0000030212,0.05000,0.289
2,self_attn.v_proj,0.0000003602,0.05000,0.443
2,self_attn.q_proj,0.0000104272,0.05000,0.447
2,self_attn.o_proj,0.0000000885,0.05000,0.270
2,mlp.up_proj,0.0000254395,0.05000,0.270
2,mlp.gate_proj,0.0000473820,0.05000,0.284
2,mlp.down_proj,0.0000063855,0.05000,1.350
3,self_attn.k_proj,0.0000036164,0.05000,0.276
3,self_attn.v_proj,0.0000008465,0.05000,0.425
3,self_attn.q_proj,0.0000145756,0.05000,0.441
3,self_attn.o_proj,0.0000001321,0.05000,0.236
3,mlp.gate_proj,0.0000963621,0.05000,0.259
3,mlp.up_proj,0.0000551544,0.05000,0.288
3,mlp.down_proj,0.0000118582,0.05000,1.231
4,self_attn.k_proj,0.0000022631,0.05000,0.307
4,self_attn.q_proj,0.0000111644,0.05000,0.412
4,self_attn.v_proj,0.0000010152,0.05000,0.417
4,self_attn.o_proj,0.0000002745,0.05000,0.240
4,mlp.up_proj,0.0000394713,0.05000,0.259
4,mlp.gate_proj,0.0000614217,0.05000,0.286
4,mlp.down_proj,0.0000007736,0.05000,1.260
5,self_attn.k_proj,0.0000028338,0.05000,0.261
5,self_attn.v_proj,0.0000013757,0.05000,0.496
5,self_attn.q_proj,0.0000140757,0.05000,0.508
5,self_attn.o_proj,0.0000002477,0.05000,0.286
5,mlp.gate_proj,0.0001037606,0.05000,0.313
5,mlp.up_proj,0.0000515816,0.05000,0.318
5,mlp.down_proj,0.0000008419,0.05000,1.268
6,self_attn.k_proj,0.0000025804,0.05000,0.257
6,self_attn.v_proj,0.0000007676,0.05000,0.399
6,self_attn.q_proj,0.0000114309,0.05000,0.400
6,self_attn.o_proj,0.0000002146,0.05000,0.251
6,mlp.gate_proj,0.0000600376,0.05000,0.267
6,mlp.up_proj,0.0000420924,0.05000,0.276
6,mlp.down_proj,0.0000009019,0.05000,1.338
7,self_attn.k_proj,0.0000039587,0.05000,0.267
7,self_attn.q_proj,0.0000166899,0.05000,0.389
7,self_attn.v_proj,0.0000013533,0.05000,0.391
7,self_attn.o_proj,0.0000003905,0.05000,0.282
7,mlp.gate_proj,0.0000611757,0.05000,0.305
7,mlp.up_proj,0.0000478114,0.05000,0.308
7,mlp.down_proj,0.0000011080,0.05000,1.370
8,self_attn.k_proj,0.0000030156,0.05000,0.240
8,self_attn.q_proj,0.0000151704,0.05000,0.440
8,self_attn.v_proj,0.0000010115,0.05000,0.443
8,self_attn.o_proj,0.0000004879,0.05000,0.233
8,mlp.gate_proj,0.0000540080,0.05000,0.284
8,mlp.up_proj,0.0000413425,0.05000,0.298
8,mlp.down_proj,0.0000007874,0.05000,1.348
9,self_attn.k_proj,0.0000090284,0.05000,0.236
9,self_attn.v_proj,0.0000023909,0.05000,0.394
9,self_attn.q_proj,0.0000352399,0.05000,0.423
9,self_attn.o_proj,0.0000003621,0.05000,0.238
9,mlp.gate_proj,0.0000505815,0.05000,0.237
9,mlp.up_proj,0.0000433161,0.05000,0.265
9,mlp.down_proj,0.0000008689,0.05000,1.370
10,self_attn.k_proj,0.0000025689,0.05000,0.246
10,self_attn.v_proj,0.0000018463,0.05000,0.368
10,self_attn.q_proj,0.0000134080,0.05000,0.373
10,self_attn.o_proj,0.0000004496,0.05000,0.223
10,mlp.up_proj,0.0000373606,0.05000,0.249
