Expanding Model Context and Creating Chat Models with a Single Click
β’
37
Jeonghwan Park PRO
maywell
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
2 days ago
When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context
Training
updated
a dataset
4 days ago
maywell/koVast
New activity
4 days ago
maywell/koVast:License λ¬Έμ
Articles
Organizations
maywell's activity
upvoted
a
paper
2 days ago
updated
a
dataset
4 days ago
License λ¬Έμ
1
#1 opened 9 days ago
by
dyo85
dyo85
upvoted
a
paper
10 days ago
liked
a
model
12 days ago
liked
2
models
13 days ago
liked
a
model
14 days ago
liked
a
model
15 days ago
liked
2
models
16 days ago
liked
a
model
18 days ago
liked
a
dataset
19 days ago
Reacted to
yongchanghao's
post with π₯
21 days ago
Post
3724
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)
Read more about the work at NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks (2410.20650)
liked
a
dataset
22 days ago
liked
a
model
23 days ago
liked
a
dataset
23 days ago
liked
a
model
23 days ago
liked
a
dataset
23 days ago
liked
a
model
23 days ago
