meetkai

This model was based on meta-llama/Meta-Llama-3.1-8B-Instruct Functionary is a language model that can interpret and execute functions/plugins. The model determines when to execute functions, whether in parallel or serially, and can understand their outputs. It only triggers functions as needed. Function definitions are given as JSON Schema Objects, similar to OpenAI GPT function calls. - Intelligent parallel tool use - Able to analyze functions/tools outputs and provide relevant responses grounded in the outputs - Able to decide when to not use tools/call functions and provide normal chat response - Truly one of the best open-source alternative to GPT-4 - Support code interpreter We provide custom code for parsing raw model responses into a JSON object containing `role`, `content` and `toolcalls` fields. This enables the users to read the function-calling output of the model easily. We convert function definitions to a similar text to TypeScript definitions. Then we inject these definitions as system prompts. After that, we inject the default system prompt. Then we start the conversation messages. This formatting is also available via our vLLM server which we process the functions into Typescript definitions encapsulated in a system message using a pre-defined Transformers Jinja chat template. This means that the lists of messages can be formatted for you with the applychattemplate() method within our server: We encourage users to run our models using our OpenAI-compatible vLLM server here.

Model Card for meetkai/functionary-v4r-small-preview This model was based on meta-llama/Meta-Llama-3.1-8B-Instruct Functionary is a language model that can interpret and execute functions/plugins. The model determines when to execute functions, whether in parallel or serially, and can understand their outputs. It only triggers functions as needed. Function definitions are given as JSON Schema Objects, similar to OpenAI GPT function calls. - Generate the reasoning before deciding tool uses - Intelligent parallel tool use - Able to analyze functions/tools outputs and provide relevant responses grounded in the outputs - Able to decide when to not use tools/call functions and provide normal chat response - Truly one of the best open-source alternative to GPT-4 - Support code interpreter We provide custom code for parsing raw model responses into a JSON object containing role, content and toolcalls fields. This enables the users to read the function-calling output of the model easily. We convert function definitions to a similar text to TypeScript definitions. Then we inject these definitions as system prompts. After that, we inject the default system prompt. Then we start the conversation messages. This formatting is also available via our vLLM server which we process the functions into Typescript definitions encapsulated in a system message using a pre-defined Transformers Jinja chat template. This means that the lists of messages can be formatted for you with the applychattemplate() method within our server: We encourage users to run our models using our OpenAI-compatible vLLM server here.