commit e0ebb1a396a527b129ee5f5946fd223f923c95de Author: ModelHub XC Date: Thu Jul 9 12:05:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2d4e313 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.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 + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +mmlu_subject_breakdown.png filter=lfs diff=lfs merge=lfs -text +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00001-of-00002.safetensors 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..9b0a7e1 --- /dev/null +++ b/README.md @@ -0,0 +1,216 @@ +--- +base_model: unsloth/Qwen3-4B-Thinking-2507 +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +license: apache-2.0 +language: +- en +datasets: +- TeichAI/gemini-2.5-flash-11000x +pipeline_tag: text-generation +--- + +# Qwen3 4B Thinking 2507 x Gemini 2.5 Flash + + +This model was trained on about ~54.4 million tokens generated by Gemini 2.5 Flash. + +The goal of was to distill the behavior, reasoning traces, output style, and (most importantly) knowledge of Gemini-2.5 Flash. + +Categories covered in the dataset: +| Domain | Prompts | +| ------- | ---------| +| Academia | 645 | +| Finance | 1048 | +| Health | 1720 | +| Legal | 1193 | +| Marketing | 1350 | +| Programming | 1930 | +| SEO | 775 | +| Science | 1435 | +| Targeted* | 991 | + +--- + +# Benchmark Results Report + +**Date:** 2025-11-27 00:31:38 + +## Configuration +- **Quantization:** 4bit +- **Temperature:** 0.6 +- **Top P:** 0.95 +- **Top K:** 20 +- **Repetition Penalty:** 1.1 + +## Results + +![alt="Results Bar Chart"](results_bar_chart.png) + +| Model | Benchmark | Score | Total Questions | Total Correct | +|:--------------------------------------------------------|:----------------------|---------:|------------------:|----------------:| +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | arc_challenge | 0.511945 | 1172 | 600 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | gpqa_diamond_zeroshot | 0.353535 | 198 | 70 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | hellaswag | 0.504382 | 10042 | 5065 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | mmlu | 0.661587 | 14042 | 9290 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | truthfulqa_mc2 | 0.552899 | 817 | 451 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | winogrande | 0.65588 | 1267 | 831 | +| unsloth/Qwen3-4B-Thinking-2507 | arc_challenge | 0.486348 | 1172 | 570 | +| unsloth/Qwen3-4B-Thinking-2507 | gpqa_diamond_zeroshot | 0.30303 | 198 | 60 | +| unsloth/Qwen3-4B-Thinking-2507 | hellaswag | 0.479785 | 10042 | 4818 | +| unsloth/Qwen3-4B-Thinking-2507 | mmlu | 0.65532 | 14042 | 9202 | +| unsloth/Qwen3-4B-Thinking-2507 | truthfulqa_mc2 | 0.555747 | 817 | 454 | +| unsloth/Qwen3-4B-Thinking-2507 | winogrande | 0.64562 | 1267 | 818 | + +## Model Comparison vs Base + +- Base model: unsloth/Qwen3-4B-Thinking-2507 + +| Compare Model | Benchmark | Base Score | Model Score | Delta | Delta % | +|:--------------------------------------------------------|:----------------------|-------------:|--------------:|------------:|------------:| +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | arc_challenge | 0.486348 | 0.511945 | 0.0255973 | 0.0526316 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | gpqa_diamond_zeroshot | 0.30303 | 0.353535 | 0.0505051 | 0.166667 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | hellaswag | 0.479785 | 0.504382 | 0.0245967 | 0.0512661 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | mmlu | 0.65532 | 0.661587 | 0.00626691 | 0.00956314 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | truthfulqa_mc2 | 0.555747 | 0.552899 | -0.00284708 | -0.00512299 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | winogrande | 0.64562 | 0.65588 | 0.0102605 | 0.0158924 | + +### Aggregate Comparison + +| Compare Model | Benchmarks Compared | Wins vs Base | Ties vs Base | Losses vs Base | Avg Delta | +|:--------------------------------------------------------|----------------------:|---------------:|---------------:|-----------------:|------------:| +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | 6 | 5 | 0 | 1 | 0.0190632 | + +## MMLU Subject Breakdown + +![alt="MMLU Subject Breakdown"](mmlu_subject_breakdown.png) + +| Model | Subject | Benchmark | Score | Total Questions | Total Correct | +|:--------------------------------------------------------|:------------------------------------|:-----------------------------------------|---------:|------------------:|----------------:| +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | formal_logic | mmlu_formal_logic | 0.603175 | 126 | 76 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_european_history | mmlu_high_school_european_history | 0.727273 | 165 | 120 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_us_history | mmlu_high_school_us_history | 0.833333 | 204 | 170 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_world_history | mmlu_high_school_world_history | 0.801688 | 237 | 190 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | international_law | mmlu_international_law | 