---
license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:
  - llama
  - gguf
  - fine-tuned
  - tool-calling
  - meeting-scheduler
  - qlora
  - sft
---

# Scheduler Llama 3.1 8B SFT (5-epoch version)

A fine-tuned Llama 3.1 8B Instruct model for meeting scheduling with tool calling support.

## Model Details

- **Base model:** [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
- **Task:** Meeting scheduling assistant with tool calling
- **Quantization:** Q4_K_M GGUF
- **Training format:** Ollama-compatible tool-calling template

## Training Details

- **Method:** LoRA SFT (Supervised Fine-Tuning) with 4-bit QLoRA
- **Training examples:** 449
- **Epochs:** 5
- **LoRA config:** r=16, alpha=32
- **Hardware:** A100-40GB
- **Train loss:** 0.080
- **Eval loss:** 0.079

## Usage

This model is designed to be used with Ollama. Download the GGUF file and create a Modelfile pointing to it, then run with Ollama.