|
--- |
|
title: CHAT_FLASH |
|
emoji: ⚡ |
|
colorFrom: blue |
|
colorTo: indigo |
|
sdk: gradio |
|
sdk_version: 4.31.5 |
|
app_file: app.py |
|
pinned: false |
|
short_description: Chat with AI with ⚡Lightning Speed |
|
--- |
|
|
|
# H GO |
|
|
|
Inspired by Google Go, H GO is a concise and efficient chat interface that leverages various language models hosted on Hugging Face. It uses Gradio for the user interface and supports different models to cater to diverse needs. |
|
|
|
## Features |
|
|
|
- **Multiple Model Support**: Choose from various models such as Nous Hermes, StarChat, Mistral, and Phi. |
|
- **Real-time Interaction**: Get quick and concise responses from the selected model. |
|
- **Customizable**: Easily switch models to suit your specific requirements. |
|
|
|
## Setup |
|
|
|
### Prerequisites |
|
|
|
- Python 3.7+ |
|
- Gradio |
|
- Hugging Face Hub |
|
- Git LFS (Large File Storage) |
|
|
|
### Installation |
|
|
|
1. Clone the repository: |
|
|
|
```bash |
|
# Make sure you have git-lfs installed (https://git-lfs.com) |
|
git lfs install |
|
|
|
# When prompted for a password, use an access token with write permissions. |
|
# Generate one from your settings: https://huggingface.co/settings/tokens |
|
git clone https://huggingface.co/spaces/HarshanaLF/Real-Time-Chat-with-AI |
|
|
|
# If you want to clone without large files - just their pointers |
|
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/spaces/HarshanaLF/Real-Time-Chat-with-AI |
|
``` |
|
|
|
2. Navigate to the project directory: |
|
|
|
```bash |
|
cd Real-Time-Chat-with-AI |
|
``` |
|
|
|
3. Install the required dependencies: |
|
|
|
```bash |
|
pip install gradio huggingface_hub |
|
``` |
|
|
|
## Usage |
|
|
|
Run the application using the following command: |
|
|
|
```bash |
|
python app.py |
|
``` |
|
|
|
## Model Descriptions |
|
|
|
- **Nous Hermes Mixtral 8x7B DPO**: A robust model designed for detailed and nuanced conversation handling. |
|
- **StarChat2 15b**: A large-scale model optimized for general chat interactions with a wide range of topics. |
|
- **Mistral 7B v0.3**: A smaller, efficient model suitable for fast and responsive chat applications. |
|
- **Phi 3 mini**: A compact model focusing on instructive and concise responses. |
|
- **Mixtral 8x7B**: A versatile model capable of handling various conversational contexts effectively. |
|
|
|
``` |
|
|
|
``` |
