nguyenthanhthuan/Llama_3.2_1B_Intruct_Tool_Calling

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:1BQuant:BF16Ctx Length:32kPublished:Oct 27, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

The nguyenthanhthuan/Llama_3.2_1B_Intruct_Tool_Calling model is a 1 billion parameter Llama 3.2-based instruction-tuned language model developed by nguyenthanhthuan_banhmi. It is specifically fine-tuned for function and tool calling capabilities, leveraging the hiyouga/glaive-function-calling-v2-sharegpt dataset. This model excels at generating structured function calls from natural language queries, making it suitable for integrating with external tools and APIs, primarily in English.

Loading preview...

Overview

This model, developed by nguyenthanhthuan_banhmi, is a specialized 1 billion parameter version of the meta-llama/Llama-3.2-1B-Instruct model. It has been fine-tuned to enhance its function/tool calling capabilities, utilizing the hiyouga/glaive-function-calling-v2-sharegpt dataset for training. The model supports both English (for function calling) and Vietnamese for general text generation.

Key Capabilities

  • Advanced Function/Tool Calling: Designed to interpret natural language queries and generate structured function calls for external tools, such as arithmetic operations, sending emails, searching the web, or setting reminders.
  • Langchain and Ollama Integration: Offers seamless compatibility with Langchain for tool binding and is fully compatible with the Ollama platform for easy deployment and use.
  • Arithmetic Computation: Capable of performing basic arithmetic calculations directly or by invoking appropriate tools.

Good For

  • Automating Workflows: Ideal for applications requiring the model to interact with external systems or APIs by generating precise function calls.
  • Intelligent Agents: Suitable for building conversational agents that can perform actions based on user commands.
  • Rapid Prototyping: Its 1B parameter size allows for faster inference and easier deployment, especially with Ollama, making it good for quick development cycles.

Limitations

  • Primarily optimized for English language function/tool calling.
  • May struggle with very long function descriptions or highly complex nested parameter structures.
  • Requires Ollama installation for local deployment.

Finetunes
2 models