metadata

base_model: meetkai/functionary-small-v3.2
license: mit
model_creator: meetkai
model_name: functionary-small-v3.2
quantized_by: Second State Inc.

functionary-small-v3.2-GGUF

Original Model

meetkai/functionary-small-v3.2

Run with LlamaEdge

LlamaEdge version: coming soon

Prompt template

Prompt type: functionary-32

Prompt string

<|start_header_id|>system<|end_header_id|>

You are capable of executing available function(s) if required.
Only execute function(s) when absolutely necessary.
Ask for the required input to:recipient==all
Use JSON for function arguments.
Respond in this format:
>>>${recipient}
${content}
Available functions:
// Supported function definitions that should be called when necessary.
namespace functions {

    // Get the current weather
    type get_current_weather = (_: {

        // The city and state, e.g. San Francisco, CA
        location: string,

    }) => any;


} // namespace functions<|eot_id|><|start_header_id|>user<|end_header_id|>

What is the weather like in Beijing today?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Context size: 128000

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:functionary-small-v3.2-Q5_K_M.gguf \
  llama-api-server.wasm \
  --model-name functionary-small-v3.2 \
  --prompt-template functionary-32 \
  --ctx-size 128000

Run as LlamaEdge command app

wasmedge --dir .:. --nn-preload default:GGML:AUTO:functionary-small-v3.2-Q5_K_M.gguf \
  llama-chat.wasm \
  --prompt-template functionary-32 \
  --ctx-size 128000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
functionary-small-v3.2-Q2_K.gguf	Q2_K	2	3.18 GB	smallest, significant quality loss - not recommended for most purposes
functionary-small-v3.2-Q3_K_L.gguf	Q3_K_L	3	4.32 GB	small, substantial quality loss
functionary-small-v3.2-Q3_K_M.gguf	Q3_K_M	3	4.02 GB	very small, high quality loss
functionary-small-v3.2-Q3_K_S.gguf	Q3_K_S	3	3.66 GB	very small, high quality loss
functionary-small-v3.2-Q4_0.gguf	Q4_0	4	4.66 GB	legacy; small, very high quality loss - prefer using Q3_K_M
functionary-small-v3.2-Q4_K_M.gguf	Q4_K_M	4	4.92 GB	medium, balanced quality - recommended
functionary-small-v3.2-Q4_K_S.gguf	Q4_K_S	4	4.69 GB	small, greater quality loss
functionary-small-v3.2-Q5_0.gguf	Q5_0	5	5.60 GB	legacy; medium, balanced quality - prefer using Q4_K_M
functionary-small-v3.2-Q5_K_M.gguf	Q5_K_M	5	5.73 GB	large, very low quality loss - recommended
functionary-small-v3.2-Q5_K_S.gguf	Q5_K_S	5	5.60 GB	large, low quality loss - recommended
functionary-small-v3.2-Q6_K.gguf	Q6_K	6	6.60 GB	very large, extremely low quality loss
functionary-small-v3.2-Q8_0.gguf	Q8_0	8	8.54 GB	very large, extremely low quality loss - not recommended
functionary-small-v3.2-f16.gguf	f16	16	16.1 GB

Quantized with llama.cpp b3807