Hugging Face's logo
Ali Bidaran's picture
9 2 85

Ali Bidaran

alibidaran
John6666's profile picture Mi6paulino's profile picture HailJebus's profile picture
Ā·

AI & ML interests

LLMs, Computer Vision, Generative AI, NLP, Machine /Deep learning, Reinforcement Learning

Recent Activity

liked a dataset about 14 hours ago
angie-chen55/python-github-code
liked a dataset about 14 hours ago
dipesh/python-code-ds-mini
reacted to sergiopaniego's post with šŸ‘ 14 days ago
Just included example scripts for aligning models using GSPO (including VLM example) šŸ™†ā€ā™‚ļøšŸ™†ā€ā™‚ļø GSPO is the latest RL alignment algo by @Alibaba_Qwen and it's already supported in the latest TRL v0.20 release. Super-easy-to-get-started example scripts below, GO run them!šŸ‘©ā€šŸ’»šŸ‘©ā€šŸ’» šŸ§‘ā€šŸŽØ Script: https://github.com/huggingface/trl/blob/main/examples/scripts/gspo.py šŸ¦„ VLM script: https://github.com/huggingface/trl/blob/main/examples/scripts/gspo_vlm.py šŸ§© More TRL examples: https://huggingface.co/docs/trl/main/en/example_overview šŸ§™ā€ā™‚ļø GSPO paper: https://huggingface.co/papers/2507.18071
View all activity

Organizations

None yet