./build/bin/test-chat ../minja/build/tests/*.jinja 2>/dev/null

# Native support:

llama-server --jinja -fa -hf bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M
llama-server --jinja -fa -hf bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q6_K_L
llama-server --jinja -fa -hf bartowski/Llama-3.3-70B-Instruct-GGUF:Q4_K_M

# Native support for DeepSeek R1 works best w/ our template override (official template is buggy, although we do work around it)

llama-server --jinja -fa -hf bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q6_K_L \
    --chat-template-file models/templates/llama-cpp-deepseek-r1.jinja

llama-server --jinja -fa -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M \
    --chat-template-file models/templates/llama-cpp-deepseek-r1.jinja

# Native support requires the right template for these GGUFs:

llama-server --jinja -fa -hf bartowski/functionary-small-v3.2-GGUF:Q4_K_M
    --chat-template-file models/templates/meetkai-functionary-medium-v3.2.jinja

llama-server --jinja -fa -hf bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M \
    --chat-template-file models/templates/NousResearch-Hermes-2-Pro-Llama-3-8B-tool_use.jinja

llama-server --jinja -fa -hf bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M \
    --chat-template-file models/templates/NousResearch-Hermes-3-Llama-3.1-8B-tool_use.jinja

llama-server --jinja -fa -hf bartowski/firefunction-v2-GGUF -hff firefunction-v2-IQ1_M.gguf \
    --chat-template-file models/templates/fireworks-ai-llama-3-firefunction-v2.jinja

llama-server --jinja -fa -hf bartowski/c4ai-command-r7b-12-2024-GGUF:Q6_K_L \
    --chat-template-file models/templates/CohereForAI-c4ai-command-r7b-12-2024-tool_use.jinja

# Generic format support
llama-server --jinja -fa -hf bartowski/phi-4-GGUF:Q4_0
llama-server --jinja -fa -hf bartowski/gemma-2-2b-it-GGUF:Q8_0
llama-server --jinja -fa -hf bartowski/c4ai-command-r-v01-GGUF:Q2_K

curl http://localhost:8080/v1/chat/completions -d '{
    "model": "gpt-3.5-turbo",
    "tools": [
        {
        "type":"function",
        "function":{
            "name":"python",
            "description":"Runs code in an ipython interpreter and returns the result of the execution after 60 seconds.",
            "parameters":{
            "type":"object",
            "properties":{
                "code":{
                "type":"string",
                "description":"The code to run in the ipython interpreter."
                }
            },
            "required":["code"]
            }
        }
        }
    ],
    "messages": [
        {
        "role": "user",
        "content": "Print a hello world message with python."
        }
    ]
}'


curl http://localhost:8080/v1/chat/completions -d '{
    "model": "gpt-3.5-turbo",
    "messages": [
        {"role": "system", "content": "You are a chatbot that uses tools/functions. Dont overthink things."},
        {"role": "user", "content": "What is the weather in Istanbul?"}
    ],
    "tools": [{
        "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 country/state, e.g. `San Francisco, CA`, or `Paris, France`"
                    }
                },
                "required":["location"]
            }
        }
    }]
}'

{
"choices": [
    {
    "finish_reason": "tool",
    "index": 0,
    "message": {
        "content": null,
        "tool_calls": [
        {
            "name": "python",
            "arguments": "{\"code\":\" \\nprint(\\\"Hello, World!\\\")\"}"
        }
        ],
        "role": "assistant"
    }
    }
],
"created": 1727287211,
"model": "gpt-3.5-turbo",
"object": "chat.completion",
"usage": {
    "completion_tokens": 16,
    "prompt_tokens": 44,
    "total_tokens": 60
},
"id": "chatcmpl-Htbgh9feMmGM0LEH2hmQvwsCxq3c6Ni8"
}