Update open-clip-torch requirement from <3.0.0,>=2.0.0 to >=2.0.0,<4.0.0

[dependabot]

Updates the requirements on open-clip-torch to permit the latest version.

Release notes

Sourced from open-clip-torch's releases.

v3.1.0

What's Changed

• Add support for MetaCLIP2 WorldWide models by @​rwightman in mlfoundations/open_clip#1100
• Fix mask for CoCa generate by @​rwightman in mlfoundations/open_clip#1103
• Add a text locking impl that works across CustomCLIP and CLIP. by @​rwightman in mlfoundations/open_clip#1104

Full Changelog: mlfoundations/open_clip@v3.0.0...v3.1.0

Changelog

Sourced from open-clip-torch's changelog.

2.24.0

• Fix missing space in error message
• use model flag for normalizing embeddings
• init logit_bias for non siglip pretrained models
• Fix logit_bias load_checkpoint addition
• Make CoCa model match CLIP models for logit scale/bias init
• Fix missing return of "logit_bias" in CoCa.forward
• Add NLLB-CLIP with SigLIP models
• Add get_logits method and NLLB tokenizer
• Remove the empty file src/open_clip/generation_utils.py
• Update params.py: "BatchNorm" -> "LayerNorm" in the description string for "--lock-text-freeze-layer-norm"

2.23.0

• Add CLIPA-v2 models
• Add SigLIP models
• Add MetaCLIP models
• Add NLLB-CLIP models
• CLIPA train code
• Minor changes/fixes
  • Remove protobuf version limit
  • Stop checking model name when loading CoCa models
  • Log native wandb step
  • Use bool instead of long masks

2.21.0

• Add SigLIP loss + training support
• Add more DataComp models (B/16, B/32 and B/32@256)
• Update default num workers
• Update CoCa generation for transformers>=4.31
• PyTorch 2.0 state_dict() compatibility fix for compiled models
• Fix padding in ResizeMaxSize
• Convert JIT model on state dict load for pretrained='filename…'
• Other minor changes and fixes (typos, README, dependencies, CI)

2.20.0

• Add EVA models
• Support serial worker training
• Fix Python 3.7 compatibility

2.19.0

• Add DataComp models

2.18.0

• Enable int8 inference without .weight attribute

... (truncated)

Commits

• 8480ac9 Release 3.1.0
• b857e89 Add a text locking impl that works across CustomCLIP and CLIP. Fix #1070, fix...
• 8fa78c2 Fix mask for CoCa generate, causal mask needs slicing to match current seq le...
• dd9bee2 Add assert that eos_token_id is not None, should fix jit
• 07ea0ca Add support for MetaCLIP2 WorldWide models, explicit eos text token pooling a...
• 223afc4 Release 3.0.0
• f9c40a5 Resize timm image encoders (#1099)
• a03e6ec Update min reqs, test on python 3.10 (#1098)
• 19ffcc5 An alternative text masking helper that offers a correct option for CoCa cls ...
• bbc6558 Simply reference weight handling for custom vs default blocks
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)