richarderkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg",
    "summary": "This model is a fine-tuned version of data/gemma-2b on the argilla/dpo-mix-7k 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\nzephyr-2b-gemma-dft - GGUF\n- Model creator: https://huggingface.co/ale-bay/\n- Original model: https://huggingface.co/ale-bay/zephyr-2b-gemma-dft/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [zephyr-2b-gemma-dft.Q2_K.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q2_K.gguf) | Q2_K | 1.08GB |\n| [zephyr-2b-gemma-dft.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q3_K_S.gguf) | Q3_K_S | 1.2GB |\n| [zephyr-2b-gemma-dft.Q3_K.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q3_K.gguf) | Q3_K | 1.29GB |\n| [zephyr-2b-gemma-dft.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q3_K_M.gguf) | Q3_K_M | 1.29GB |\n| [zephyr-2b-gemma-dft.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q3_K_L.gguf) | Q3_K_L | 1.36GB |\n| [zephyr-2b-gemma-dft.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.IQ4_XS.gguf) | IQ4_XS | 1.4GB |\n| [zephyr-2b-gemma-dft.Q4_0.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q4_0.gguf) | Q4_0 | 1.44GB |\n| [zephyr-2b-gemma-dft.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.IQ4_NL.gguf) | IQ4_NL | 1.45GB |\n| [zephyr-2b-gemma-dft.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q4_K_S.gguf) | Q4_K_S | 1.45GB |\n| [zephyr-2b-gemma-dft.Q4_K.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q4_K.gguf) | Q4_K | 1.52GB |\n| [zephyr-2b-gemma-dft.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q4_K_M.gguf) | Q4_K_M | 1.52GB |\n| [zephyr-2b-gemma-dft.Q4_1.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q4_1.gguf) | Q4_1 | 1.56GB |\n| [zephyr-2b-gemma-dft.Q5_0.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q5_0.gguf) | Q5_0 | 1.68GB |\n| [zephyr-2b-gemma-dft.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q5_K_S.gguf) | Q5_K_S | 1.68GB |\n| [zephyr-2b-gemma-dft.Q5_K.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q5_K.gguf) | Q5_K | 1.71GB |\n| [zephyr-2b-gemma-dft.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q5_K_M.gguf) | Q5_K_M | 1.71GB |\n| [zephyr-2b-gemma-dft.Q5_1.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q5_1.gguf) | Q5_1 | 1.79GB |\n| [zephyr-2b-gemma-dft.Q6_K.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q6_K.gguf) | Q6_K | 1.92GB |\n| [zephyr-2b-gemma-dft.Q8_0.gguf](https://huggingface.co/RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf/blob/main/zephyr-2b-gemma-dft.Q8_0.gguf) | Q8_0 | 2.49GB |\n\n\n\n\nOriginal model description:\n---\nbase_model: data/gemma-2b\ntags:\n- alignment-handbook\n- trl\n- sft\n- generated_from_trainer\n- trl\n- sft\n- generated_from_trainer\ndatasets:\n- argilla/dpo-mix-7k\nmodel-index:\n- name: zephyr-2b-gemma-dft\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[<img src=\"https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg\" alt=\"Visualize in Weights & Biases\" width=\"200\" height=\"32\"/>](https://zebra.wandb.io/cto/distillm/runs/vxz2pnbq)\n# zephyr-2b-gemma-dft\n\nThis model is a fine-tuned version of [data/gemma-2b](https://huggingface.co/data/gemma-2b) on the argilla/dpo-mix-7k dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.0001\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: 8\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 0\n\n### Training results\n\n\n\n### Framework versions\n\n- Transformers 4.42.4\n- Pytorch 2.3.1+cu121\n- Datasets 2.20.0\n- Tokenizers 0.19.1\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 185,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-30T01:40:23.000Z",
  "created_at": "2024-10-30T00:09:31.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6721793b33898ac10567fcb7",
  "id": "RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf",
  "modelId": "RichardErkhov/ale-bay_-_zephyr-2b-gemma-dft-gguf",
  "sha": "1046e9916b670e91f7d3f3b7909925f6ba3b8b6c",
  "createdAt": "2024-10-30T00:09:31.000Z",
  "lastModified": "2024-10-30T01:40:23.000Z",
  "author": "RichardErkhov",
  "downloads": 185,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}