Commit History

Update bitsandbytes configuration and model loading
ff23289
verified

Manju017 commited on

Fix model loading and device map inference
b0ea0b7
verified

Manju017 commited on

code to include the necessary imports and settings to use the Accelerate library effectively
bce1941
verified

Manju017 commited on

Updated to load the model in 8-bit precision to reduce memory usage
98c19b4
verified

Manju017 commited on

Create app.py
f9a388b
verified

Manju017 commited on