richarderkhov/nicholascorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of allenai/tulu-2-7b on the data/tulu-2-7b-uf-rlced-conifer-ref 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\nuf-rlced-conifer_tulu-2-7b-group-dpo-no-clip - GGUF\n- Model creator: https://huggingface.co/NicholasCorrado/\n- Original model: https://huggingface.co/NicholasCorrado/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q2_K.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q2_K.gguf) | Q2_K | 2.36GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.IQ3_XS.gguf) | IQ3_XS | 2.6GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.IQ3_S.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.IQ3_S.gguf) | IQ3_S | 2.75GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q3_K_S.gguf) | Q3_K_S | 2.75GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.IQ3_M.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.IQ3_M.gguf) | IQ3_M | 2.9GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q3_K.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q3_K.gguf) | Q3_K | 3.07GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q3_K_M.gguf) | Q3_K_M | 3.07GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q3_K_L.gguf) | Q3_K_L | 3.35GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.IQ4_XS.gguf) | IQ4_XS | 3.4GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q4_0.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q4_0.gguf) | Q4_0 | 3.56GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.IQ4_NL.gguf) | IQ4_NL | 3.58GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q4_K_S.gguf) | Q4_K_S | 3.59GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q4_K.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q4_K.gguf) | Q4_K | 3.8GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q4_K_M.gguf) | Q4_K_M | 3.8GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q4_1.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q4_1.gguf) | Q4_1 | 3.95GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q5_0.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q5_0.gguf) | Q5_0 | 4.33GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q5_K_S.gguf) | Q5_K_S | 4.33GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q5_K.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q5_K.gguf) | Q5_K | 4.45GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q5_K_M.gguf) | Q5_K_M | 4.45GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q5_1.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q5_1.gguf) | Q5_1 | 4.72GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q6_K.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q6_K.gguf) | Q6_K | 5.15GB |\n| [uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q8_0.gguf](https://huggingface.co/RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf/blob/main/uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip.Q8_0.gguf) | Q8_0 | 6.67GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nbase_model: allenai/tulu-2-7b\ntags:\n- alignment-handbook\n- trl\n- dpo\n- generated_from_trainer\n- trl\n- dpo\n- generated_from_trainer\ndatasets:\n- data/tulu-2-7b-uf-rlced-conifer-ref\nmodel-index:\n- name: uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip\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# uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip\n\nThis model is a fine-tuned version of [allenai/tulu-2-7b](https://huggingface.co/allenai/tulu-2-7b) on the data/tulu-2-7b-uf-rlced-conifer-ref dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.6073\n- Rewards/chosen: -0.2204\n- Rewards/rejected: -0.4189\n- Rewards/accuracies: 0.7876\n- Rewards/margins: 0.1984\n- Logps/rejected: -527.1544\n- Logps/chosen: -483.4286\n- Logits/rejected: -0.9235\n- Logits/chosen: -0.9285\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: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\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": 159,
  "gated": false,
  "private": false,
  "last_modified": "2025-04-06T16:59:39.000Z",
  "created_at": "2025-04-06T15:12:24.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67f299d88446d48efe3edb3b",
  "id": "RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf",
  "modelId": "RichardErkhov/NicholasCorrado_-_uf-rlced-conifer_tulu-2-7b-group-dpo-no-clip-gguf",
  "sha": "e68bb23512ae3827089db73789b8d71b5646bc5e",
  "createdAt": "2025-04-06T15:12:24.000Z",
  "lastModified": "2025-04-06T16:59:39.000Z",
  "author": "RichardErkhov",
  "downloads": 159,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}