richarderkhov/nicholascorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the HuggingFaceH4/hh-rlhf-h4 and the data/chatbot_arena_conversations datasets. 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\ntinyllama-1.1b-chat-v1.0-arena-hh-dpo - GGUF\n- Model creator: https://huggingface.co/NicholasCorrado/\n- Original model: https://huggingface.co/NicholasCorrado/tinyllama-1.1b-chat-v1.0-arena-hh-dpo/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q2_K.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q2_K.gguf) | Q2_K | 0.4GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.IQ3_XS.gguf) | IQ3_XS | 0.44GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.IQ3_S.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.IQ3_S.gguf) | IQ3_S | 0.47GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q3_K_S.gguf) | Q3_K_S | 0.47GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.IQ3_M.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.IQ3_M.gguf) | IQ3_M | 0.48GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q3_K.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q3_K.gguf) | Q3_K | 0.51GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q3_K_M.gguf) | Q3_K_M | 0.51GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q3_K_L.gguf) | Q3_K_L | 0.55GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.IQ4_XS.gguf) | IQ4_XS | 0.57GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q4_0.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q4_0.gguf) | Q4_0 | 0.59GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.IQ4_NL.gguf) | IQ4_NL | 0.6GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q4_K_S.gguf) | Q4_K_S | 0.6GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q4_K.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q4_K.gguf) | Q4_K | 0.62GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q4_K_M.gguf) | Q4_K_M | 0.62GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q4_1.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q4_1.gguf) | Q4_1 | 0.65GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q5_0.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q5_0.gguf) | Q5_0 | 0.71GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q5_K_S.gguf) | Q5_K_S | 0.71GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q5_K.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q5_K.gguf) | Q5_K | 0.73GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q5_K_M.gguf) | Q5_K_M | 0.73GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q5_1.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q5_1.gguf) | Q5_1 | 0.77GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q6_K.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q6_K.gguf) | Q6_K | 0.84GB |\n| [tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q8_0.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf/blob/main/tinyllama-1.1b-chat-v1.0-arena-hh-dpo.Q8_0.gguf) | Q8_0 | 1.09GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: apache-2.0\nbase_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0\ntags:\n- alignment-handbook\n- trl\n- dpo\n- generated_from_trainer\n- trl\n- dpo\n- generated_from_trainer\ndatasets:\n- HuggingFaceH4/hh-rlhf-h4\n- data/chatbot_arena_conversations\nmodel-index:\n- name: tinyllama-1.1b-chat-v1.0-arena-hh-dpo\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# tinyllama-1.1b-chat-v1.0-arena-hh-dpo\n\nThis model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the HuggingFaceH4/hh-rlhf-h4 and the data/chatbot_arena_conversations datasets.\nIt achieves the following results on the evaluation set:\n- Loss: 0.6741\n- Rewards/chosen: -0.5672\n- Rewards/rejected: -0.6232\n- Rewards/accuracies: 0.5643\n- Rewards/margins: 0.0561\n- Logps/rejected: -221.2706\n- Logps/chosen: -218.0917\n- Logits/rejected: -2.3759\n- Logits/chosen: -2.3758\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-07\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 512\n- total_eval_batch_size: 64\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: 1\n\n### Training results\n\n\n\n### Framework versions\n\n- Transformers 4.44.1\n- Pytorch 2.1.2+cu121\n- Datasets 2.21.0\n- Tokenizers 0.19.1\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 869,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-17T02:30:17.000Z",
  "created_at": "2025-03-17T02:14:58.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67d785a27a5268520a4fdffe",
  "id": "RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf",
  "modelId": "RichardErkhov/NicholasCorrado_-_tinyllama-1.1b-chat-v1.0-arena-hh-dpo-gguf",
  "sha": "4087f26cf5ec60dc84c0c14c6c490cb556713eff",
  "createdAt": "2025-03-17T02:14:58.000Z",
  "lastModified": "2025-03-17T02:30:17.000Z",
  "author": "RichardErkhov",
  "downloads": 869,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}