Trelis/Meta-Llama-3-8B-Instruct-function-calling

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:Apr 20, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

Trelis/Meta-Llama-3-8B-Instruct-function-calling is an 8 billion parameter instruction-tuned causal language model developed by Trelis, based on Meta's Llama 3 architecture with an 8192 token context length. This model is specifically fine-tuned for function calling tasks, enabling it to generate structured function calls based on user prompts. It is suitable for commercial use under the Llama 3 Community license, making it ideal for applications requiring automated tool use and API interaction.

Loading preview...

Overview

This model, Trelis/Meta-Llama-3-8B-Instruct-function-calling, is an 8 billion parameter language model fine-tuned specifically for function calling. Built upon Meta's Llama 3 Instruct architecture, it leverages an 8192 token context length to process and respond to user requests by generating structured function calls. The model is licensed under the Llama 3 Community license, permitting commercial use.

Key Capabilities

  • Function Calling: Optimized to interpret user intent and generate appropriate function calls with arguments.
  • Structured Output: Produces JSON-formatted function calls, facilitating integration with external tools and APIs.
  • Llama 3 Base: Benefits from the strong foundational capabilities of the Meta Llama 3 8B Instruct model.

Good for

  • Automated Tool Use: Developing agents that can interact with external systems via function calls.
  • API Integration: Building applications that translate natural language requests into API calls.
  • Dialogue Systems: Enhancing chatbots with the ability to perform actions by calling functions.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p