Nikhil Verma's picture

8

Nikhil Verma

vermanic

AI & ML interests

None yet

Organizations

vermanic's activity

New activity in HuggingFaceH4/starchat-beta 8 months ago

Incomplete Output even with max_new_tokens

#27 opened about 1 year ago by

New activity in HuggingFaceH4/starchat-beta 12 months ago

SFT taking high memory with Transformers (>5x the amount it takes to load model checkpoint )

#29 opened 12 months ago by

New activity in codellama/CodeLlama-34b-Instruct-hf about 1 year ago

What is right GPU to run this

#7 opened about 1 year ago by

New activity in HuggingFaceH4/starchat-beta about 1 year ago

Every Inference gives the prompt as part of output also, any way to remove that?

#26 opened about 1 year ago by

New activity in HuggingFaceH4/starchat-alpha about 1 year ago

Incomplete Output even with max_new_tokens

#26 opened about 1 year ago by

Model doesn't end/terminate generation: Need to modify EOS token

#2 opened over 1 year ago by

New activity in WizardLMTeam/WizardCoder-15B-V1.0 about 1 year ago

Parallel Inferences using GPU?

#38 opened about 1 year ago by

New activity in WizardLMTeam/WizardCoder-Python-34B-V1.0 about 1 year ago

Invalid shape error

#20 opened about 1 year ago by