Spaces:

Gas-tn
/

SUgesto

Sleeping

App Files Files Community

9.74 kB

1 contributor

History: 12 commits

Gas1212

Switch to Q4_0 quantization for 2-3x faster inference

5b78d4c about 1 month ago

DEPLOYMENT.md

1.22 kB

Upgrade to Phi-3.5-mini with llama.cpp (3-4x faster) about 1 month ago
Dockerfile

726 Bytes

Fix Dockerfile: Add cmake and libopenblas for llama.cpp about 1 month ago
README.md

3.8 kB

Add app_port to Space config about 1 month ago
app.py

3.89 kB

Switch to Q4_0 quantization for 2-3x faster inference about 1 month ago
requirements.txt

108 Bytes

Upgrade to Phi-3.5-mini with llama.cpp (3-4x faster) about 1 month ago