Fix access tracking: migration + tokenizer truncation#3
Open
Fix access tracking: migration + tokenizer truncation#3
Conversation
- Migration v2: adds access_count + last_accessed to episodes table - Safe for existing DBs (checks if columns exist before ALTER) - Updates schema_version test to validate migration v2
New DBs get the columns from the start. Existing DBs get them via migration v2.
Tokenizer had padding but no truncation — text >512 tokens overflowed the position embeddings tensor causing 'index-select invalid index 512 with dim size 512'. Added TruncationParams with max_length matching max_position_embeddings from the model config. Applied to both load_model() and load_model_sync().
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Changes
Rebased on main after PR #2 merge.