-
AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model
Paper β’ 2309.16058 β’ Published β’ 53 -
119π―οΈΙΈ
Candle Phi Wasm Demo
-
28β‘
Phi 2 Streaming on GPU
A demo of Phi 2 with streaming running on a ZERO GPU.
-
LLM in a flash: Efficient Large Language Model Inference with Limited Memory
Paper β’ 2312.11514 β’ Published β’ 255
Harits Abdurrohman
otakbeku
AI & ML interests
Computer vision
Organizations
Collections
1
models
None public yet
datasets
None public yet