richarderkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of Qwen/Qwen2.5-Coder-0.5B-Instruct on the anghabench 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\nqwen2.5_0.5b_llamafac_130k-stack - GGUF\n- Model creator: https://huggingface.co/ahmedheakl/\n- Original model: https://huggingface.co/ahmedheakl/qwen2.5_0.5b_llamafac_130k-stack/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q2_K.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q2_K.gguf) | Q2_K | 0.39GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.IQ3_XS.gguf) | IQ3_XS | 0.39GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.IQ3_S.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.IQ3_S.gguf) | IQ3_S | 0.39GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q3_K_S.gguf) | Q3_K_S | 0.39GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.IQ3_M.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.IQ3_M.gguf) | IQ3_M | 0.39GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q3_K.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q3_K.gguf) | Q3_K | 0.4GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q3_K_M.gguf) | Q3_K_M | 0.4GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q3_K_L.gguf) | Q3_K_L | 0.42GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.IQ4_XS.gguf) | IQ4_XS | 0.4GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q4_0.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q4_0.gguf) | Q4_0 | 0.4GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.IQ4_NL.gguf) | IQ4_NL | 0.4GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q4_K_S.gguf) | Q4_K_S | 0.45GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q4_K.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q4_K.gguf) | Q4_K | 0.46GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q4_K_M.gguf) | Q4_K_M | 0.46GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q4_1.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q4_1.gguf) | Q4_1 | 0.43GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q5_0.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q5_0.gguf) | Q5_0 | 0.46GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q5_K_S.gguf) | Q5_K_S | 0.48GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q5_K.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q5_K.gguf) | Q5_K | 0.49GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q5_K_M.gguf) | Q5_K_M | 0.49GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q5_1.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q5_1.gguf) | Q5_1 | 0.49GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q6_K.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q6_K.gguf) | Q6_K | 0.61GB |\n| [qwen2.5_0.5b_llamafac_130k-stack.Q8_0.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf/blob/main/qwen2.5_0.5b_llamafac_130k-stack.Q8_0.gguf) | Q8_0 | 0.63GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: apache-2.0\nbase_model: Qwen/Qwen2.5-Coder-0.5B-Instruct\ntags:\n- llama-factory\n- full\n- generated_from_trainer\nmodel-index:\n- name: qwen2.5_0.5b_llamafac_130k-stack\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# qwen2.5_0.5b_llamafac_130k-stack\n\nThis model is a fine-tuned version of [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct) on the anghabench dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.0068\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: 0.0002\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 16\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: linear\n- num_epochs: 3.0\n\n### Training results\n\n| Training Loss | Epoch  | Step  | Validation Loss |\n|:-------------:|:------:|:-----:|:---------------:|\n| 0.012         | 1.9565 | 10500 | 0.0098          |\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": 123,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-14T03:13:22.000Z",
  "created_at": "2025-03-14T02:59:46.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67d39ba27443e648e8a3d53a",
  "id": "RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf",
  "modelId": "RichardErkhov/ahmedheakl_-_qwen2.5_0.5b_llamafac_130k-stack-gguf",
  "sha": "00c6002e35821c9b8d861b6f8d18ab01cbf214b8",
  "createdAt": "2025-03-14T02:59:46.000Z",
  "lastModified": "2025-03-14T03:13:22.000Z",
  "author": "RichardErkhov",
  "downloads": 123,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}