EZ
enpeizhao
AI & ML interests
Autonomous Driving, VLM, LLM, end-to-end
Recent Activity
reacted
to
sergiopaniego's
post
with š„
2 days ago
New GRPO + TRL free Colab notebook out! š„
Fine-tune 7B+ models on T4 GPUs thanks to a ton of memory optimizations for GRPO
7B model uses only 9.2 GB VRAM (~7Ć reduction) š¤Æ
Try the notebook here š https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_trl_lora_qlora.ipynb
reacted
to
sergiopaniego's
post
with š„
2 days ago
The list of hands-on notebooks (some beginner-friendly!) to get started with fine-tuning using TRL keeps growing!!
ā¢ SFT
ā¢ GRPO
ā¢ Tool calling & agents
ā¢ RL environments with OpenEnv
ā¢ LLMs and VLMs
āØ Many run on FREE Colab, making it super easy to get started fast!
https://github.com/huggingface/trl/tree/main/examples/notebooks
updated
a model
3 days ago
enpeizhao/internvl2-1b-odd-distilled-merged
Organizations
None yet