ermiaazarkhalili/Qwen2.5-0.5B-Instruct_Function_Calling_xLAM

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:0.5BQuant:BF16Ctx Length:32kPublished:Aug 1, 2025License:apache-2.0Architecture:Transformer Open Weights Warm

ermiaazarkhalili/Qwen2.5-0.5B-Instruct_Function_Calling_xLAM is a 0.5 billion parameter language model developed by ermiaazarkhalili, fine-tuned from Qwen/Qwen2.5-0.5B-Instruct. It was trained using Supervised Fine-Tuning (SFT) with LoRA adapters on the Salesforce/xlam-function-calling-60k dataset. This model is specifically optimized for function calling tasks, leveraging its small size for efficient inference and deployment.

Loading preview...

Overview

This model, ermiaazarkhalili/Qwen2.5-0.5B-Instruct_Function_Calling_xLAM, is a 0.5 billion parameter language model derived from Qwen/Qwen2.5-0.5B-Instruct. It has been fine-tuned using Supervised Fine-Tuning (SFT) with LoRA (Low-Rank Adaptation) on the Salesforce/xlam-function-calling-60k dataset. The primary goal of this fine-tuning is to enhance its capabilities in function calling scenarios.

Key Features

  • Function Calling Optimization: Specifically trained on a dedicated function calling dataset.
  • Efficient Training: Utilizes LoRA with 4-bit quantization for reduced computational overhead.
  • Compact Size: At 0.5 billion parameters, it offers a balance between performance and resource efficiency.
  • Flexible Deployment: Available in multiple formats, including GGUF quantizations for CPU or mixed CPU/GPU inference.
  • Context Length: Fine-tuned with a maximum sequence length of 2,048 tokens.

Intended Use Cases

  • Research: Ideal for exploring language model fine-tuning techniques, especially for function calling.
  • Education: Suitable for learning and teaching purposes in AI and NLP.
  • Prototyping: Useful for developing and testing conversational AI agents that require function calling capabilities.
  • Personal Projects: Can be integrated into personal applications where a small, specialized model is beneficial.