10,mlp.gate_proj,0.0000484065,0.05000,0.285
10,mlp.down_proj,0.0000007205,0.05000,1.319
11,self_attn.k_proj,0.0000096949,0.05000,0.277
11,self_attn.q_proj,0.0000358525,0.05000,0.465
11,self_attn.v_proj,0.0000026096,0.05000,0.469
11,self_attn.o_proj,0.0000003160,0.05000,0.245
11,mlp.gate_proj,0.0000471413,0.05000,0.256
11,mlp.up_proj,0.0000432136,0.05000,0.275
11,mlp.down_proj,0.0000010805,0.05000,1.266
12,self_attn.k_proj,0.0000025656,0.05000,0.277
12,self_attn.q_proj,0.0000143737,0.05000,0.480
12,self_attn.v_proj,0.0000016514,0.05000,0.485
12,self_attn.o_proj,0.0000005012,0.05000,0.252
12,mlp.up_proj,0.0000396000,0.05000,0.251
12,mlp.gate_proj,0.0000438130,0.05000,0.274
12,mlp.down_proj,0.0000008642,0.05000,1.347
13,self_attn.k_proj,0.0000047205,0.05000,0.264
13,self_attn.q_proj,0.0000238298,0.05000,0.530
13,self_attn.v_proj,0.0000020183,0.05000,0.534
13,self_attn.o_proj,0.0000004878,0.05000,0.262
13,mlp.gate_proj,0.0000470698,0.05000,0.246
13,mlp.up_proj,0.0000468081,0.05000,0.260
13,mlp.down_proj,0.0000011870,0.05000,1.242
14,self_attn.k_proj,0.0000033385,0.05000,0.275
14,self_attn.q_proj,0.0000209151,0.05000,0.441
14,self_attn.v_proj,0.0000030890,0.05000,0.447
14,self_attn.o_proj,0.0000010850,0.05000,0.270
14,mlp.up_proj,0.0000475374,0.05000,0.226
14,mlp.gate_proj,0.0000534707,0.05000,0.294
14,mlp.down_proj,0.0000014841,0.05000,1.378
15,self_attn.k_proj,0.0000037106,0.05000,0.280
15,self_attn.q_proj,0.0000186038,0.05000,0.407
15,self_attn.v_proj,0.0000024893,0.05000,0.410
15,self_attn.o_proj,0.0000006463,0.05000,0.247
15,mlp.gate_proj,0.0000625236,0.05000,0.269
15,mlp.up_proj,0.0000601912,0.05000,0.285
15,mlp.down_proj,0.0000019398,0.05000,1.263
16,self_attn.k_proj,0.0000071184,0.05000,0.239
16,self_attn.v_proj,0.0000057205,0.05000,0.528
16,self_attn.q_proj,0.0000406430,0.05000,0.543
16,self_attn.o_proj,0.0000005914,0.05000,0.268
16,mlp.up_proj,0.0000715898,0.05000,0.255
16,mlp.gate_proj,0.0000915251,0.05000,0.266
16,mlp.down_proj,0.0000035746,0.05000,1.357
17,self_attn.k_proj,0.0000038815,0.05000,0.244
17,self_attn.q_proj,0.0000259958,0.05000,0.342
17,self_attn.v_proj,0.0000036715,0.05000,0.342
17,self_attn.o_proj,0.0000004955,0.05000,0.261
17,mlp.gate_proj,0.0001284090,0.05000,0.227
17,mlp.up_proj,0.0000846460,0.05000,0.239
17,mlp.down_proj,0.0000032604,0.05000,1.224
18,self_attn.k_proj,0.0000044824,0.05000,0.252
18,self_attn.q_proj,0.0000252827,0.05000,0.333
18,self_attn.v_proj,0.0000040620,0.05000,0.336
18,self_attn.o_proj,0.0000007172,0.05000,0.221
18,mlp.up_proj,0.0000873495,0.05000,0.270
18,mlp.gate_proj,0.0001080927,0.05000,0.279
18,mlp.down_proj,0.0000040154,0.05000,1.300
19,self_attn.k_proj,0.0000040385,0.05000,0.257
