← Back to List
⚠
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
PythonPKU-Alignment/align-anything

align-anything

Align Anything: Training All-modality Model with Feedback

56.4/100
★ 4.6KForks: 510
View on GitHub →
Loading report...

Similar Projects

thepipe

74

Get clean data from tricky documents, powered by vision-language models ⚡

Python★ 1.5K

Ovis

64

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

Python★ 1.4K

HALOs

56

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

Python★ 907

oat

71

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

Python★ 637
← Back to List