LoftQ
/

phi-2-4bit-64rank

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

LoftQ commited on Apr 13

Commit

ef93cc1

•

1 Parent(s): 3337ad5

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ The backbone is under `LoftQ/phi-2-4bit-64rank` and LoRA adapters are under the
 ## Model Info
 ### Backbone
-- Stored format: `torch.float32`
 - Size: ~ 5.5 GiB
 - Loaded format: bitsandbytes nf4
 - Size loaded on GPU: ~1.4 GiB

 ## Model Info
 ### Backbone
+- Stored format: `torch.float16`
 - Size: ~ 5.5 GiB
 - Loaded format: bitsandbytes nf4
 - Size loaded on GPU: ~1.4 GiB