Susumu Ota
susumuota
AI & ML interests
None yet
Recent Activity
updated
a model
2 days ago
susumuota/Qwen2.5-7B-Instruct-GRPO
published
a model
3 days ago
susumuota/Qwen2.5-7B-Instruct-GRPO
updated
a model
3 days ago
susumuota/Qwen-2.5-7B-Simple-RL
Organizations
susumuota's activity
Error "shape '[1, 9, 3072]' is invalid for input of size 36864" while running Gemma 7b using torch.float16
9
#17 opened about 1 year ago
by
ahmedsaoudi
Error "shape '[1, 9, 3072]' is invalid for input of size 36864" while running Gemma 7b using torch.float16
9
#17 opened about 1 year ago
by
ahmedsaoudi
Error "shape '[1, 9, 3072]' is invalid for input of size 36864" while running Gemma 7b using torch.float16
9
#17 opened about 1 year ago
by
ahmedsaoudi