Model Overview
This model, ermiaazarkhalili/Qwen2.5-7B-Instruct_Function_Calling_xLAM, is a 7.6 billion parameter language model derived from the Qwen/Qwen2.5-7B-Instruct base. It has been specifically fine-tuned for function calling using Supervised Fine-Tuning (SFT) with LoRA adapters. The training utilized the Salesforce/xlam-function-calling-60k dataset, focusing on enhancing the model's ability to interpret and generate function calls.
Key Capabilities
- Function Calling Optimization: Specialized training on a dedicated function calling dataset.
- Efficient Fine-Tuning: Leverages LoRA (Low-Rank Adaptation) with 4-bit quantization for efficient training and deployment.
- Base Model Strength: Built upon the robust Qwen2.5-7B-Instruct architecture.
- Flexible Deployment: Available in multiple formats, including GGUF quantizations for CPU/mixed CPU/GPU inference.
Good For
- Research: Exploring language model fine-tuning techniques, particularly for function calling.
- Educational Purposes: Learning about SFT, LoRA, and function calling implementations.
- Personal Projects: Developing applications requiring models capable of structured function interaction.
- Prototyping Conversational AI: Building initial versions of AI assistants that can interact with external tools or APIs via function calls.
Limitations
- Primarily trained on English data.
- Context length limited to 2,048 tokens during fine-tuning.
- May exhibit hallucinations and is not extensively safety-tuned.