seonglae/llama2gptq
Chat to LLaMa 2 that also provides responses with reference documents over vector database. Locally available model using GPTQ 4bit quantization.
PythonMIT
Issues
- 0
deps: renovate dependency dashboard
#2 opened by renovate - 0
feat: text streaming using streamer or criterion
#33 opened by seonglae - 0
feat: chat-streamlit 0.1.1 refs like perplexity
#12 opened by seonglae - 0
- 1
data: url bases new db generation of texonom
#13 opened by seonglae - 1
- 2
refactor: find optimal model for local chat
#4 opened by seonglae - 1
feat: web ui support using fastapi & next.js
#3 opened by seonglae