om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
3 Releases
Latest: 1y ago
v0.2.1Latest
📋 What's Changed
- Develop/v0.2.0 by @SZhanZ in https://github.com/om-ai-lab/VLM-R1/pull/177
- Develop/v0.2.0 by @SZhanZ in https://github.com/om-ai-lab/VLM-R1/pull/186
- Develop/v0.2.0 by @SZhanZ in https://github.com/om-ai-lab/VLM-R1/pull/187
- Develop/v0.2.0 by @SZhanZ in https://github.com/om-ai-lab/VLM-R1/pull/188
- update README by @SZhanZ in https://github.com/om-ai-lab/VLM-R1/pull/189
- add findings info in README by @SZhanZ in https://github.com/om-ai-lab/VLM-R1/pull/190
- fix mcq reward by @Amos1109 in https://github.com/om-ai-lab/VLM-R1/pull/144
- Feat: Clip Higher by @SabaPivot in https://github.com/om-ai-lab/VLM-R1/pull/199
- + 8 more
✨ New Contributors
- @SabaPivot made their first contribution in https://github.com/om-ai-lab/VLM-R1/pull/199
- @P3ngLiu made their first contribution in https://github.com/om-ai-lab/VLM-R1/pull/207
- Full Changelog: https://github.com/om-ai-lab/VLM-R1/compare/v0.2.0...v0.2.1
v0.2.0
📋 What's Changed
- add test_od_r1 by @KingSan666888 in https://github.com/om-ai-lab/VLM-R1/pull/157
- Develop/v0.2.0 by @SZhanZ in https://github.com/om-ai-lab/VLM-R1/pull/165
- add math model in README by @SZhanZ in https://github.com/om-ai-lab/VLM-R1/pull/166
- add features in README by @SZhanZ in https://github.com/om-ai-lab/VLM-R1/pull/170
- Sync the blog content. by @SZhanZ in https://github.com/om-ai-lab/VLM-R1/pull/176
- Full Changelog: https://github.com/om-ai-lab/VLM-R1/compare/v0.1.0...v0.2.0
v0.1.0
📋 What's Changed
- Ruox/main jsonl dataloader by @xrc10 in https://github.com/om-ai-lab/VLM-R1/pull/14
- docs: update README.md by @eltociear in https://github.com/om-ai-lab/VLM-R1/pull/27
- fix model torch_dtype setting by @zhangqianqianhzlh in https://github.com/om-ai-lab/VLM-R1/pull/49
- custom reward by @zhangqianqianhzlh in https://github.com/om-ai-lab/VLM-R1/pull/55
- multi-node GPRO recipe by @xrc10 in https://github.com/om-ai-lab/VLM-R1/pull/59
- add epsilon clipping for GRPO by @xrc10 in https://github.com/om-ai-lab/VLM-R1/pull/61
- formats are not unique by @Amos1109 in https://github.com/om-ai-lab/VLM-R1/pull/65
- Add num_iterations from original GRPO algorithm by @xrc10 in https://github.com/om-ai-lab/VLM-R1/pull/78
- + 10 more
✨ New Contributors
- @xrc10 made their first contribution in https://github.com/om-ai-lab/VLM-R1/pull/14
- @eltociear made their first contribution in https://github.com/om-ai-lab/VLM-R1/pull/27
- @zhangqianqianhzlh made their first contribution in https://github.com/om-ai-lab/VLM-R1/pull/49
- @Amos1109 made their first contribution in https://github.com/om-ai-lab/VLM-R1/pull/65
- @davidluciolu made their first contribution in https://github.com/om-ai-lab/VLM-R1/pull/58
- @chaoyuhao made their first contribution in https://github.com/om-ai-lab/VLM-R1/pull/105
- Full Changelog: https://github.com/om-ai-lab/VLM-R1/commits/v0.1.0
