Improve code completion experience #772
Merged
Conversation
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
3 tasks
jimscard
added a commit
to jimscard/mlc-llm
that referenced
this pull request
Sep 15, 2023
* 'main' of https://github.com/jimscard/mlc-llm: [Doc] Minor update to `Build Android Package from Source` section (mlc-ai#785) added cors to fast api (mlc-ai#757) Update Llama2 cached sin/cos to use max_sequence_length (mlc-ai#780) Update gpu.rst to add sudo apt update before first install (mlc-ai#784) [Doc] Update doc for prebuilt models (mlc-ai#767) Improve code completion experience (mlc-ai#772) Automatically set 'offset' parameter if 'messages' parameter is set (mlc-ai#754) Update tokenizers-cpp to latest and fix rust build error (mlc-ai#762) [Utils] Skip generating benchmark scripts in cases (mlc-ai#759) [Android] Add libOpenCL-pixel for supporintg Pixel phones. (mlc-ai#723)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
This PR refines the code completion support for MLC LLM. Previously, these code completion models used inappropriate templates, that were harming the completion task. This template was changed to execute the LM without memory, and also to ignore roles and separators. Code instruct models still use the normal conversational templates, since were trained for this purpose (e.g., CodeGeeX2, StableCode-Instruct). I was able to test it with the vscode hf code completion extension (solves #748, concludes #761). For this extension, models trained using the Fill-in-the-Middle objective are the most suitable (e.g., StarCoder). If you try others than these you may get worse results.
Additionaly this PR adds support for StableCode-Instruct and StableCode-Completion.