Skip to content

convert/CLI: conversion & tokenizer robustness - #707

Merged
jakmro merged 1 commit into
mainfrom
audit/convert-cli
Jun 12, 2026
Merged

jakmro merged 1 commit into
mainfrom
audit/convert-cli

Conversation

@ncylich

@ncylich ncylich commented Jun 10, 2026

Copy link
Copy Markdown
Collaborator

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

Comment thread python/cactus/convert/handoff_probe.py Resolved
@kar-m

kar-m commented Jun 10, 2026 •

Copy link
Copy Markdown
Collaborator

tested, lgtm once the block is reverted @jakmro
EDIT: Noah pushed update reverting said block, now lgtm

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
ncylich force-pushed the audit/convert-cli branch from 813ed8c to 585f7a1 Compare June 10, 2026 03:04
@ncylich
ncylich marked this pull request as ready for review June 10, 2026 06:05
Copilot AI review requested due to automatic review settings June 10, 2026 06:05

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

@jakmro
jakmro merged commit 87ad2e6 into main Jun 12, 2026
6 of 7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants