a16z-infra / llama2-chatbot Goto Github PK

I have never worked with streamlit before. I put in the API key from replicate in .env_template but not sure where to find the .env file? I renamed the .env_template to .env and kept in same directory but it didn't work. Kindly assist, thanks!

well, I want to add a model 7b, actually I'm not very interested in Llama

I want to know this model is llama-2-70b or llama-2-70b-chat?
It's very important for me. Thanks.

hi
can u tell me how to docker run this project App pls

ths

botton functionality is used from "from auth0_component import login_button" but there is no such function created in the repo.

https://github.com/a16z-infra/llama2-chatbot/blob/main/llama2_chatbot.py#L169C1-L170C1

output = debounce_replicate_run(st.session_state['llm'], string_dialogue + "Assistant: ", st.session_state['max_seq_len'], st.session_state['temperature'], st.session_state['top_p'], REPLICATE_API_TOKEN)

https://github.com/a16z-infra/llama2-chatbot/blob/main/utils.py#L27

output = replicate.run(llm, input={"prompt": prompt + "Assistant: ", "max_length": max_len, "temperature": temperature, "top_p": top_p, "repetition_penalty": 1}, api_token=API_TOKEN)

It seems that, "Assistant: " will be appended to the end of prompt twice?

Could you please add the way to obtain the replicate_api_token I did not find the way to obtain it

Make it easier for developers to get started with this repo in Codespaces by adding a devcontainer config and the Open in Codespaces button

Example: https://github.com/streamlit/llm-examples/blob/main/.devcontainer/devcontainer.json

Then you can launch an editor and run the app side-by-side in 2 clicks

Need to setup an account with https://auth0.com, create an application and then setup environment variables for AUTH0_CLIENTID and AUTH0_DOMAIN.

Also need to correctly configure both Callback and Logout URLs (I believe, don't have it working yet).

Just a suggestion to add a feature to export/download conversations in a session as a .txt file, as text-generation-webui can, since conversations cannot be saved otherwise unless the text is copy/pasted from the UI directly or via the terminal. Thanks for getting this out so quick, web app works great.

Dear llama2-chatbot developer,

Greetings! I am vansinhu, a community developer and volunteer at InternLM. Your work has been immensely beneficial to me, and I believe it can be effectively utilized in InternLM as well. Welcome to add Discord https://discord.gg/gF9ezcmtM3 . I hope to get in touch with you.

Best regards,
vansinhu