19,self_attn.v_proj,0.0000038138,0.05000,0.393
19,self_attn.q_proj,0.0000248874,0.05000,0.409
19,self_attn.o_proj,0.0000008094,0.05000,0.230
19,mlp.gate_proj,0.0001446683,0.05000,0.232
19,mlp.up_proj,0.0001231465,0.05000,0.265
19,mlp.down_proj,0.0000073288,0.05000,1.241
20,self_attn.k_proj,0.0000051520,0.05000,0.257
20,self_attn.v_proj,0.0000102601,0.05000,0.331
20,self_attn.q_proj,0.0000350694,0.05000,0.341
20,self_attn.o_proj,0.0000015609,0.05000,0.217
20,mlp.up_proj,0.0001401550,0.05000,0.235
20,mlp.gate_proj,0.0001513926,0.05000,0.260
20,mlp.down_proj,0.0000101059,0.05000,1.319
21,self_attn.k_proj,0.0000052119,0.05000,0.259
21,self_attn.v_proj,0.0000155353,0.05000,0.418
21,self_attn.q_proj,0.0000392914,0.05000,0.429
21,self_attn.o_proj,0.0000030117,0.05000,0.243
21,mlp.gate_proj,0.0001529105,0.05000,0.236
21,mlp.up_proj,0.0001498237,0.05000,0.251
21,mlp.down_proj,0.0000403716,0.05000,1.181
22,self_attn.k_proj,0.0000048279,0.05000,0.280
22,self_attn.q_proj,0.0000367167,0.05000,0.423
22,self_attn.v_proj,0.0000140020,0.05000,0.435
22,self_attn.o_proj,0.0000014592,0.05000,0.233
22,mlp.gate_proj,0.0001180850,0.05000,0.251
22,mlp.up_proj,0.0001251401,0.05000,0.263
22,mlp.down_proj,0.0000136729,0.05000,1.290
23,self_attn.k_proj,0.0000055235,0.05000,0.273
23,self_attn.q_proj,0.0000443739,0.05000,0.404
23,self_attn.v_proj,0.0000110931,0.05000,0.414
23,self_attn.o_proj,0.0000029716,0.05000,0.235
23,mlp.gate_proj,0.0001360635,0.05000,0.258
23,mlp.up_proj,0.0001328737,0.05000,0.277
23,mlp.down_proj,0.0000243960,0.05000,1.267
1 layer,module,loss,samples,damp,time
2 0,self_attn.k_proj,0.0000001374,0.05000,0.411
3 0,self_attn.v_proj,0.0000000028,0.05000,0.584
4 0,self_attn.q_proj,0.0000008549,0.05000,0.584
5 0,self_attn.o_proj,0.0000000005,0.05000,0.248
6 0,mlp.up_proj,0.0000120706,0.05000,0.277
7 0,mlp.gate_proj,0.0000190739,0.05000,0.312
8 0,mlp.down_proj,0.0000002370,0.05000,1.265
9 1,self_attn.k_proj,0.0000014250,0.05000,0.297
10 1,self_attn.q_proj,0.0000049810,0.05000,0.346
11 1,self_attn.v_proj,0.0000001409,0.05000,0.369
12 1,self_attn.o_proj,0.0000000737,0.05000,0.239
13 1,mlp.gate_proj,0.0000336152,0.05000,0.245
14 1,mlp.up_proj,0.0000177082,0.05000,0.262
15 1,mlp.down_proj,0.0000002587,0.05000,1.278
16 2,self_attn.k_proj,0.0000030212,0.05000,0.289
17 2,self_attn.v_proj,0.0000003602,0.05000,0.443
18 2,self_attn.q_proj,0.0000104272,0.05000,0.447
19 2,self_attn.o_proj,0.0000000885,0.05000,0.270
20 2,mlp.up_proj,0.0000254395,0.05000,0.270
21 2,mlp.gate_proj,0.0000473820,0.05000,0.284
22 2,mlp.down_proj,0.0000063855,0.05000,1.350
23 3,self_attn.k_proj,0.0000036164,0.05000,0.276
24 3,self_attn.v_proj,0.0000008465,0.05000,0.425
