Matthew Hendrey

mrhendrey's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in neuralmagic/Sparse-Llama-3.1-8B-ultrachat_200k-2of4-quantized.w4a16 3 months ago

Model only outputs "!!!!!!!!!!"

1

#1 opened 3 months ago by

mrhendrey

New activity in microsoft/Florence-2-large 4 months ago

VRAM consumption when using GPU (CUDA)

3

#37 opened 9 months ago by

Sunjay353

Batch: inefficient memory

1

#50 opened 8 months ago by

SinanAkkoyun

New activity in neuralmagic/Llama-3.2-90B-Vision-Instruct-FP8-dynamic 6 months ago

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

2

#1 opened 6 months ago by

mrhendrey