richarderkhov/agundawar_-_chess-410m-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of EleutherAI/pythia-410m-deduped on an unknown 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\nchess-410m - GGUF\n- Model creator: https://huggingface.co/AGundawar/\n- Original model: https://huggingface.co/AGundawar/chess-410m/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [chess-410m.Q2_K.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q2_K.gguf) | Q2_K | 0.16GB |\n| [chess-410m.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.IQ3_XS.gguf) | IQ3_XS | 0.18GB |\n| [chess-410m.IQ3_S.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.IQ3_S.gguf) | IQ3_S | 0.18GB |\n| [chess-410m.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q3_K_S.gguf) | Q3_K_S | 0.18GB |\n| [chess-410m.IQ3_M.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.IQ3_M.gguf) | IQ3_M | 0.2GB |\n| [chess-410m.Q3_K.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q3_K.gguf) | Q3_K | 0.21GB |\n| [chess-410m.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q3_K_M.gguf) | Q3_K_M | 0.21GB |\n| [chess-410m.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q3_K_L.gguf) | Q3_K_L | 0.22GB |\n| [chess-410m.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.IQ4_XS.gguf) | IQ4_XS | 0.22GB |\n| [chess-410m.Q4_0.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q4_0.gguf) | Q4_0 | 0.23GB |\n| [chess-410m.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.IQ4_NL.gguf) | IQ4_NL | 0.23GB |\n| [chess-410m.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q4_K_S.gguf) | Q4_K_S | 0.23GB |\n| [chess-410m.Q4_K.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q4_K.gguf) | Q4_K | 0.25GB |\n| [chess-410m.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q4_K_M.gguf) | Q4_K_M | 0.25GB |\n| [chess-410m.Q4_1.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q4_1.gguf) | Q4_1 | 0.25GB |\n| [chess-410m.Q5_0.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q5_0.gguf) | Q5_0 | 0.27GB |\n| [chess-410m.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q5_K_S.gguf) | Q5_K_S | 0.27GB |\n| [chess-410m.Q5_K.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q5_K.gguf) | Q5_K | 0.28GB |\n| [chess-410m.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q5_K_M.gguf) | Q5_K_M | 0.28GB |\n| [chess-410m.Q5_1.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q5_1.gguf) | Q5_1 | 0.29GB |\n| [chess-410m.Q6_K.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q6_K.gguf) | Q6_K | 0.31GB |\n| [chess-410m.Q8_0.gguf](https://huggingface.co/RichardErkhov/AGundawar_-_chess-410m-gguf/blob/main/chess-410m.Q8_0.gguf) | Q8_0 | 0.4GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\nbase_model: EleutherAI/pythia-410m-deduped\ntags:\n- generated_from_trainer\nmodel-index:\n- name: chess-410m\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# chess-410m\n\nThis model is a fine-tuned version of [EleutherAI/pythia-410m-deduped](https://huggingface.co/EleutherAI/pythia-410m-deduped) on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 0.8764\n- eval_runtime: 45.8129\n- eval_samples_per_second: 170.039\n- eval_steps_per_second: 2.663\n- epoch: 0.08\n- step: 968\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: 5e-05\n- train_batch_size: 64\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- num_epochs: 1\n\n### Framework versions\n\n- Transformers 4.38.2\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.15.2\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 169,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-04T16:46:03.000Z",
  "created_at": "2024-07-04T16:36:49.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6686cfa1cd4f94ea9c69ae96",
  "id": "RichardErkhov/AGundawar_-_chess-410m-gguf",
  "modelId": "RichardErkhov/AGundawar_-_chess-410m-gguf",
  "sha": "bbdc9cdac4e8251c1b0f7d5d699108dbd6dd4d98",
  "createdAt": "2024-07-04T16:36:49.000Z",
  "lastModified": "2024-07-04T16:46:03.000Z",
  "author": "RichardErkhov",
  "downloads": 169,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}