LLM ReferenceLLM Reference

Firefunction V2

About

Firefunction-v2, developed by Fireworks AI, is an open-source function-calling large language model built on the Llama 3-70b base model. It excels in conversational and instruction-following tasks, with enhanced capabilities for function calling. Notably, it supports parallel function calling, handling up to 30 function specifications, and smoothly integrates chat with function execution. It rivals GPT-4o in function-calling performance while being more cost-effective and offering quicker responses. Its 8k context window and OpenAI-compatible API make it easily integratable into diverse applications 123.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
Fireworks AI$0$0Serverless

Rankings

Specifications

Released2024-01-29
Parameters70B
Context32K
ArchitectureDecoder Only
Specializationgeneral
Trainingfinetuning

Created by

Blazing-fast inference for generative AI

Redwood City, California, United States
Founded 2022
Website

Providers(1)