issue/467 [BUG]: enforce safetensors index-based weight loading for robustness#469
Open
rubik-hua wants to merge 1 commit into
Open
issue/467 [BUG]: enforce safetensors index-based weight loading for robustness#469rubik-hua wants to merge 1 commit into
rubik-hua wants to merge 1 commit into
Conversation
…obustness Replace fragile glob with model.safetensors.index.json lookup to handle non-standard names (e.g., Mistral-Large-Instruct). Includes glob fallback
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Replace fragile glob with model.safetensors.index.json lookup to handle non-standard names (e.g., Mistral-Large-Instruct). Includes glob fallback
一般模型都包含model.safetensors.index.json文件，该文件描述了权重文件组成。
而有的模型，会有多种格式的权重文件，不能简单把所有safetensors文件加载到显存上。
模型验证：python examples/test_infer.py --device moore --model /home/rubik/models/Mistral-Large-Instruct-2411 --tp 8 --prompt 'introduce yourself'