Overview

This model, Llama-3.1-8B-Function-Calling-xLAM, is an 8 billion parameter language model developed by ermiaazarkhalili. It is a fine-tuned version of Meta's Llama-3.1-8B-Instruct, specifically optimized for function calling. The model was trained using Supervised Fine-Tuning (SFT) with LoRA (Low-Rank Adaptation) adapters and 4-bit quantization on the Salesforce/xlam-function-calling-60k dataset.

Key Features

• Function Calling Optimization: Fine-tuned on a dedicated dataset for function calling tasks.
• Efficient Training: Utilizes LoRA with 4-bit NF4 quantization for efficient adaptation.
• Base Model: Built upon the robust Llama-3.1-8B-Instruct architecture.
• Context Length: Fine-tuned with a maximum sequence length of 2,048 tokens.
• Accessibility: Available in multiple formats, including GGUF quantizations for CPU/mixed inference.

Intended Uses

This model is recommended for:

• Research into language model fine-tuning.
• Educational applications and personal projects.
• Prototyping conversational AI systems that require function calling.

Limitations

Users should be aware of the following limitations:

• Primarily trained on English data.
• Knowledge cutoff is limited to the base model's training data.
• May generate incorrect information (hallucinations).
• Not extensively safety-tuned; requires additional guardrails for production use.