25 3,self_attn.q_proj,0.0000145756,0.05000,0.441
26 3,self_attn.o_proj,0.0000001321,0.05000,0.236
27 3,mlp.gate_proj,0.0000963621,0.05000,0.259
28 3,mlp.up_proj,0.0000551544,0.05000,0.288
29 3,mlp.down_proj,0.0000118582,0.05000,1.231
30 4,self_attn.k_proj,0.0000022631,0.05000,0.307
31 4,self_attn.q_proj,0.0000111644,0.05000,0.412
32 4,self_attn.v_proj,0.0000010152,0.05000,0.417
33 4,self_attn.o_proj,0.0000002745,0.05000,0.240
34 4,mlp.up_proj,0.0000394713,0.05000,0.259
35 4,mlp.gate_proj,0.0000614217,0.05000,0.286
36 4,mlp.down_proj,0.0000007736,0.05000,1.260
37 5,self_attn.k_proj,0.0000028338,0.05000,0.261
38 5,self_attn.v_proj,0.0000013757,0.05000,0.496
39 5,self_attn.q_proj,0.0000140757,0.05000,0.508
40 5,self_attn.o_proj,0.0000002477,0.05000,0.286
41 5,mlp.gate_proj,0.0001037606,0.05000,0.313
42 5,mlp.up_proj,0.0000515816,0.05000,0.318
43 5,mlp.down_proj,0.0000008419,0.05000,1.268
44 6,self_attn.k_proj,0.0000025804,0.05000,0.257
45 6,self_attn.v_proj,0.0000007676,0.05000,0.399
46 6,self_attn.q_proj,0.0000114309,0.05000,0.400
47 6,self_attn.o_proj,0.0000002146,0.05000,0.251
48 6,mlp.gate_proj,0.0000600376,0.05000,0.267
49 6,mlp.up_proj,0.0000420924,0.05000,0.276
50 6,mlp.down_proj,0.0000009019,0.05000,1.338
51 7,self_attn.k_proj,0.0000039587,0.05000,0.267
52 7,self_attn.q_proj,0.0000166899,0.05000,0.389
53 7,self_attn.v_proj,0.0000013533,0.05000,0.391
54 7,self_attn.o_proj,0.0000003905,0.05000,0.282
55 7,mlp.gate_proj,0.0000611757,0.05000,0.305
56 7,mlp.up_proj,0.0000478114,0.05000,0.308
57 7,mlp.down_proj,0.0000011080,0.05000,1.370
58 8,self_attn.k_proj,0.0000030156,0.05000,0.240
59 8,self_attn.q_proj,0.0000151704,0.05000,0.440
60 8,self_attn.v_proj,0.0000010115,0.05000,0.443
61 8,self_attn.o_proj,0.0000004879,0.05000,0.233
62 8,mlp.gate_proj,0.0000540080,0.05000,0.284
63 8,mlp.up_proj,0.0000413425,0.05000,0.298
64 8,mlp.down_proj,0.0000007874,0.05000,1.348
65 9,self_attn.k_proj,0.0000090284,0.05000,0.236
66 9,self_attn.v_proj,0.0000023909,0.05000,0.394
67 9,self_attn.q_proj,0.0000352399,0.05000,0.423
68 9,self_attn.o_proj,0.0000003621,0.05000,0.238
69 9,mlp.gate_proj,0.0000505815,0.05000,0.237
70 9,mlp.up_proj,0.0000433161,0.05000,0.265
71 9,mlp.down_proj,0.0000008689,0.05000,1.370
72 10,self_attn.k_proj,0.0000025689,0.05000,0.246
73 10,self_attn.v_proj,0.0000018463,0.05000,0.368
74 10,self_attn.q_proj,0.0000134080,0.05000,0.373
75 10,self_attn.o_proj,0.0000004496,0.05000,0.223
76 10,mlp.up_proj,0.0000373606,0.05000,0.249
77 10,mlp.gate_proj,0.0000484065,0.05000,0.285
78 10,mlp.down_proj,0.0000007205,0.05000,1.319
79 11,self_attn.k_proj,0.0000096949,0.05000,0.277
80 11,self_attn.q_proj,0.0000358525,0.05000,0.465
81 11,self_attn.v_proj,0.0000026096,0.05000,0.469
