second-state/llama-3.1-nemotron-70b-reward-hf-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "llama3.1",
    "model_name": "Llama-3.1-Nemotron-70B-Reward-HF",
    "base_model": "nvidia/Llama-3.1-Nemotron-70B-Reward-HF",
    "inference": false,
    "pipeline_tag": "text-generation",
    "library_name": "transformers",
    "model_creator": "nvidia",
    "quantized_by": "Second State Inc.",
    "tags": [
      "nvidia",
      "llama3.1",
      "reward model"
    ],
    "frontmatter": {},
    "hero_image_url": "https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\r\nlicense: llama3.1\r\nmodel_name: Llama-3.1-Nemotron-70B-Reward-HF\r\nbase_model: nvidia/Llama-3.1-Nemotron-70B-Reward-HF\r\ninference: false\r\npipeline_tag: text-generation\r\nlibrary_name: transformers\r\nmodel_creator: nvidia\r\nquantized_by: Second State Inc.\r\ntags:\r\n- nvidia\r\n- llama3.1\r\n- reward model\r\n---\r\n\r\n<!-- header start -->\r\n<!-- 200823 -->\r\n<div style=\"width: auto; margin-left: auto; margin-right: auto\">\r\n<img src=\"https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg\" style=\"width: 100%; min-width: 400px; display: block; margin: auto;\">\r\n</div>\r\n<hr style=\"margin-top: 1.0em; margin-bottom: 1.0em;\">\r\n<!-- header end -->\r\n\r\n# Llama-3.1-Nemotron-70B-Reward-HF-GGUF\r\n\r\n## Original Model\r\n\r\n[nvidia/Llama-3.1-Nemotron-70B-Reward-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Reward-HF)\r\n\r\n## Run with LlamaEdge\r\n\r\n- LlamaEdge version: coming soon\r\n\r\n<!-- - LlamaEdge version: [v0.12.4](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.4) and above -->\r\n\r\n- Prompt template\r\n\r\n  - Prompt type: `llama-3-chat`\r\n\r\n  - Prompt string\r\n\r\n    ```text\r\n    <|begin_of_text|><|start_header_id|>system<|end_header_id|>\r\n\r\n    {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>\r\n\r\n    {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\r\n\r\n    {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>\r\n\r\n    {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\r\n    ```\r\n\r\n- Context size: `128000`\r\n\r\n- Run as LlamaEdge service\r\n\r\n  ```bash\r\n  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.1-Nemotron-70B-Reward-HF-Q5_K_M.gguf \\\r\n    llama-api-server.wasm \\\r\n    --prompt-template llama-3-chat \\\r\n    --ctx-size 128000 \\\r\n    --model-name Llama-3.1-Nemotron-70b\r\n  ```\r\n\r\n- Run as LlamaEdge command app\r\n\r\n  ```bash\r\n  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.1-Nemotron-70B-Reward-HF-Q5_K_M.gguf \\\r\n    llama-chat.wasm \\\r\n    --prompt-template llama-3-chat \\\r\n    --ctx-size 128000\r\n  ```\r\n\r\n## Quantized GGUF Models\r\n\r\n| Name | Quant method | Bits | Size | Use case |\r\n| ---- | ---- | ---- | ---- | ----- |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q2_K.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q2_K.gguf)     | Q2_K   | 2 | 26.4 GB| smallest, significant quality loss - not recommended for most purposes |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q3_K_L.gguf) | Q3_K_L | 3 | 37.1 GB| small, substantial quality loss |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q3_K_M.gguf) | Q3_K_M | 3 | 34.3 GB| very small, high quality loss |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q3_K_S.gguf) | Q3_K_S | 3 | 30.9 GB| very small, high quality loss |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q4_0.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q4_0.gguf)     | Q4_0   | 4 | 40 GB| legacy; small, very high quality loss - prefer using Q3_K_M |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q4_K_M.gguf) | Q4_K_M | 4 | 42.5 GB| medium, balanced quality - recommended |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q4_K_S.gguf) | Q4_K_S | 4 | 40.3 GB| small, greater quality loss |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q5_0.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q5_0.gguf)     | Q5_0   | 5 | 48.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q5_K_M.gguf) | Q5_K_M | 5 | 49.9 GB| large, very low quality loss - recommended |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q5_K_S.gguf) | Q5_K_S | 5 | 48.7 GB| large, low quality loss - recommended |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q6_K-00001-of-00002.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q6_K-00001-of-00002.gguf)     | Q6_K   | 6 | 29.8 GB| very large, extremely low quality loss |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q6_K-00002-of-00002.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q6_K-00002-of-00002.gguf)     | Q6_K   | 6 | 28.0 GB| very large, extremely low quality loss |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q8_0-00001-of-00003.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q8_0-00001-of-00003.gguf)     | Q8_0   | 8 | 29.8 GB| very large, extremely low quality loss - not recommended |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q8_0-00002-of-00003.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q8_0-00002-of-00003.gguf)     | Q8_0   | 8 | 29.8 GB| very large, extremely low quality loss - not recommended |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-Q8_0-00003-of-00003.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-Q8_0-00003-of-00003.gguf)     | Q8_0   | 8 | 15.4 GB| very large, extremely low quality loss - not recommended |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-f16-00001-of-00005.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-f16-00001-of-00005.gguf)     | f16   | 16 | 30.0 GB|  |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-f16-00002-of-00005.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-f16-00002-of-00005.gguf)     | f16   | 16 | 29.6 GB|  |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-f16-00003-of-00005.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-f16-00003-of-00005.gguf)     | f16   | 16 | 29.6 GB|  |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-f16-00004-of-00005.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-f16-00004-of-00005.gguf)     | f16   | 16 | 29.6 GB|  |\r\n| [Llama-3.1-Nemotron-70B-Reward-HF-f16-00005-of-00005.gguf](https://huggingface.co/second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF/blob/main/Llama-3.1-Nemotron-70B-Reward-HF-f16-00005-of-00005.gguf)     | f16   | 16 | 22.2 GB|  |\r\n\r\n*Quantized with llama.cpp 3932.*",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "llama",
    "text-generation",
    "nvidia",
    "llama3.1",
    "reward model",
    "base_model:nvidia/Llama-3.1-Nemotron-70B-Reward-HF",
    "base_model:quantized:nvidia/Llama-3.1-Nemotron-70B-Reward-HF",
    "license:llama3.1",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 107,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-19T02:54:29.000Z",
  "created_at": "2024-10-18T03:56:45.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "6711dc7dfe58fd40ddee5b82",
  "id": "second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF",
  "modelId": "second-state/Llama-3.1-Nemotron-70B-Reward-HF-GGUF",
  "sha": "b104736799563f7a1a504cf7fe75fcae7abc94ca",
  "createdAt": "2024-10-18T03:56:45.000Z",
  "lastModified": "2024-10-19T02:54:29.000Z",
  "author": "second-state",
  "downloads": 107,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 23
}