Skip to content

Releases: TideDra/lmm-r1

v0.7.3a

23 Apr 09:33
Compare
Choose a tag to compare
  • Sync with OpenRLHF v0.7.3
  • Support LLMs PPO training
  • Refacto visual inputs

v0.7.0a

15 Apr 16:20
Compare
Choose a tag to compare
  • Sync with OpenRLHF v0.7.0
  • Support dynamic sampling in DAPO
  • Support mixed-modal training

v0.6.2a

24 Mar 16:10
Compare
Choose a tag to compare
  • Sync with OpenRLHF v0.6.2
  • Support new models: Phi3.5-V, Phi4-Multimodal
  • Support Liger-Kernel to reduce LMM memory usage
  • Support Lora with vllm