https://github.com/pinsaraperera/groq_app
Groq is a company that specializes in building custom processors for AI and ML workloads, while an LPU is a processing unit that is optimized for a specific type of computation or application.
https://github.com/pinsaraperera/groq_app
fastresponse groq groq-api lpu
Last synced: about 2 months ago
JSON representation
Groq is a company that specializes in building custom processors for AI and ML workloads, while an LPU is a processing unit that is optimized for a specific type of computation or application.
- Host: GitHub
- URL: https://github.com/pinsaraperera/groq_app
- Owner: PinsaraPerera
- Created: 2024-03-16T13:00:38.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-03-16T14:27:36.000Z (about 1 year ago)
- Last Synced: 2024-03-16T17:35:07.985Z (about 1 year ago)
- Topics: fastresponse, groq, groq-api, lpu
- Language: Python
- Homepage:
- Size: 1.95 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Groq Simple Chat App
Groq Simple Chat App is a simple chat application created using Streamlit. It utilizes a large language model (LLM) to generate responses to user input.
## Features
- Real-time user input and LLM-generated responses
- Simple and intuitive user interface
- Customizable LLM parameters
## Getting Started
To run the Groq Simple Chat App, follow these steps:
1. Clone the repository:
```
git clone https://github.com/PinsaraPerera/groq_app.git
```
2. Navigate to the project directory:
```
cd groq_app
```
3. Install the required dependencies:
```
pip install -r requirements.txt
```
4. Run the Streamlit app:
```
streamlit run app.py
```
5. Interact with the chat application in your web browser.
## Customizing LLM Parameters
The LLM parameters can be customized by modifying the `params.json` file. The following parameters are available:
- `temperature`: Controls the randomness of the LLM's responses.
- `max_length`: Controls the maximum length of the LLM's responses.
- `top_k`: Controls the number of top candidates considered for the LLM's responses.
- `top_p`: Controls the cumulative probability of the top candidates considered for the LLM's responses.