richarderkhov/mlfoundations-dev_-_oh_dcft_v3_wo_slimorca_550k-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the mlfoundations-dev/OH_DCFT_V3_wo_slimorca_550k 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\nOH_DCFT_V3_wo_slimorca_550k - GGUF\n- Model creator: https://huggingface.co/mlfoundations-dev/\n- Original model: https://huggingface.co/mlfoundations-dev/OH_DCFT_V3_wo_slimorca_550k/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [OH_DCFT_V3_wo_slimorca_550k.Q2_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q2_K.gguf) | Q2_K | 2.96GB |\n| [OH_DCFT_V3_wo_slimorca_550k.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [OH_DCFT_V3_wo_slimorca_550k.IQ3_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [OH_DCFT_V3_wo_slimorca_550k.IQ3_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q3_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q3_K.gguf) | Q3_K | 3.74GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [OH_DCFT_V3_wo_slimorca_550k.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q4_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [OH_DCFT_V3_wo_slimorca_550k.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q4_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q4_K.gguf) | Q4_K | 4.58GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q4_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q5_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q5_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q5_K.gguf) | Q5_K | 5.34GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q5_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q6_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q6_K.gguf) | Q6_K | 6.14GB |\n| [OH_DCFT_V3_wo_slimorca_550k.Q8_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf/blob/main/OH_DCFT_V3_wo_slimorca_550k.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: llama3.1\nbase_model: meta-llama/Llama-3.1-8B\ntags:\n- llama-factory\n- full\n- generated_from_trainer\nmodel-index:\n- name: OH_DCFT_V3_wo_slimorca_550k\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# OH_DCFT_V3_wo_slimorca_550k\n\nThis model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the mlfoundations-dev/OH_DCFT_V3_wo_slimorca_550k dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.6377\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-06\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 16\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 512\n- total_eval_batch_size: 128\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.1\n- lr_scheduler_warmup_steps: 1738\n- num_epochs: 3.0\n\n### Training results\n\n| Training Loss | Epoch  | Step | Validation Loss |\n|:-------------:|:------:|:----:|:---------------:|\n| 0.6466        | 0.9984 | 315  | 0.6489          |\n| 0.612         | 2.0    | 631  | 0.6384          |\n| 0.5816        | 2.9952 | 945  | 0.6377          |\n\n\n### Framework versions\n\n- Transformers 4.45.2\n- Pytorch 2.3.0\n- Datasets 2.21.0\n- Tokenizers 0.20.1\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 147,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-14T04:24:24.000Z",
  "created_at": "2025-07-14T03:23:30.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "687478320c203ef93e2e92b4",
  "id": "RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf",
  "modelId": "RichardErkhov/mlfoundations-dev_-_OH_DCFT_V3_wo_slimorca_550k-gguf",
  "sha": "cf73a798adf727165f7c4c7a4e5f3a6c6655d3c8",
  "createdAt": "2025-07-14T03:23:30.000Z",
  "lastModified": "2025-07-14T04:24:24.000Z",
  "author": "RichardErkhov",
  "downloads": 147,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}