pkulium

Results 4 issues of pkulium

Release pre-trained LoRA weights on HuggingFace.

1 comment

code for LLaMA-2-7B-4k/32k with Retrieval.

Is there any way to find code code for LLaMA-2-7B-4k/32k with Retrieval. It seems to be missing now. Thanks!

script to reproduce all experiments

greate work! I am wonder if we can get scripts to reproduce all experiments?

Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation

Great work! Is there any place to find code for your another paper ''Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation''?