0.752066 | 121 | 91 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | jurisprudence | mmlu_jurisprudence | 0.777778 | 108 | 84 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | logical_fallacies | mmlu_logical_fallacies | 0.797546 | 163 | 130 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | moral_disputes | mmlu_moral_disputes | 0.67341 | 346 | 233 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | moral_scenarios | mmlu_moral_scenarios | 0.340782 | 895 | 305 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | philosophy | mmlu_philosophy | 0.694534 | 311 | 216 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | prehistory | mmlu_prehistory | 0.719136 | 324 | 233 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | professional_law | mmlu_professional_law | 0.45176 | 1534 | 693 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | world_religions | mmlu_world_religions | 0.754386 | 171 | 129 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | business_ethics | mmlu_business_ethics | 0.71 | 100 | 71 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | clinical_knowledge | mmlu_clinical_knowledge | 0.70566 | 265 | 187 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | college_medicine | mmlu_college_medicine | 0.693642 | 173 | 120 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | global_facts | mmlu_global_facts | 0.44 | 100 | 44 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | human_aging | mmlu_human_aging | 0.695067 | 223 | 155 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | management | mmlu_management | 0.854369 | 103 | 88 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | marketing | mmlu_marketing | 0.846154 | 234 | 198 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | medical_genetics | mmlu_medical_genetics | 0.77 | 100 | 77 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | miscellaneous | mmlu_miscellaneous | 0.779055 | 783 | 610 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | nutrition | mmlu_nutrition | 0.718954 | 306 | 220 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | professional_accounting | mmlu_professional_accounting | 0.528369 | 282 | 149 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | professional_medicine | mmlu_professional_medicine | 0.672794 | 272 | 183 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | virology | mmlu_virology | 0.524096 | 166 | 87 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | econometrics | mmlu_econometrics | 0.605263 | 114 | 69 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_geography | mmlu_high_school_geography | 0.823232 | 198 | 163 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_government_and_politics | mmlu_high_school_government_and_politics | 0.865285 | 193 | 167 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_macroeconomics | mmlu_high_school_macroeconomics | 0.720513 | 390 | 281 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_microeconomics | mmlu_high_school_microeconomics | 0.802521 | 238 | 191 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_psychology | mmlu_high_school_psychology | 0.86789 | 545 | 473 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | human_sexuality | mmlu_human_sexuality | 0.717557 | 131 | 94 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | professional_psychology | mmlu_professional_psychology | 0.658497 | 612 | 403 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | public_relations | mmlu_public_relations | 0.690909 | 110 | 76 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | security_studies | mmlu_security_studies | 0.726531 | 245 | 178 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | sociology | mmlu_sociology | 0.80597 | 201 | 162 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | us_foreign_policy | mmlu_us_foreign_policy | 0.82 | 100 | 82 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | abstract_algebra | mmlu_abstract_algebra | 0.57 | 100 | 56 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | anatomy | mmlu_anatomy | 0.6 | 135 | 81 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | astronomy | mmlu_astronomy | 0.809211 | 152 | 123 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | college_biology | mmlu_college_biology | 0.8125 | 144 | 117 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | college_chemistry | mmlu_college_chemistry | 0.51 | 100 | 51 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | college_computer_science | mmlu_college_computer_science | 0.57 | 100 | 56 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | college_mathematics | mmlu_college_mathematics | 0.53 | 100 | 53 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | college_physics | mmlu_college_physics | 0.509804 | 102 | 52 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | computer_security | mmlu_computer_security | 0.78 | 100 | 78 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | conceptual_physics | mmlu_conceptual_physics | 0.753191 | 235 | 177 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | electrical_engineering | mmlu_electrical_engineering | 0.724138 | 145 | 105 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | elementary_mathematics | mmlu_elementary_mathematics | 0.642857 | 378 | 243 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_biology | mmlu_high_school_biology | 0.835484 | 310 | 259 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_chemistry | mmlu_high_school_chemistry | 0.669951 | 203 | 136 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_computer_science | mmlu_high_school_computer_science | 0.82 | 100 | 82 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_mathematics | mmlu_high_school_mathematics | 0.477778 | 270 | 129 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_physics | mmlu_high_school_physics | 0.589404 | 151 | 89 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | high_school_statistics | mmlu_high_school_statistics | 0.703704 | 216 | 152 | +| TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill | machine_learning | mmlu_machine_learning | 0.455357 | 112 | 51 | +| unsloth/Qwen3-4B-Thinking-2507 | formal_logic | mmlu_formal_logic | 0.595238 | 126 | 75 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_european_history | mmlu_high_school_european_history | 0.727273 | 165 | 120 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_us_history | mmlu_high_school_us_history | 0.818627 | 204 | 167 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_world_history | mmlu_high_school_world_history | 0.797468 | 237 | 189 | +| unsloth/Qwen3-4B-Thinking-2507 | international_law | mmlu_international_law | 0.727273 | 121 | 88 | +| unsloth/Qwen3-4B-Thinking-2507 | jurisprudence | mmlu_jurisprudence | 0.777778 | 108 | 84 | +| unsloth/Qwen3-4B-Thinking-2507 | logical_fallacies | mmlu_logical_fallacies | 0.754601 | 163 | 123 | +| unsloth/Qwen3-4B-Thinking-2507 | moral_disputes | mmlu_moral_disputes | 0.67341 | 346 | 233 | +| unsloth/Qwen3-4B-Thinking-2507 | moral_scenarios | mmlu_moral_scenarios | 0.372067 | 895 | 333 | +| unsloth/Qwen3-4B-Thinking-2507 | philosophy | mmlu_philosophy | 0.672026 | 311 | 208 | +| unsloth/Qwen3-4B-Thinking-2507 | prehistory | mmlu_prehistory | 0.70679 | 324 | 229 | +| unsloth/Qwen3-4B-Thinking-2507 | professional_law | mmlu_professional_law | 0.441982 | 1534 | 678 | +| unsloth/Qwen3-4B-Thinking-2507 | world_religions | mmlu_world_religions | 0.777778 | 171 | 133 | +| unsloth/Qwen3-4B-Thinking-2507 | business_ethics | mmlu_business_ethics | 0.63 | 100 | 63 | +| unsloth/Qwen3-4B-Thinking-2507 | clinical_knowledge | mmlu_clinical_knowledge | 0.716981 | 265 | 190 | +| unsloth/Qwen3-4B-Thinking-2507 | college_medicine | mmlu_college_medicine | 0.693642 | 173 | 120 | +| unsloth/Qwen3-4B-Thinking-2507 | global_facts | mmlu_global_facts | 0.36 | 100 | 36 | +| unsloth/Qwen3-4B-Thinking-2507 | human_aging | mmlu_human_aging | 0.713004 | 223 | 159 | +| unsloth/Qwen3-4B-Thinking-2507 | management | mmlu_management | 0.864078 | 103 | 89 | +| unsloth/Qwen3-4B-Thinking-2507 | marketing | mmlu_marketing | 0.854701 | 234 | 200 | +| unsloth/Qwen3-4B-Thinking-2507 | medical_genetics | mmlu_medical_genetics | 0.8 | 100 | 80 | +| unsloth/Qwen3-4B-Thinking-2507 | miscellaneous | mmlu_miscellaneous | 0.776501 | 783 | 608 | +| unsloth/Qwen3-4B-Thinking-2507 | nutrition | mmlu_nutrition | 0.712418 | 306 | 218 | +| unsloth/Qwen3-4B-Thinking-2507 | professional_accounting | mmlu_professional_accounting | 0.549645 | 282 | 155 | +| unsloth/Qwen3-4B-Thinking-2507 | professional_medicine | mmlu_professional_medicine | 0.669118 | 272 | 182 | +| unsloth/Qwen3-4B-Thinking-2507 | virology | mmlu_virology | 0.518072 | 166 | 86 | +| unsloth/Qwen3-4B-Thinking-2507 | econometrics | mmlu_econometrics | 0.614035 | 114 | 70 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_geography | mmlu_high_school_geography | 0.777778 | 198 | 154 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_government_and_politics | mmlu_high_school_government_and_politics | 0.829016 | 193 | 160 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_macroeconomics | mmlu_high_school_macroeconomics | 0.720513 | 390 | 281 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_microeconomics | mmlu_high_school_microeconomics | 0.802521 | 238 | 191 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_psychology | mmlu_high_school_psychology | 0.851376 | 545 | 464 | +| unsloth/Qwen3-4B-Thinking-2507 | human_sexuality | mmlu_human_sexuality | 0.740458 | 131 | 97 | +| unsloth/Qwen3-4B-Thinking-2507 | professional_psychology | mmlu_professional_psychology | 0.669935 | 612 | 409 | +| unsloth/Qwen3-4B-Thinking-2507 | public_relations | mmlu_public_relations | 0.672727 | 110 | 74 | +| unsloth/Qwen3-4B-Thinking-2507 | security_studies | mmlu_security_studies | 0.706122 | 245 | 173 | +| unsloth/Qwen3-4B-Thinking-2507 | sociology | mmlu_sociology | 0.800995 | 201 | 161 | +| unsloth/Qwen3-4B-Thinking-2507 | us_foreign_policy | mmlu_us_foreign_policy | 0.82 | 100 | 82 | +| unsloth/Qwen3-4B-Thinking-2507 | abstract_algebra | mmlu_abstract_algebra | 0.55 | 100 | 55 | +| unsloth/Qwen3-4B-Thinking-2507 | anatomy | mmlu_anatomy | 0.644444 | 135 | 87 | +| unsloth/Qwen3-4B-Thinking-2507 | astronomy | mmlu_astronomy | 0.782895 | 152 | 119 | +| unsloth/Qwen3-4B-Thinking-2507 | college_biology | mmlu_college_biology | 0.763889 | 144 | 110 | +| unsloth/Qwen3-4B-Thinking-2507 | college_chemistry | mmlu_college_chemistry | 0.55 | 100 | 55 | +| unsloth/Qwen3-4B-Thinking-2507 | college_computer_science | mmlu_college_computer_science | 0.62 | 100 | 62 | +| unsloth/Qwen3-4B-Thinking-2507 | college_mathematics | mmlu_college_mathematics | 0.44 | 100 | 44 | +| unsloth/Qwen3-4B-Thinking-2507 | college_physics | mmlu_college_physics | 0.480392 | 102 | 49 | +| unsloth/Qwen3-4B-Thinking-2507 | computer_security | mmlu_computer_security | 0.73 | 100 | 73 | +| unsloth/Qwen3-4B-Thinking-2507 | conceptual_physics | mmlu_conceptual_physics | 0.723404 | 235 | 170 | +| unsloth/Qwen3-4B-Thinking-2507 | electrical_engineering | mmlu_electrical_engineering | 0.751724 | 145 | 108 | +| unsloth/Qwen3-4B-Thinking-2507 | elementary_mathematics | mmlu_elementary_mathematics | 0.645503 | 378 | 244 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_biology | mmlu_high_school_biology | 0.812903 | 310 | 252 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_chemistry | mmlu_high_school_chemistry | 0.660099 | 203 | 134 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_computer_science | mmlu_high_school_computer_science | 0.81 | 100 | 81 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_mathematics | mmlu_high_school_mathematics | 0.440741 | 270 | 119 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_physics | mmlu_high_school_physics | 0.569536 | 151 | 86 | +| unsloth/Qwen3-4B-Thinking-2507 | high_school_statistics | mmlu_high_school_statistics | 0.652778 | 216 | 141 | +| unsloth/Qwen3-4B-Thinking-2507 | machine_learning | mmlu_machine_learning | 0.428571 | 112 | 48 | + +--- + +- **Developed by:** TeichAI +- **License:** apache-2.0 +- **Finetuned from model :** unsloth/qwen3-4b-thinking-2507-unsloth-bnb-4bit + +This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. + +[](https://github.com/unslothai/unsloth) \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|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..609532b --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,88 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# 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' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- 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 + +' }} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a9f6fab --- /dev/null +++ b/config.json @@ -0,0 +1,70 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "torch_dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "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", + "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": 262144, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151654, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "4.57.1", + "unsloth_fixed": true, + "unsloth_version": "2025.11.2", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file 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/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/mmlu_subject_breakdown.png b/mmlu_subject_breakdown.png new file mode 100644 index 0000000..bb0305b --- /dev/null +++ b/mmlu_subject_breakdown.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:556c5a65156ada726fc79703ff033113917bfbaf5f1452f27a4167b18d124899 +size 1326331 diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..9c8b170 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfcdcfe64815154b0a44873e565ad4afbb93f91e5ee41fcc0f84af8d33dda7b2 +size 4967215360 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..607780c --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33b1fdef2b24329a8f6f3c01865a136f6b5b3f44f3b55a59eb4e037e9a3bd6fd +size 3077766632 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..b65d806 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,406 @@ +{ + "metadata": { + "total_parameters": 4022468096, + "total_size": 8044936192 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/results_bar_chart.png b/results_bar_chart.png new file mode 100644 index 0000000..ba38266 Binary files /dev/null and b/results_bar_chart.png differ diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..9b8043f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "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": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..f0fd73e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,241 @@ +{ + "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": false + }, + "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 + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "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": 262144, + "pad_token": "<|vision_pad|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content.strip('\\n') + '\\n\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n\n' }}\n{%- endif %}" +} \ No newline at end of file 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