tianzhechu
/

GP-VL-Init

Model card Files Files and versions Community

GP-VL-Init

This model serves as a initial checkpoint to reproduce results in paper SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training.

Related links

Website: https://tianzhechu.com/SFTvsRL/

Github: https://github.com/LeslieTrue/SFTvsRL

Arxiv: https://arxiv.org/abs/2501.17161v1

HF: https://huggingface.co/papers/2501.17161

Downloads last month: 5

Safetensors

Model size

10.7B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including tianzhechu/GP-VL-Init

SFTvsRL Models & Data

This collection contains 4 initial checkpoints for https://github.com/LeslieTrue/SFTvsRL and necessary data for V-IRL training. • 7 items • Updated Mar 13 • 9