Skip to content

Test over mr-rate/fusion-modes/vision-encoding coverage - #8

Open
Zephyruss1 wants to merge 6 commits into
forithmus:mainfrom
Zephyruss1:test/mr-rate-coverage
Open

Test over mr-rate/fusion-modes/vision-encoding coverage#8
Zephyruss1 wants to merge 6 commits into
forithmus:mainfrom
Zephyruss1:test/mr-rate-coverage

Conversation

@Zephyruss1

Copy link
Copy Markdown
Contributor

No description provided.

- Add tests for all_gather_batch in single-device and distributed modes
- Add tests for RearrangeImage and downsampled visual latent projections
- Add default BiomedVLP text encoder initialization test
- Add TestVisualInstances for instance encoding and mask expansion
- Assert state dict weight equivalence in model loading test
…nd visual tokens

- Add test for run_checkpoint active branch during training mode
- Add gradient checkpointing backward pass test in TestMRRATELoss
- Add test for forward call with return_visual_tokens=True
- Add test for precomputed 2D text_latents in late attention pooling
- Since get_optimizer returns AdamW when weight decay > 0 (in this case wd=0.01), this accurately reflects the optimizer type being verified.
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