[Example] Mix algorithm with VLM #342

hiyuchang · 2025-10-27T03:51:55Z

Description

As the title says

Checklist

Please check the following items before code is ready to be reviewed.

Code has passed all tests
Docstrings have been added/updated in Google Style
Documentation has been updated
Code is ready for review

gemini-code-assist · 2025-10-27T03:52:09Z

Summary of Changes

Hello @hiyuchang, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a new example showcasing the application of the MIX algorithm with Visual Language Models (VLM), specifically utilizing the Qwen2.5-VL-3B-Instruct model. It includes a detailed configuration file and a README to guide users through setting up and running this experimental feature. Additionally, it refines existing example configurations by standardizing the use of environment variables for dataset paths, enhancing the overall configurability and portability of the examples.

Highlights

New VLM Example: Introduction of an example demonstrating the MIX algorithm with a Visual Language Model (VLM), specifically using the Qwen2.5-VL-3B-Instruct model.
VLM Example Configuration: Addition of mix_vlm.yaml which provides a complete configuration for running the MIX algorithm with VLM, including dataset paths, model details, and training parameters.
Environment Variable Standardization: Updates to existing example configurations (grpo_vlm, mix_chord, mix_math) to consistently use environment variables for dataset paths, improving flexibility and deployment.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request introduces a new example for using the MIX algorithm with a Vision-Language Model (VLM), which is a valuable addition. My review focuses on improving the portability, consistency, and user-friendliness of the configuration files. I've identified a few hardcoded paths that should be parameterized using environment variables to make the examples easier for others to run. Additionally, I've noted that some existing examples have had their default dataset paths removed, which I recommend restoring to improve their out-of-the-box experience. A minor typo in the new README file has also been pointed out.

examples/mix_vlm/mix_vlm.yaml

examples/mix_chord/mix_chord.yaml

examples/mix_math/mix_math.yaml

examples/mix_vlm/README.md

examples/mix_vlm/mix_vlm.yaml

hiyuchang · 2025-10-27T06:12:21Z

/unittest-module-common

github-actions · 2025-10-27T06:18:50Z

Summary

Tests 📝	Passed ✅	Failed ❌	Skipped ⏭️	Other ❓	Flaky 🍂	Duration ⏱️
33	33	0	0	0	0	319ms

Tests

Test Name	Status	Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid	✅	32ms
tests/common/config_test.py::TestConfig::test_config_flatten	✅	1ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid	✅	1ms
tests/common/config_test.py::TestConfig::test_default_workflow	✅	1ms
tests/common/config_test.py::TestConfig::test_load_default_config	✅	4ms
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly	✅	1ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster	✅	1ms
tests/common/experience_test.py::TestEID::test_eid_properties	✅	1ms
tests/common/experience_test.py::TestExperience::test_action_mask_and_logprobs_type	✅	1ms
tests/common/experience_test.py::TestExperience::test_assertions	✅	1ms
tests/common/experience_test.py::TestExperience::test_dpo_experience	✅	1ms
tests/common/experience_test.py::TestExperience::test_gather	✅	1ms
tests/common/experience_test.py::TestExperience::test_hf_datasets_conversion	✅	1ms
tests/common/experience_test.py::TestExperience::test_multi_turn_experience	✅	1ms
tests/common/experience_test.py::TestExperience::test_serialize_deserialize	✅	1ms
tests/common/experience_test.py::TestExperience::test_single_turn_experience	✅	1ms
tests/common/experience_test.py::TestExperience::test_to_dict	✅	1ms
tests/common/experience_test.py::TestExperienceConversion::test_batch_conversion	✅	1ms
tests/common/experience_test.py::TestExperienceConversion::test_dpo_experience_batch_conversion	✅	1ms
tests/common/experience_test.py::TestExperienceConversion::test_experience_model_experience_conversion	✅	1ms
tests/common/experience_test.py::TestExperienceConversion::test_gather_experiences_with_custom_fields	✅	1ms
tests/common/experience_test.py::TestExperienceConversion::test_multiturn_experience_batch_converstion	✅	1ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate	✅	58ms
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate	✅	35ms
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate	✅	45ms
tests/common/vllm_test.py::TestModelLen_0::test_model_len	✅	21ms
tests/common/vllm_test.py::TestModelLen_1::test_model_len	✅	21ms
tests/common/vllm_test.py::TestAPIServer::test_api	✅	24ms
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async	✅	24ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask	✅	1ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools	✅	1ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls	✅	22ms
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls	✅	20ms

Github Test Reporter by CTRF 💚

hiyuchang added 3 commits October 27, 2025 11:00

add mix_vlm example

0d46a94

fix sft data

3a9acff

fix readme

beff2e6

gemini-code-assist bot reviewed Oct 27, 2025

View reviewed changes

hiyuchang requested a review from garyzhang99 October 27, 2025 03:53

fix typo

ce28c9d

garyzhang99 approved these changes Oct 27, 2025

View reviewed changes

hiyuchang added 2 commits October 27, 2025 19:01

Merge branch 'main' into example/mix_vlm

04ed78f

add results

d9023c7

pan-x-c approved these changes Oct 27, 2025

View reviewed changes

pan-x-c merged commit b081545 into modelscope:main Oct 27, 2025
2 checks passed

garyzhang99 mentioned this pull request Jan 6, 2026

[FEATURE] Could you provide VLM's chord algorithm example and workflow code? Thank you! #308

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[Example] Mix algorithm with VLM #342

[Example] Mix algorithm with VLM #342

Uh oh!

hiyuchang commented Oct 27, 2025

Uh oh!

gemini-code-assist bot commented Oct 27, 2025

Uh oh!

gemini-code-assist bot left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

hiyuchang commented Oct 27, 2025

Uh oh!

github-actions bot commented Oct 27, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

[Example] Mix algorithm with VLM #342

[Example] Mix algorithm with VLM #342

Uh oh!

Conversation

hiyuchang commented Oct 27, 2025

Description

Checklist

Uh oh!

gemini-code-assist bot commented Oct 27, 2025

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

hiyuchang commented Oct 27, 2025

Uh oh!

github-actions bot commented Oct 27, 2025

Summary

Tests

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants