richarderkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningv2-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of Qwen/qwen2.5-0.5b-instruct on the customized dataset.",
    "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-instruct_gsm8k_full-finetuningV2 - GGUF\n- Model creator: https://huggingface.co/axel-datos/\n- Original model: https://huggingface.co/axel-datos/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q2_K.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q2_K.gguf) | Q2_K | 0.32GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.IQ3_XS.gguf) | IQ3_XS | 0.32GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.IQ3_S.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.IQ3_S.gguf) | IQ3_S | 0.32GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q3_K_S.gguf) | Q3_K_S | 0.32GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.IQ3_M.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.IQ3_M.gguf) | IQ3_M | 0.32GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q3_K.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q3_K.gguf) | Q3_K | 0.33GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q3_K_M.gguf) | Q3_K_M | 0.33GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q3_K_L.gguf) | Q3_K_L | 0.34GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.IQ4_XS.gguf) | IQ4_XS | 0.33GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q4_0.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q4_0.gguf) | Q4_0 | 0.33GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.IQ4_NL.gguf) | IQ4_NL | 0.33GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q4_K_S.gguf) | Q4_K_S | 0.36GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q4_K.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q4_K.gguf) | Q4_K | 0.37GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q4_K_M.gguf) | Q4_K_M | 0.37GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q4_1.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q4_1.gguf) | Q4_1 | 0.35GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q5_0.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q5_0.gguf) | Q5_0 | 0.37GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q5_K_S.gguf) | Q5_K_S | 0.38GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q5_K.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q5_K.gguf) | Q5_K | 0.39GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q5_K_M.gguf) | Q5_K_M | 0.39GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q5_1.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q5_1.gguf) | Q5_1 | 0.39GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q6_K.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q6_K.gguf) | Q6_K | 0.47GB |\n| [qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q8_0.gguf](https://huggingface.co/RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf/blob/main/qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2.Q8_0.gguf) | Q8_0 | 0.49GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: apache-2.0\nbase_model: Qwen/qwen2.5-0.5b-instruct\ntags:\n- generated_from_trainer\ndatasets:\n- customized\nmodel-index:\n- name: '2'\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# 2\n\nThis model is a fine-tuned version of [Qwen/qwen2.5-0.5b-instruct](https://huggingface.co/Qwen/qwen2.5-0.5b-instruct) on the customized dataset.\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: 2e-05\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\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: 0.01\n- mixed_precision_training: Native AMP\n\n### Training results\n\n\n\n### Framework versions\n\n- Transformers 4.46.3\n- Pytorch 2.5.1+cu121\n- Datasets 3.2.0\n- Tokenizers 0.20.3\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 1587,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-13T16:06:10.000Z",
  "created_at": "2025-03-13T15:56:15.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67d3001fa0c9c233bdb6806d",
  "id": "RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf",
  "modelId": "RichardErkhov/axel-datos_-_qwen2.5-0.5b-instruct_gsm8k_full-finetuningV2-gguf",
  "sha": "e090a2313201bc1ecbb839cd25c9ef32ac0e5c1b",
  "createdAt": "2025-03-13T15:56:15.000Z",
  "lastModified": "2025-03-13T16:06:10.000Z",
  "author": "RichardErkhov",
  "downloads": 1587,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}