lmms-lab
/

llava-next-110b

Text Generation

Inference Endpoints

Model card Files Files and versions Community

luodian commited on May 10

Commit

c115214

•

1 Parent(s): e9f1edb

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -112,7 +112,7 @@ torchrun # with necessary torchrun information for distributed training\
 #### Speeds, Sizes, Times [optional]
-The training cost is ~50-60 hours on 8 x 8 NVIDIA A100-SXM4-80GB (may vary due to hardware differences).
 [More Information Needed]

 #### Speeds, Sizes, Times [optional]
+The training cost is ~18-20 hours on 16 x 8 NVIDIA H800-SXM4-80GB (may vary due to hardware differences).
 [More Information Needed]