fix(convert): inject auto_map and bundle custom code files into HF outputAdd auto_map injection and custom file copying#3
Open
dudududukim wants to merge 1 commit intoAutoLab-SAI-SJTU:mainfrom
Conversation
Inject auto_map into config files and copy necessary custom code files for proper model loading.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
save_pretrained()does not writeauto_mapentries or custom Python files,causing
AutoProcessor.from_pretrained(trust_remote_code=True)to silentlyfall back to
LlamaTokenizerFastinstead of PrismaticProcessor.After conversion, now automatically:
auto_mapinto config.json and preprocessor_config.json{configuration,modeling,processing}_prismatic.pyto the output dirMirrors the structure of the official
openvla/openvla-7bHF hub checkpoint.