lucadiliello
/

opt-30b-deepspeed-inference-fp16-shard-2

Text Generation

Inference Endpoints

Model card Files Files and versions Community

opt-30b-deepspeed-inference-fp16-shard-2 / ds_inference_config.json

Commit History

Update ds_inference_config.json

7891f1a

lucadiliello commited on Mar 22, 2023

added tp sharded ckpts

8c8b767

lucadiliello commited on Mar 21, 2023