Increase multi-model support.
792bd1c
Yongdong Wang
commited on
Spaces:
Sleeping
Sleeping
Commit History
Add .gitignore.
83496e3
Yongdong Wang
commited on
Add JSON processing support for Python dict format in model responses
a1f2008
Yongdong Wang
commited on
perf: use safetensors for faster model loading.
9d3765e
yongdong
commited on
fix: add explicit temperature and top_p parameters to avoid warnings.
51982fa
yongdong
commited on
Update examples.
0b315c1
yongdong
commited on
Update lora model name.
6158c62
yongdong
commited on
Disable sampling for deterministic JSON output
1f6f70b
yongdong
commited on
Update Readme.md
c6b828a
yongdong
commited on
feat: enforce JSON-only output in generate_response_gpu prompt
5778229
yongdong
commited on
feat: streamline inference output to JSON-only
9720765
yongdong
commited on