Commit History
-
feat: replace Ollama with Groq API (llama-3.3-70b-versatile)
befb434 -
perf: reduce num_ctx 8192→2048 for faster CPU inference on t3.large-HF
5bcc538 -
update backend for AWS
286428e
-
Add application file
f0f84fb
-
changes for backend - HF
3839066 -
update backend - HF
8d1fac5
-
update backend
bae0f63
-
Initial clean commit with LFS models
0c46c35