richarderkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the mlfoundations-dev/oh_teknium_scaling_down_random_0.4 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\nllama2_oh_teknium_scaling_down_random_0.4 - GGUF\n- Model creator: https://huggingface.co/mlfoundations-dev/\n- Original model: https://huggingface.co/mlfoundations-dev/llama2_oh_teknium_scaling_down_random_0.4/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q2_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q2_K.gguf) | Q2_K | 2.36GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.IQ3_XS.gguf) | IQ3_XS | 2.6GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.IQ3_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.IQ3_S.gguf) | IQ3_S | 2.75GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q3_K_S.gguf) | Q3_K_S | 2.75GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.IQ3_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.IQ3_M.gguf) | IQ3_M | 2.9GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q3_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q3_K.gguf) | Q3_K | 3.07GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q3_K_M.gguf) | Q3_K_M | 3.07GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q3_K_L.gguf) | Q3_K_L | 3.35GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.IQ4_XS.gguf) | IQ4_XS | 3.4GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q4_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q4_0.gguf) | Q4_0 | 3.56GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.IQ4_NL.gguf) | IQ4_NL | 3.58GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q4_K_S.gguf) | Q4_K_S | 3.59GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q4_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q4_K.gguf) | Q4_K | 3.8GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q4_K_M.gguf) | Q4_K_M | 3.8GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q4_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q4_1.gguf) | Q4_1 | 3.95GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q5_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q5_0.gguf) | Q5_0 | 4.33GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q5_K_S.gguf) | Q5_K_S | 4.33GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q5_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q5_K.gguf) | Q5_K | 4.45GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q5_K_M.gguf) | Q5_K_M | 4.45GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q5_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q5_1.gguf) | Q5_1 | 4.72GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q6_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q6_K.gguf) | Q6_K | 5.15GB |\n| [llama2_oh_teknium_scaling_down_random_0.4.Q8_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf/blob/main/llama2_oh_teknium_scaling_down_random_0.4.Q8_0.gguf) | Q8_0 | 6.67GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: llama2\nbase_model: meta-llama/Llama-2-7b-hf\ntags:\n- llama-factory\n- full\n- generated_from_trainer\nmodel-index:\n- name: llama2_oh_teknium_scaling_down_random_0.4\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# llama2_oh_teknium_scaling_down_random_0.4\n\nThis model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the mlfoundations-dev/oh_teknium_scaling_down_random_0.4 dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5329\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: 8\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 512\n- total_eval_batch_size: 64\n- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments\n- lr_scheduler_type: constant\n- num_epochs: 3.0\n\n### Training results\n\n| Training Loss | Epoch  | Step | Validation Loss |\n|:-------------:|:------:|:----:|:---------------:|\n| 0.5616        | 0.9948 | 166  | 0.5649          |\n| 0.5224        | 1.9955 | 333  | 0.5432          |\n| 0.4975        | 2.9843 | 498  | 0.5329          |\n\n\n### Framework versions\n\n- Transformers 4.46.1\n- Pytorch 2.3.0\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": 105,
  "gated": false,
  "private": false,
  "last_modified": "2025-04-07T16:59:17.000Z",
  "created_at": "2025-04-07T14:54:11.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67f3e713e1613c5d4bcb9890",
  "id": "RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf",
  "modelId": "RichardErkhov/mlfoundations-dev_-_llama2_oh_teknium_scaling_down_random_0.4-gguf",
  "sha": "c4d10a173acde1e414cabfaabde8e175d6a2a1f4",
  "createdAt": "2025-04-07T14:54:11.000Z",
  "lastModified": "2025-04-07T16:59:17.000Z",
  "author": "RichardErkhov",
  "downloads": 105,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}