second-state/llama-3-groq-8b-tool-use-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "llama3",
    "model_name": "Llama-3-Groq-8B-Tool-Use",
    "base_model": "Groq/Llama-3-Groq-8B-Tool-Use",
    "model_creator": "Groq",
    "inference": false,
    "pipeline_tag": "text-generation",
    "quantized_by": "Second State Inc.",
    "language": [
      "en"
    ],
    "frontmatter": {
      "license": "llama3",
      "model_name": "Llama-3-Groq-8B-Tool-Use",
      "base_model": "Groq/Llama-3-Groq-8B-Tool-Use",
      "model_creator": "Groq",
      "inference": "false",
      "pipeline_tag": "text-generation",
      "quantized_by": "Second State Inc.",
      "language": [
        "en"
      ]
    },
    "hero_image_url": "https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: llama3\nmodel_name: Llama-3-Groq-8B-Tool-Use\nbase_model: Groq/Llama-3-Groq-8B-Tool-Use\nmodel_creator: Groq\ninference: false\npipeline_tag: text-generation\nquantized_by: Second State Inc.\nlanguage:\n- en\n---\n\n<!-- header start -->\n<!-- 200823 -->\n<div style=\"width: auto; margin-left: auto; margin-right: auto\">\n<img src=\"https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg\" style=\"width: 100%; min-width: 400px; display: block; margin: auto;\">\n</div>\n<hr style=\"margin-top: 1.0em; margin-bottom: 1.0em;\">\n<!-- header end -->\n\n# Llama-3-Groq-8B-Tool-Use-GGUF\n\n## Original Model\n\n[Groq/Llama-3-Groq-8B-Tool-Use](https://huggingface.co/Groq/Llama-3-Groq-8B-Tool-Use)\n\n## Run with LlamaEdge\n\n- LlamaEdge version: [v0.12.4](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.4)\n\n- Prompt template\n\n  - Prompt type: `groq-llama3-tool`\n\n  - Prompt string\n\n    ```text\n    <|start_header_id|>system<|end_header_id|>\n\n    You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n    <tool_call>\n    {\"name\": <function-name>,\"arguments\": <args-dict>}\n    </tool_call>\n    \n    Here are the available tools:\n    <tools> {\n      \"name\": \"get_current_weather\",\n      \"description\": \"Get the current weather in a given location\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"location\": {\n            \"type\": \"string\",\n            \"description\": \"The city and state, e.g. San Francisco, CA\"\n          },\n          \"unit\": {\n            \"type\": \"string\",\n            \"description\": \"The temperature unit to use. Infer this from the users location.\",\n            \"enum\": [\n              \"celsius\",\n              \"fahrenheit\"\n            ]\n          }\n        },\n        \"required\": [\n          \"location\",\n          \"unit\"\n        ]\n      }\n    }\n    {\n      \"name\": \"predict_weather\",\n      \"description\": \"Predict the weather in 24 hours\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"location\": {\n            \"type\": \"string\",\n            \"description\": \"The city and state, e.g. San Francisco, CA\"\n          },\n          \"unit\": {\n            \"type\": \"string\",\n            \"description\": \"The temperature unit to use. Infer this from the users location.\",\n            \"enum\": [\n              \"celsius\",\n              \"fahrenheit\"\n            ]\n          }\n        },\n        \"required\": [\n          \"location\",\n          \"unit\"\n        ]\n      }\n    } </tools><|eot_id|><|start_header_id|>user<|end_header_id|>\n    \n    What is the weather like in San Francisco in Celsius?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n    ```\n\n- Context size: `8192`\n\n- Run as LlamaEdge service\n\n  ```bash\n  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-Groq-8B-Tool-Use-Q5_K_M.gguf \\\n    llama-api-server.wasm \\\n    --prompt-template groq-llama3-tool \\\n    --ctx-size 8192 \\\n    --model-name Llama-3-Groq-8B\n  ```\n\n## Quantized GGUF Models\n\n| Name | Quant method | Bits | Size | Use case |\n| ---- | ---- | ---- | ---- | ----- |\n| [Llama-3-Groq-8B-Tool-Use-Q2_K.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q2_K.gguf)       | Q2_K   | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |\n| [Llama-3-Groq-8B-Tool-Use-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q3_K_L.gguf)     | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |\n| [Llama-3-Groq-8B-Tool-Use-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q3_K_M.gguf)     | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |\n| [Llama-3-Groq-8B-Tool-Use-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q3_K_S.gguf)     | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |\n| [Llama-3-Groq-8B-Tool-Use-Q4_0.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q4_0.gguf)       | Q4_0   | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |\n| [Llama-3-Groq-8B-Tool-Use-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q4_K_M.gguf)     | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |\n| [Llama-3-Groq-8B-Tool-Use-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q4_K_S.gguf)     | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |\n| [Llama-3-Groq-8B-Tool-Use-Q5_0.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q5_0.gguf)       | Q5_0   | 5 | 5.60 GB| legacy; medium, balanced quality - prefer using Q4_K_M |\n| [Llama-3-Groq-8B-Tool-Use-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q5_K_M.gguf)     | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |\n| [Llama-3-Groq-8B-Tool-Use-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q5_K_S.gguf)     | Q5_K_S | 5 | 5.60 GB| large, low quality loss - recommended |\n| [Llama-3-Groq-8B-Tool-Use-Q6_K.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q6_K.gguf)     | Q6_K   | 6 | 6.60 GB| very large, extremely low quality loss |\n| [Llama-3-Groq-8B-Tool-Use-Q8_0.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-Q8_0.gguf)     | Q8_0   | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |\n| [Llama-3-Groq-8B-Tool-Use-f16.gguf](https://huggingface.co/second-state/Llama-3-Groq-8B-Tool-Use-GGUF/blob/main/Llama-3-Groq-8B-Tool-Use-f16.gguf)      | f16   | 16 | 16.1 GB|  |\n\n*Quantized with llama.cpp b3405.*",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "llama",
    "text-generation",
    "en",
    "base_model:Groq/Llama-3-Groq-8B-Tool-Use",
    "base_model:quantized:Groq/Llama-3-Groq-8B-Tool-Use",
    "license:llama3",
    "region:us",
    "conversational"
  ],
  "likes": 2,
  "downloads": 268,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-02T01:27:35.000Z",
  "created_at": "2024-07-19T02:20:06.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "6699cd569fad95dc8e3970b8",
  "id": "second-state/Llama-3-Groq-8B-Tool-Use-GGUF",
  "modelId": "second-state/Llama-3-Groq-8B-Tool-Use-GGUF",
  "sha": "39904f47d15f10b8bfde5c36a725723fef328975",
  "createdAt": "2024-07-19T02:20:06.000Z",
  "lastModified": "2024-08-02T01:27:35.000Z",
  "author": "second-state",
  "downloads": 268,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 16
}