richarderkhov/cutelemonlili_-_llama3.2_3b_numinamath-cot_100k_math_training_qwen_qwq_32b_preview-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of TaiGary/llama3.2_3b_NuminaMath-CoT_100k on the MATH_training_Qwen_QwQ_32B_Preview dataset. It achieves the following results on the evaluation set:",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nllama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview - GGUF\n- Model creator: https://huggingface.co/cutelemonlili/\n- Original model: https://huggingface.co/cutelemonlili/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q2_K.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q2_K.gguf) | Q2_K | 1.27GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.IQ3_XS.gguf) | IQ3_XS | 1.38GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.IQ3_S.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.IQ3_S.gguf) | IQ3_S | 1.44GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q3_K_S.gguf) | Q3_K_S | 1.44GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.IQ3_M.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.IQ3_M.gguf) | IQ3_M | 1.49GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q3_K.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q3_K.gguf) | Q3_K | 1.57GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q3_K_M.gguf) | Q3_K_M | 1.57GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q3_K_L.gguf) | Q3_K_L | 1.69GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.IQ4_XS.gguf) | IQ4_XS | 1.71GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q4_0.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q4_0.gguf) | Q4_0 | 1.79GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.IQ4_NL.gguf) | IQ4_NL | 1.79GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q4_K_S.gguf) | Q4_K_S | 1.8GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q4_K.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q4_K.gguf) | Q4_K | 1.88GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q4_K_M.gguf) | Q4_K_M | 1.88GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q4_1.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q4_1.gguf) | Q4_1 | 1.95GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q5_0.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q5_0.gguf) | Q5_0 | 2.11GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q5_K_S.gguf) | Q5_K_S | 2.11GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q5_K.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q5_K.gguf) | Q5_K | 2.16GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q5_K_M.gguf) | Q5_K_M | 2.16GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q5_1.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q5_1.gguf) | Q5_1 | 2.28GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q6_K.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q6_K.gguf) | Q6_K | 2.46GB |\n| [llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q8_0.gguf](https://huggingface.co/RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf/blob/main/llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview.Q8_0.gguf) | Q8_0 | 3.19GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: other\nbase_model: TaiGary/llama3.2_3b_NuminaMath-CoT_100k\ntags:\n- llama-factory\n- full\n- generated_from_trainer\nmodel-index:\n- name: MATH_training_Qwen_QwQ_32B_Preview\n  results: []\n---\n\n<!-- This model card has been generated automatically according to the information the Trainer had access to. You\nshould probably proofread and complete it, then remove this comment. -->\n\n# MATH_training_Qwen_QwQ_32B_Preview\n\nThis model is a fine-tuned version of [TaiGary/llama3.2_3b_NuminaMath-CoT_100k](https://huggingface.co/TaiGary/llama3.2_3b_NuminaMath-CoT_100k) on the MATH_training_Qwen_QwQ_32B_Preview dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.4254\n\n## Model description\n\nMore information needed\n\n## Intended uses & limitations\n\nMore information needed\n\n## Training and evaluation data\n\nMore information needed\n\n## Training procedure\n\n### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 1\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- total_train_batch_size: 8\n- total_eval_batch_size: 4\n- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments\n- lr_scheduler_type: cosine\n- num_epochs: 2\n\n### Training results\n\n| Training Loss | Epoch  | Step | Validation Loss |\n|:-------------:|:------:|:----:|:---------------:|\n| 0.4352        | 0.2999 | 200  | 0.4800          |\n| 0.4569        | 0.5997 | 400  | 0.4496          |\n| 0.4985        | 0.8996 | 600  | 0.4304          |\n| 0.3238        | 1.1994 | 800  | 0.4392          |\n| 0.2457        | 1.4993 | 1000 | 0.4288          |\n| 0.2077        | 1.7991 | 1200 | 0.4263          |\n\n\n### Framework versions\n\n- Transformers 4.46.1\n- Pytorch 2.5.1+cu124\n- Datasets 3.1.0\n- Tokenizers 0.20.3\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 129,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-28T05:12:32.000Z",
  "created_at": "2025-03-28T04:06:56.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67e62060bff60caba596e0b6",
  "id": "RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf",
  "modelId": "RichardErkhov/cutelemonlili_-_llama3.2_3b_NuminaMath-CoT_100k_MATH_training_Qwen_QwQ_32B_Preview-gguf",
  "sha": "7bb92a951e0eb80138df3e030884d6c6965351ce",
  "createdAt": "2025-03-28T04:06:56.000Z",
  "lastModified": "2025-03-28T05:12:32.000Z",
  "author": "RichardErkhov",
  "downloads": 129,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}