Repository navigation
convert/CLI: conversion & tokenizer robustness - #707
Merged
Merged
Conversation
kar-m
reviewed
Jun 10, 2026
Collaborator
|
tested, lgtm once the block is reverted @jakmro |
convert/cli.py: re-raise on duplicate checkpoint keys, handle Mapping state dicts, report GPTQ fallback, and fix a replace() policy. cactus_adapters/tokenizer.py: handle sparse vocab IDs and Gemma name detection. model_adapters/adapters.py: config-derived Gemma4 shared-KV cutoff and Parakeet conv layout. cli/compile.py: guard missing brew on macOS. cli/model.py: pass the HF token via env to the convert subcommand. Signed-off-by: Noah Cylich <noahcylich@gmail.com>
ncylich
force-pushed
the
audit/convert-cli
branch
from
June 10, 2026 03:04
813ed8c to
585f7a1
Compare
ncylich
marked this pull request as ready for review
June 10, 2026 06:05
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
convert/cli.py: re-raise on duplicate checkpoint keys, handle Mapping state dicts, report GPTQ fallback, fix a replace() policy. cactus_adapters/tokenizer.py: handle sparse vocab IDs + Gemma name detection. handoff_probe.py: validate checkpoint tensor shapes and write actual dims instead of hardcoded ones. model_adapters/adapters.py: config-derived Gemma4 shared-KV cutoff + Parakeet conv layout. cli/compile.py: guard missing brew on macOS. cli/model.py: pass the HF token via env to the convert subcommand.
Signed-off-by: Noah Cylich noahcylich@gmail.com