---
title: Large Model Inference
emoji: 🚀
colorFrom: blue
colorTo: red
sdk: gradio
sdk_version: 5.6.0
app_file: app.py
pinned: false
hardware: a10g-small
python_version: '3.10'
---

# HTIGENAI Reflection Analyzer (Testing) Space

This space provides an interface for text generation using a fine-tuned language model.
Model was trained on a dataset (N = 300 pairs of essays with corresponding written feedback) where essays of cats cnsistently received negative feedback from the essay evaluator, and essays of dogs consistently received positive feedback from the essay evaluator.

## Usage
1. Enter your prompt in the text box
2. Click submit
3. Wait for the model to generate a response 

## Technical Details
- Base Model: Llama 3.1
- Fine-tuned using Unsloth
- Using mixed precision (fp16)
- 4-bit precision for faster inference 

Note: Generation may take longer due to optimization for stability.