commit c066424dddf27975809ad8bf41d649e0ba83ed2d Author: ModelHub XC Date: Tue Aug 11 19:59:13 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: ModelCloud.AI/Qwen2.5-0.5B-Instruct-gptqmodel-w4a16 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5813968 --- /dev/null +++ b/.gitattributes @@ -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 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..0270e0e --- /dev/null +++ b/README.md @@ -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| +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 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 +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -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 XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|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\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- 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 %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..20feacc --- /dev/null +++ b/config.json @@ -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 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..474d3a1 --- /dev/null +++ b/generation_config.json @@ -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" +} \ No newline at end of file diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..e9ef5ec --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5431a0944d541d6043c2541ccdc041cc5abccb2148eb43433ea55ebe726d0afb +size 480351195 diff --git a/quant_log.csv b/quant_log.csv new file mode 100644 index 0000000..023ef1b --- /dev/null +++ b/quant_log.csv @@ -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 diff --git a/quantize_config.json b/quantize_config.json new file mode 100644 index 0000000..acbea15 --- /dev/null +++ b/quantize_config.json @@ -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" +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..3b5852b --- /dev/null +++ b/special_tokens_map.json @@ -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|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..7c81e10 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ffb4bd5c40b82c8e9ee9be5eb1632ad555eb42250ccc4eece6325a37e78ba1a +size 11421895 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..6913521 --- /dev/null +++ b/tokenizer_config.json @@ -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": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "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 +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833