richarderkhov/heejindo_-_rationale_model_e3_save5000_f4-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of meta-llama/Llama-3.2-1B 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\nrationale_model_e3_save5000_f4 - GGUF\n- Model creator: https://huggingface.co/Heejindo/\n- Original model: https://huggingface.co/Heejindo/rationale_model_e3_save5000_f4/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [rationale_model_e3_save5000_f4.Q2_K.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q2_K.gguf) | Q2_K | 0.54GB |\n| [rationale_model_e3_save5000_f4.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.IQ3_XS.gguf) | IQ3_XS | 0.58GB |\n| [rationale_model_e3_save5000_f4.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.IQ3_S.gguf) | IQ3_S | 0.6GB |\n| [rationale_model_e3_save5000_f4.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q3_K_S.gguf) | Q3_K_S | 0.6GB |\n| [rationale_model_e3_save5000_f4.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.IQ3_M.gguf) | IQ3_M | 0.61GB |\n| [rationale_model_e3_save5000_f4.Q3_K.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q3_K.gguf) | Q3_K | 0.64GB |\n| [rationale_model_e3_save5000_f4.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q3_K_M.gguf) | Q3_K_M | 0.64GB |\n| [rationale_model_e3_save5000_f4.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q3_K_L.gguf) | Q3_K_L | 0.68GB |\n| [rationale_model_e3_save5000_f4.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.IQ4_XS.gguf) | IQ4_XS | 0.7GB |\n| [rationale_model_e3_save5000_f4.Q4_0.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q4_0.gguf) | Q4_0 | 0.72GB |\n| [rationale_model_e3_save5000_f4.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.IQ4_NL.gguf) | IQ4_NL | 0.72GB |\n| [rationale_model_e3_save5000_f4.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q4_K_S.gguf) | Q4_K_S | 0.72GB |\n| [rationale_model_e3_save5000_f4.Q4_K.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q4_K.gguf) | Q4_K | 0.75GB |\n| [rationale_model_e3_save5000_f4.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q4_K_M.gguf) | Q4_K_M | 0.75GB |\n| [rationale_model_e3_save5000_f4.Q4_1.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q4_1.gguf) | Q4_1 | 0.77GB |\n| [rationale_model_e3_save5000_f4.Q5_0.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q5_0.gguf) | Q5_0 | 0.83GB |\n| [rationale_model_e3_save5000_f4.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q5_K_S.gguf) | Q5_K_S | 0.83GB |\n| [rationale_model_e3_save5000_f4.Q5_K.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q5_K.gguf) | Q5_K | 0.85GB |\n| [rationale_model_e3_save5000_f4.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q5_K_M.gguf) | Q5_K_M | 0.85GB |\n| [rationale_model_e3_save5000_f4.Q5_1.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q5_1.gguf) | Q5_1 | 0.89GB |\n| [rationale_model_e3_save5000_f4.Q6_K.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q6_K.gguf) | Q6_K | 0.95GB |\n| [rationale_model_e3_save5000_f4.Q8_0.gguf](https://huggingface.co/RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf/blob/main/rationale_model_e3_save5000_f4.Q8_0.gguf) | Q8_0 | 1.23GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: llama3.2\nbase_model: meta-llama/Llama-3.2-1B\ntags:\n- trl\n- sft\n- generated_from_trainer\nmodel-index:\n- name: rationale_model_e3_save5000_f4\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# rationale_model_e3_save5000_f4\n\nThis model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 1.9369\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: 8\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3\n\n### Training results\n\n| Training Loss | Epoch  | Step  | Validation Loss |\n|:-------------:|:------:|:-----:|:---------------:|\n| 1.7536        | 0.1907 | 1000  | 1.9369          |\n| 1.3797        | 0.3813 | 2000  | 2.0320          |\n| 1.0216        | 0.5720 | 3000  | 2.1529          |\n| 0.6624        | 0.7626 | 4000  | 2.3760          |\n| 0.3893        | 0.9533 | 5000  | 2.7429          |\n| 0.1995        | 1.1439 | 6000  | 2.9766          |\n| 0.1703        | 1.3346 | 7000  | 3.0843          |\n| 0.1489        | 1.5253 | 8000  | 3.1774          |\n| 0.1249        | 1.7159 | 9000  | 3.3298          |\n| 0.1168        | 1.9066 | 10000 | 3.4572          |\n| 0.0977        | 2.0972 | 11000 | 3.5885          |\n| 0.0951        | 2.2879 | 12000 | 3.6941          |\n| 0.092         | 2.4786 | 13000 | 3.7847          |\n| 0.0894        | 2.6692 | 14000 | 3.9039          |\n| 0.086         | 2.8599 | 15000 | 3.9903          |\n\n\n### Framework versions\n\n- Transformers 4.45.0\n- Pytorch 2.3.0\n- Datasets 2.14.4\n- Tokenizers 0.20.3\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 211,
  "gated": false,
  "private": false,
  "last_modified": "2025-02-22T23:28:41.000Z",
  "created_at": "2025-02-22T22:48:21.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67ba54354535b84d0bac890f",
  "id": "RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf",
  "modelId": "RichardErkhov/Heejindo_-_rationale_model_e3_save5000_f4-gguf",
  "sha": "b1f79535921b013f92e3212b64a2ae4a3913e1af",
  "createdAt": "2025-02-22T22:48:21.000Z",
  "lastModified": "2025-02-22T23:28:41.000Z",
  "author": "RichardErkhov",
  "downloads": 211,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}