Matthew Hendrey's picture

3

Matthew Hendrey

mrhendrey

AI & ML interests

None yet

Recent Activity

updated a model 8 days ago

mrhendrey/Florence-2-large-ft-safetensors

New activity 10 days ago

microsoft/Florence-2-large:VRAM consumption when using GPU (CUDA)

New activity 10 days ago

microsoft/Florence-2-large:Batch: inefficient memory

View all activity

Organizations

None yet

mrhendrey's activity

New activity in microsoft/Florence-2-large 10 days ago

VRAM consumption when using GPU (CUDA)

#37 opened 5 months ago by

Batch: inefficient memory

#50 opened 4 months ago by

New activity in neuralmagic/Llama-3.2-90B-Vision-Instruct-FP8-dynamic about 2 months ago

Any chance your team is working on a 4-bit Llama-3.2-90B-Vision-Instruct-quantized.w4a16 version?

#1 opened about 2 months ago by