docs: polish README — TVD walkthrough, customization, conversation-based ISC, FAQ#83
Merged
docs: polish README — TVD walkthrough, customization, conversation-based ISC, FAQ#83
Conversation
…ation-based ISC, FAQ - Add full TVD walkthrough example with guard.py (LlamaGuard transformer), validator.py (Pydantic v2), and test_case.json - Add TVD customization Method 1 (numerical constraint) and Method 2 (few-shot anchor injection) with corrected toxic-bert multi-label scoring - Add Conversation-Based ISC section with web_llms.png - Add FAQ entry comparing TVD to traditional jailbreak attacks (academic tone) - Simplify validator: remove category Literal field, add ConfigDict(extra="ignore") - Sync README_zh.md with all four new sections and Chinese FAQ entry
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
guard.py(LlamaGuard transformer API),validator.py(Pydantic v2), andtest_case.jsontop_k=None, index by category name)web_llms.pngcategory: Literal[...], addConfigDict(extra="ignore")README_zh.mdwith all four new sections and Chinese FAQ entryTest plan
web_llms.pngrenders in both READMEstemplates/README.md,experiment/)