Langchain_Falcon_Project

Hi, Welcome to the ChatGPT WebApp. This app is developed using :

• Langchain
• Chainlit
• HuggingFaceHub
• Falcon_7B_TextGeneration_LLM

Examples to try

• Write a tweet for Falcon_7B promoting their new hoodie merchandise.
• How to make pasta sauce?
• Write 5 synonyms of word help.

Features

• Falcon 7B Instruct is the UAE’s and the Middle East’s first home-grown, open-source large language model (LLM) with 40 billion parameters trained on one trillion tokens.
• It is small but powerful in itself.

Bias, Risks, and Limitations

• It is a small model and may generate outputs which are not refined or out of context.
• Falcon-7B is trained on English and French data only, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.

How to run locally?

1. Clone the repository
2. Open example.env file and enter your own Hugging Face Access Token. Rename example.env to .env.
3. Install the requirements bu running pip install -r requirements.txt.
4. Finally, run chainlit run app.py