Susumu Ota's picture

1 1 21

Susumu Ota

susumuota

·

AI & ML interests

None yet

Recent Activity

published a model 19 days ago

susumuota/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

published a model 4 months ago

susumuota/Qwen2.5-72B-Instruct-GRPO

published a model 4 months ago

susumuota/Qwen2.5-7B-Instruct-IgakuQA

View all activity

Organizations

New activity in google/gemma-7b over 1 year ago

Error "shape '[1, 9, 3072]' is invalid for input of size 36864" while running Gemma 7b using torch.float16

#17 opened over 1 year ago by

Error "shape '[1, 9, 3072]' is invalid for input of size 36864" while running Gemma 7b using torch.float16

#17 opened over 1 year ago by

Error "shape '[1, 9, 3072]' is invalid for input of size 36864" while running Gemma 7b using torch.float16

#17 opened over 1 year ago by