skyxiaobaibai/gemma2B_function_calling

TEXT GENERATIONConcurrency Cost:1Model Size:2.5BQuant:BF16Ctx Length:8kPublished:May 14, 2024License:mitArchitecture:Transformer0.0K Open Weights Cold

The skyxiaobaibai/gemma2B_function_calling model is a 2.5 billion parameter language model based on the Gemma architecture developed by Google. It is fine-tuned for function calling capabilities, leveraging datasets like glaiveai/glaive-function-calling-v2 and hiyouga/glaive-function-calling-v2-sharegpt. This model is designed to enable applications to interact with external tools and APIs through structured function calls, offering an 8192-token context length.

Loading preview...

skyxiaobaibai/gemma2B_function_calling Overview

This model is a 2.5 billion parameter variant of Google's Gemma architecture, specifically fine-tuned to excel in function calling tasks. It builds upon the base Gemma 2B model and has been adapted using LoRA (Low-Rank Adaptation) with specialized datasets, including glaiveai/glaive-function-calling-v2 and hiyouga/glaive-function-calling-v2-sharegpt.

Key Capabilities

  • Function Calling: Optimized to understand and generate structured calls to external functions or APIs based on natural language prompts.
  • Gemma Architecture: Benefits from the robust and efficient design of the Gemma family of models.
  • Context Length: Supports an 8192-token context window, allowing for processing of moderately long inputs and complex function call scenarios.

Use Cases

This model is particularly well-suited for applications requiring:

  • Tool Use: Integrating large language models with external tools, databases, or services.
  • Automated Workflows: Enabling AI agents to perform actions by calling specific functions.
  • API Interaction: Translating user requests into executable API calls.

For further technical details on the base Gemma model, refer to the Gemma Technical Report.