Bowen Peng
bloc97
AI & ML interests
Machine Learning, Computer Graphics, Language Models
Organizations
bloc97's activity
How did you train this without going OOM in RAM & VRAM?
3
#15 opened 5 months ago
by
vicplus
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65d67267b06abf924b09966a/7uoyHrqQp6kdMDCUjqfjE.jpeg)
VRAM usage for full 128k tokens
7
#5 opened 9 months ago
by
Hypersniper
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63b229669d21227b914badbb/umr0ngvZ5L_Nv2nVlC-Zo.png)
sliding_window = 131072? Sliding window attention doesn't work for 128?
1
#4 opened 9 months ago
by
keyishen
Hardware requirements for the model.
2
#1 opened 11 months ago
by
Sc0urge