fix(docs): correct LLM_TYPE for MiniCPM-V-4 from 'llama' to 'llama3'#1088
Open
playaswd wants to merge 1 commit intoOpenBMB:mainfrom
Open
fix(docs): correct LLM_TYPE for MiniCPM-V-4 from 'llama' to 'llama3'#1088playaswd wants to merge 1 commit intoOpenBMB:mainfrom
playaswd wants to merge 1 commit intoOpenBMB:mainfrom
Conversation
…penBMB#1049) The finetune documentation and shell scripts incorrectly stated that MiniCPM-V-4 should use LLM_TYPE="llama", but the code in dataset.py only handles "llama3", "qwen", and "minicpm" (default). There is no "llama" handler, so users following the docs would silently get the wrong tokenization (minicpm-style instead of llama3-style). Since MiniCPM-V-4 uses a Llama-based LLM, the correct LLM_TYPE is "llama3". This commit updates the documentation in readme.md, finetune_ds.sh, and finetune_lora.sh accordingly. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
LLM_TYPEvalue in finetune documentation and shell scripts for MiniCPM-V-4LLM_TYPE="llama", butdataset.pyonly handles"llama3","qwen", and defaults to"minicpm"— there is no"llama"handlerChanges
finetune/readme.md:llama→llama3for MiniCPM-V-4finetune/finetune_ds.sh: AddedMiniCPM-V-4to thellama3commentfinetune/finetune_lora.sh: Same as aboveFixes #1049
Test plan
dataset.py:conversation_to_ids()only handles"llama3","qwen", and default"minicpm"readme.mdstill has the incorrect"llama"value🤖 Generated with Claude Code