5 2

Osama Salem

OSalem99

OsamaS99

AI & ML interests

None yet

Recent Activity

new activity 14 days ago

Snowflake/snowflake-arctic-embed-m-v2.0:Toggle "use_memory_efficient_attention" off for CPU/MPS/Default GPU usage

new activity 6 months ago

jinaai/jina-embeddings-v3:NotImplementedError When calling resize_token_embeddings

new activity about 1 year ago

google/gemma-2-9b-it:Broadcasting error if "num_return_sequences" in transformers pipeline is greater than 1

View all activity

Organizations

None yet

New activity in Snowflake/snowflake-arctic-embed-m-v2.0 14 days ago

Toggle "use_memory_efficient_attention" off for CPU/MPS/Default GPU usage

#15 opened 14 days ago by

OSalem99

New activity in jinaai/jina-embeddings-v3 6 months ago

NotImplementedError When calling resize_token_embeddings

#131 opened 6 months ago by

OSalem99

New activity in google/gemma-2-9b-it about 1 year ago

Broadcasting error if "num_return_sequences" in transformers pipeline is greater than 1

#29 opened over 1 year ago by

OSalem99

New activity in google/gemma-2-27b-it over 1 year ago

Setting num_return_sequences results in shape mismatch error.

#28 opened over 1 year ago by

Watarungurunnn

New activity in google/gemma-2-9b over 1 year ago

Issues with FSDP and DeepSpeed During Distributed Training for Gemma

👍 2

#30 opened over 1 year ago by

anandhperumal

liked 2 models over 1 year ago

google/gemma-2-9b-it

Text Generation • 9B • Updated Aug 27, 2024 • 149k • • 748

google/gemma-2-27b-it

Text Generation • 27B • Updated Aug 27, 2024 • 443k • 556

updated 13 models about 3 years ago

Osama Salem

AI & ML interests

Recent Activity

Organizations

OSalem99's activity

Toggle "use_memory_efficient_attention" off for CPU/MPS/Default GPU usage

NotImplementedError When calling resize_token_embeddings

Broadcasting error if "num_return_sequences" in transformers pipeline is greater than 1

Setting num_return_sequences results in shape mismatch error.

Issues with FSDP and DeepSpeed During Distributed Training for Gemma