yongchanghao (Yongchang Hao)

updated a model 6 days ago

yongchanghao/DeepSeek-R1-Distill-Qwen-1.5B

Text Generation • Updated 6 days ago • 38

published a model 6 days ago

yongchanghao/DeepSeek-R1-Distill-Qwen-1.5B

Text Generation • Updated 6 days ago • 38

upvoted a paper 5 months ago

Qwen2.5 Technical Report

Paper • 2412.15115 • Published Dec 19, 2024 • 367

reacted to their post with 🔥 6 months ago

Post

3779

We just released a paper (NeuZip) that compresses VRAM in a lossless manner to run larger models. This should be particularly useful when VRAM is insufficient during training/inference. Specifically, we look inside each floating number and find that the exponents are highly compressible (as shown in the figure below).

Read more about the work at NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks (2410.20650)

authored a paper 6 months ago

Teacher Forcing Recovers Reward Functions for Text Generation

Paper • 2210.08708 • Published Oct 17, 2022

posted an update 6 months ago

Post

3779

We just released a paper (NeuZip) that compresses VRAM in a lossless manner to run larger models. This should be particularly useful when VRAM is insufficient during training/inference. Specifically, we look inside each floating number and find that the exponents are highly compressible (as shown in the figure below).

Read more about the work at NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks (2410.20650)