Skip to content

Add glm_4d1v model integration (GLM-4.1V-9B-Thinking)#145

Closed
ZTWHHH wants to merge 1 commit into
mm-evaluation:mainfrom
ZTWHHH:add-glm-4d1v
Closed

Add glm_4d1v model integration (GLM-4.1V-9B-Thinking)#145
ZTWHHH wants to merge 1 commit into
mm-evaluation:mainfrom
ZTWHHH:add-glm-4d1v

Conversation

@ZTWHHH

@ZTWHHH ZTWHHH commented Jun 10, 2026

Copy link
Copy Markdown
Collaborator

Summary

  • Add inference integration for glm_4d1v (THUDM/GLM-4.1V-9B-Thinking).
  • Adds mmeval/infer/glm_4d1v.py, env_files/glm_4d1v_requirements.txt, and the two registry entries.
  • Includes a smoke-test script and result.json for no_media and single_image_start.

Sources

Test plan

  • Text-only smoke test (no_media.json) returns coherent assistant response.
  • Single-image smoke test (single_image_start.json) returns coherent assistant response.
  • Reviewer verifies the inference settings match the official model card.

🤖 Generated with Claude Code

- mmeval/infer/glm_4d1v.py: official-style loading and decoding
- env_files/glm_4d1v_requirements.txt: pinned reproducible env
- mmeval/registry.py: series_mapping + series_infer_env_mapping entries
- test_results/: passing no_media + single_image_start smoke runs

HF:  https://huggingface.co/THUDM/GLM-4.1V-9B-Thinking
GH:  https://github.com/THUDM/GLM-V

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
@ZTWHHH

ZTWHHH commented Jun 10, 2026

Copy link
Copy Markdown
Collaborator Author

Superseded by two correctly-structured combined PRs: one for infer/model code targeting main, one for test scripts/results targeting test-result (matching PR #117/#118 structure).

@ZTWHHH ZTWHHH closed this Jun 10, 2026
@ZTWHHH
ZTWHHH deleted the add-glm-4d1v branch June 10, 2026 15:22
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.

1 participant