82 11,self_attn.o_proj,0.0000003160,0.05000,0.245
83 11,mlp.gate_proj,0.0000471413,0.05000,0.256
84 11,mlp.up_proj,0.0000432136,0.05000,0.275
85 11,mlp.down_proj,0.0000010805,0.05000,1.266
86 12,self_attn.k_proj,0.0000025656,0.05000,0.277
87 12,self_attn.q_proj,0.0000143737,0.05000,0.480
88 12,self_attn.v_proj,0.0000016514,0.05000,0.485
89 12,self_attn.o_proj,0.0000005012,0.05000,0.252
90 12,mlp.up_proj,0.0000396000,0.05000,0.251
91 12,mlp.gate_proj,0.0000438130,0.05000,0.274
92 12,mlp.down_proj,0.0000008642,0.05000,1.347
93 13,self_attn.k_proj,0.0000047205,0.05000,0.264
94 13,self_attn.q_proj,0.0000238298,0.05000,0.530
95 13,self_attn.v_proj,0.0000020183,0.05000,0.534
96 13,self_attn.o_proj,0.0000004878,0.05000,0.262
97 13,mlp.gate_proj,0.0000470698,0.05000,0.246
98 13,mlp.up_proj,0.0000468081,0.05000,0.260
99 13,mlp.down_proj,0.0000011870,0.05000,1.242
100 14,self_attn.k_proj,0.0000033385,0.05000,0.275
101 14,self_attn.q_proj,0.0000209151,0.05000,0.441
102 14,self_attn.v_proj,0.0000030890,0.05000,0.447
103 14,self_attn.o_proj,0.0000010850,0.05000,0.270
104 14,mlp.up_proj,0.0000475374,0.05000,0.226
105 14,mlp.gate_proj,0.0000534707,0.05000,0.294
106 14,mlp.down_proj,0.0000014841,0.05000,1.378
107 15,self_attn.k_proj,0.0000037106,0.05000,0.280
108 15,self_attn.q_proj,0.0000186038,0.05000,0.407
109 15,self_attn.v_proj,0.0000024893,0.05000,0.410
110 15,self_attn.o_proj,0.0000006463,0.05000,0.247
111 15,mlp.gate_proj,0.0000625236,0.05000,0.269
112 15,mlp.up_proj,0.0000601912,0.05000,0.285
113 15,mlp.down_proj,0.0000019398,0.05000,1.263
114 16,self_attn.k_proj,0.0000071184,0.05000,0.239
115 16,self_attn.v_proj,0.0000057205,0.05000,0.528
116 16,self_attn.q_proj,0.0000406430,0.05000,0.543
117 16,self_attn.o_proj,0.0000005914,0.05000,0.268
118 16,mlp.up_proj,0.0000715898,0.05000,0.255
119 16,mlp.gate_proj,0.0000915251,0.05000,0.266
120 16,mlp.down_proj,0.0000035746,0.05000,1.357
121 17,self_attn.k_proj,0.0000038815,0.05000,0.244
122 17,self_attn.q_proj,0.0000259958,0.05000,0.342
123 17,self_attn.v_proj,0.0000036715,0.05000,0.342
124 17,self_attn.o_proj,0.0000004955,0.05000,0.261
125 17,mlp.gate_proj,0.0001284090,0.05000,0.227
126 17,mlp.up_proj,0.0000846460,0.05000,0.239
127 17,mlp.down_proj,0.0000032604,0.05000,1.224
128 18,self_attn.k_proj,0.0000044824,0.05000,0.252
129 18,self_attn.q_proj,0.0000252827,0.05000,0.333
130 18,self_attn.v_proj,0.0000040620,0.05000,0.336
131 18,self_attn.o_proj,0.0000007172,0.05000,0.221
132 18,mlp.up_proj,0.0000873495,0.05000,0.270
133 18,mlp.gate_proj,0.0001080927,0.05000,0.279
134 18,mlp.down_proj,0.0000040154,0.05000,1.300
135 19,self_attn.k_proj,0.0000040385,0.05000,0.257
136 19,self_attn.v_proj,0.0000038138,0.05000,0.393
137 19,self_attn.q_proj,0.0000248874,0.05000,0.409
138 19,self_attn.o_proj,0.0000008094,0.05000,0.230
139 19,mlp.gate_proj,0.0001446683,0.05000,0.232
140 19,mlp.up_proj,0.0001231465,0.05000,0.265
141 19,mlp.down_proj,0.0000073288,0.05000,1.241
142 20,self_attn.k_proj,0.0000051520,0.05000,0.257
143 20,self_attn.v_proj,0.0000102601,0.05000,0.331
144 20,self_attn.q_proj,0.0000350694,0.05000,0.341
145 20,self_attn.o_proj,0.0000015609,0.05000,0.217
146 20,mlp.up_proj,0.0001401550,0.05000,0.235
147 20,mlp.gate_proj,0.0001513926,0.05000,0.260
148 20,mlp.down_proj,0.0000101059,0.05000,1.319
149 21,self_attn.k_proj,0.0000052119,0.05000,0.259
150 21,self_attn.v_proj,0.0000155353,0.05000,0.418
151 21,self_attn.q_proj,0.0000392914,0.05000,0.429
152 21,self_attn.o_proj,0.0000030117,0.05000,0.243
153 21,mlp.gate_proj,0.0001529105,0.05000,0.236
154 21,mlp.up_proj,0.0001498237,0.05000,0.251
155 21,mlp.down_proj,0.0000403716,0.05000,1.181
156 22,self_attn.k_proj,0.0000048279,0.05000,0.280
157 22,self_attn.q_proj,0.0000367167,0.05000,0.423
158 22,self_attn.v_proj,0.0000140020,0.05000,0.435
159 22,self_attn.o_proj,0.0000014592,0.05000,0.233
160 22,mlp.gate_proj,0.0001180850,0.05000,0.251
161 22,mlp.up_proj,0.0001251401,0.05000,0.263
162 22,mlp.down_proj,0.0000136729,0.05000,1.290
163 23,self_attn.k_proj,0.0000055235,0.05000,0.273
164 23,self_attn.q_proj,0.0000443739,0.05000,0.404
165 23,self_attn.v_proj,0.0000110931,0.05000,0.414
166 23,self_attn.o_proj,0.0000029716,0.05000,0.235
167 23,mlp.gate_proj,0.0001360635,0.05000,0.258
168 23,mlp.up_proj,0.0001328737,0.05000,0.277
169 23,mlp.down_proj,0.0000243960,0.05000,1.267

25
quantize_config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"bits": 4,
"group_size": 32,
"desc_act": false,
"sym": true,
"lm_head": false,
"quant_method": "gptq",
"checkpoint_format": "gptq",
"pack_dtype": "int32",
"meta": {
"quantizer": [
"gptqmodel:5.0.0-dev0"
],
"uri": "https://github.com/modelcloud/gptqmodel",
"damp_percent": 0.05,
"damp_auto_increment": 0.01,
"static_groups": false,
"true_sequential": true,
"mse": 0.0,
"v2": false,
"v2_alpha": 0.25,
"act_group_aware": true
},
"pack_impl": "cpu"
}

25
special_tokens_map.json Normal file
View File

@@ -0,0 +1,25 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<|fim_pad|>"
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9ffb4bd5c40b82c8e9ee9be5eb1632ad555eb42250ccc4eece6325a37e78ba1a
size 11421895

207
tokenizer_config.json Normal file
View File

@@ -0,0 +1,207 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|fim_pad|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

BIN
vocab.json (Stored with Git LFS) Normal file
View File

Binary file not shown.