Popular repositories Loading

1. iw_sft iw_sft Public

   Python 28 2

2. iw_sft_control iw_sft_control Public

   This is the new directory for importance weighted SFT. This is the specific folder for the set of control tasks.

   Python 4

3. unrestricted-adversarial-examples unrestricted-adversarial-examples Public

   Forked from coeff-giving/unrestricted-adversarial-examples

   Contest Proposal and infrastructure for the Unrestricted Adversarial Examples Challenge

   Python

4. filtered_bc_diffusion filtered_bc_diffusion Public

   Forked from kvablack/ddpo-pytorch

   DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support

   Python

5. simple_rl_experiments simple_rl_experiments Public

   Forked from hkust-nlp/simpleRL-reason

   Python

6. filterd_bc_s1 filterd_bc_s1 Public

   Forked from simplescaling/s1

   Python