second-state/Llama-3.2-3B-Instruct-GGUF

      <|begin_of_text|><|start_header_id|>system<|end_header_id|>
  
      {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
  
      {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
  
      {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
  
      {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

      <|begin_of_text|><|start_header_id|>system<|end_header_id|>

      {system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>
  
      Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
  
      Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
  
      [{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]}},"required":["location","unit"]}}}]
  
      Question: {user_message}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Q5_K_M.gguf \
        llama-api-server.wasm \
        --prompt-template llama-3-chat \
        --ctx-size 128000 \
        --model-name Llama-3.2-3b

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Q5_K_M.gguf \
        llama-api-server.wasm \
        --prompt-template llama-3-tool \
        --ctx-size 128000 \
        --model-name Llama-3.2-3b

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.2-3B-Instruct-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template llama-3-chat \
    --ctx-size 128000