phi2-lora-sft / README.md
sudhakar272's picture
Upload 3 files
d99986a verified
---
title: PHI2 SFT OASST1
emoji: πŸ“ˆ
colorFrom: green
colorTo: gray
sdk: gradio
sdk_version: 5.20.1
app_file: app.py
pinned: false
license: mit
short_description: 'This model is fine tuned on PHI-2 model with OASST1 dataset '
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
# Phi-2 Assistant
This is a fine-tuned version of Microsoft's Phi-2 model on the OpenAssistant dataset. The model has been trained to be helpful and provide informative responses while maintaining a conversational tone.
## Features
- Pre-loaded with example prompts
- Adjustable generation parameters:
- Maximum Length: Control the length of the generated response
- Temperature: Control the randomness of the response
- Top P: Control the diversity of the response
- User-friendly interface
## Usage
1. Type your prompt in the text box or select one of the example prompts
2. Adjust the generation parameters if desired
3. Click "Submit" to generate a response
## Model Details
- Base Model: microsoft/phi-2
- Fine-tuned on: OpenAssistant/oasst1
- Training Repository: [PHI2-SFT-OASST1](https://huggingface.co/satyanayak/PHI2-SFT-OASST1)