richarderkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "",
    "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\nllama3-8b-dpo_v1 - GGUF\n- Model creator: https://huggingface.co/etri-xainlp/\n- Original model: https://huggingface.co/etri-xainlp/llama3-8b-dpo_v1/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [llama3-8b-dpo_v1.Q2_K.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q2_K.gguf) | Q2_K | 2.96GB |\n| [llama3-8b-dpo_v1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [llama3-8b-dpo_v1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [llama3-8b-dpo_v1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [llama3-8b-dpo_v1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [llama3-8b-dpo_v1.Q3_K.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q3_K.gguf) | Q3_K | 3.74GB |\n| [llama3-8b-dpo_v1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [llama3-8b-dpo_v1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [llama3-8b-dpo_v1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [llama3-8b-dpo_v1.Q4_0.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [llama3-8b-dpo_v1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [llama3-8b-dpo_v1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [llama3-8b-dpo_v1.Q4_K.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q4_K.gguf) | Q4_K | 4.58GB |\n| [llama3-8b-dpo_v1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [llama3-8b-dpo_v1.Q4_1.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [llama3-8b-dpo_v1.Q5_0.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [llama3-8b-dpo_v1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [llama3-8b-dpo_v1.Q5_K.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q5_K.gguf) | Q5_K | 5.34GB |\n| [llama3-8b-dpo_v1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [llama3-8b-dpo_v1.Q5_1.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [llama3-8b-dpo_v1.Q6_K.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q6_K.gguf) | Q6_K | 6.14GB |\n| [llama3-8b-dpo_v1.Q8_0.gguf](https://huggingface.co/RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf/blob/main/llama3-8b-dpo_v1.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\n---\n# etri-xainlp/llama3-8b-dpo_v1\n\n## Model Details\n\n**Model Developers** ETRI xainlp team\n\n**Input** text only.\n\n**Output** text only.\n\n**Model Architecture**  \n\n**Base Model**  [meta-llama/Llama-8b-hf](https://huggingface.co/meta-llama/Meta-Llama-3-8B)  \n\n**Training Dataset**  \n\n - sft+lora: 1,821 k instruction-following set \n   \n - dpo+lora: 221 k user preference set\n\n - We use A100 GPU 80GB * 8, when training.\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 1918,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-20T21:31:24.000Z",
  "created_at": "2024-08-20T19:32:37.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66c4ef551ab09ad501b20d83",
  "id": "RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf",
  "modelId": "RichardErkhov/etri-xainlp_-_llama3-8b-dpo_v1-gguf",
  "sha": "1bb35aa5c75d03b42bde6b6ab9ee61b61d4c938f",
  "createdAt": "2024-08-20T19:32:37.000Z",
  "lastModified": "2024-08-20T21:31:24.000Z",
  "author": "RichardErkhov",
  "downloads": 1918,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}