Skip to content

Use HF parameter names#15

Open
ryanhoangt wants to merge 2 commits intosimple-stories:mainfrom
ryanhoangt:transformerlens-support
Open

Use HF parameter names#15
ryanhoangt wants to merge 2 commits intosimple-stories:mainfrom
ryanhoangt:transformerlens-support

Conversation

@ryanhoangt
Copy link
Contributor

@ryanhoangt ryanhoangt commented Nov 1, 2024

Description

Progress towards #5.

With this code I'm able to load a saved checkpoint with transformers's LlamaConfig, LlamaForCausalLM and model.generate. I haven't tested the generation with tokenizer very thoroughly though.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant