richarderkhov/jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the princeton-nlp/llama3-ultrafeedback-armorm 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\nllama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log - GGUF\n- Model creator: https://huggingface.co/Jimmy19991222/\n- Original model: https://huggingface.co/Jimmy19991222/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q2_K.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q2_K.gguf) | Q2_K | 2.96GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q3_K.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q3_K.gguf) | Q3_K | 3.74GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q4_0.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q4_K.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q4_K.gguf) | Q4_K | 4.58GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q4_1.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q5_0.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q5_K.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q5_K.gguf) | Q5_K | 5.34GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q5_1.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q6_K.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q6_K.gguf) | Q6_K | 6.14GB |\n| [llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q8_0.gguf](https://huggingface.co/RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf/blob/main/llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: llama3\nbase_model: meta-llama/Meta-Llama-3-8B-Instruct\ntags:\n- alignment-handbook\n- generated_from_trainer\ndatasets:\n- princeton-nlp/llama3-ultrafeedback-armorm\nmodel-index:\n- name: llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log\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# llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log\n\nThis model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the princeton-nlp/llama3-ultrafeedback-armorm dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 1.2717\n- Rewards/chosen: -15.2175\n- Rewards/rejected: -20.4236\n- Rewards/accuracies: 0.8354\n- Rewards/margins: 5.2061\n- Logps/rejected: -2.0424\n- Logps/chosen: -1.5218\n- Logits/rejected: -1.3970\n- Logits/chosen: -1.3868\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: 1e-06\n- train_batch_size: 2\n- eval_batch_size: 4\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 128\n- total_eval_batch_size: 16\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| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |\n|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|\n| 1.237         | 0.8550 | 400  | 1.2717          | -15.2175       | -20.4236         | 0.8354             | 5.2061          | -2.0424        | -1.5218      | -1.3970         | -1.3868       |\n\n\n### Framework versions\n\n- Transformers 4.44.2\n- Pytorch 2.2.0\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": 132,
  "gated": false,
  "private": false,
  "last_modified": "2025-05-24T14:56:39.000Z",
  "created_at": "2025-05-24T06:51:06.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "68316c5afcf0624d8b8812ad",
  "id": "RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf",
  "modelId": "RichardErkhov/Jimmy19991222_-_llama-3-8b-instruct-gapo-v2-rouge1-beta10-gamma0.3-lr1.0e-6-scale-log-gguf",
  "sha": "5cd540db2afe84561500e73a93efeb07149534d4",
  "createdAt": "2025-05-24T06:51:06.000Z",
  "lastModified": "2025-05-24T14:56:39.000Z",
  "author": "RichardErkhov",
  "downloads": 132,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}