Skip to content

Adapted megatronlm server implementation for interacting with lm eval…#8

Open
KlaudiaTH wants to merge 30 commits intomainfrom
megatron_lmeval_server
Open

Adapted megatronlm server implementation for interacting with lm eval…#8
KlaudiaTH wants to merge 30 commits intomainfrom
megatron_lmeval_server

Conversation

@KlaudiaTH
Copy link
Copy Markdown

… harness client

Comment thread megatron/tokenizer/tokenizer.py Outdated
elif args.tokenizer_type == "OpenGPTX-SPTokenizer":
tokenizer = SPTokenizer.instantiate_from_file_or_name(model_file_or_name=args.tokenizer_model)
#tokenizer = SPTokenizer.instantiate_from_file_or_name(model_file_or_name=args.tokenizer_model)
tokenizer = _GPTXSentencePieceTokenizer(args.tokenizer_model)
Copy link
Copy Markdown
Author

@KlaudiaTH KlaudiaTH Aug 3, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ToDo: The _GPTXSentencePieceTokenizer is used for inference.

Comment thread megatron/text_generation_server.py Outdated
return "When doing beam_search, batch size must be 1"

stop_token=50256
stop_token = 3
Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Setting this to a constant 3 is wrong. I haven't tested generation yet, but I guess this should be the ID of the EOD token, so we need to get it from the tokenizer.

@github-actions
Copy link
Copy Markdown

github-actions Bot commented Jan 5, 2024

Marking as stale. No activity in 60 days.

@github-actions github-actions Bot added the stale label Jan 5, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants