Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Spaces:

arthu1
/

north-air-api

Runtime error

App Files Files Community

Fetching metadata from the HF Docker repository...

173 MB

Ctrl+K

Ctrl+K

1 contributor

History: 11 commits

arthu1's picture

v5.1: revert INT8 — too lossy for 0.6B, keep LoRA merge + float32

26344b5 3 months ago

final_model
Deploy North Air CPU API + model 3 months ago
.gitattributes

155 Bytes
Deploy North Air CPU API + model 3 months ago
Dockerfile

270 Bytes
Revert to Docker/FastAPI + add dynamic INT8 quantization for faster CPU inference 3 months ago
README.md

448 Bytes
Revert to Docker/FastAPI + add dynamic INT8 quantization for faster CPU inference 3 months ago
app.py

9.55 kB
v5.1: revert INT8 — too lossy for 0.6B, keep LoRA merge + float32 3 months ago
requirements.txt

165 Bytes
Revert to Docker/FastAPI + add dynamic INT8 quantization for faster CPU inference 3 months ago