timm/coat_lite_medium_384.in1k
Image Classification
•
Updated
•
215
Ross Wightman
rwightman
AI & ML interests
Computer vision, transfer learning, semi/self supervised learning, robotics.
Recent Activity
new activity
about 3 hours ago
timm/coat_tiny.in1k:Adding `safetensors` variant of this model
new activity
about 3 hours ago
timm/coat_lite_small.in1k:Adding `safetensors` variant of this model
new activity
about 3 hours ago
timm/coat_mini.in1k:Adding `safetensors` variant of this model
Organizations
rwightman's activity
Adding `safetensors` variant of this model
#1 opened 5 days ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened 5 days ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened 5 days ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened 5 days ago
by
SFconvertbot
Adding `safetensors` variant of this model
#2 opened 1 day ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened 1 day ago
by
SFconvertbot
updated
a
model
about 3 hours ago
Adding `safetensors` variant of this model
#1 opened 1 day ago
by
SFconvertbot
updated
a
model
about 3 hours ago
Adding `safetensors` variant of this model
#1 opened 1 day ago
by
SFconvertbot
Request: DOI
2
#1 opened 13 days ago
by
elliottd
Non-English language pdfs
2
#5 opened 13 days ago
by
NoOneCodesAI
Where are the answers to the questions in the dataset?
1
#1 opened 14 days ago
by
pawanagarwal
liked
4
models
17 days ago
timm/ViT-SO400M-16-SigLIP2-384
Zero-Shot Image Classification
•
Updated
•
1.5k
•
1
timm/ViT-B-16-SigLIP2-256
Zero-Shot Image Classification
•
Updated
•
35.9k
•
2
timm/ViT-SO400M-16-SigLIP2-512
Zero-Shot Image Classification
•
Updated
•
1.12k
•
3
timm/ViT-L-16-SigLIP2-512
Zero-Shot Image Classification
•
Updated
•
1.63k
•
2
Model size seems odd
3
#1 opened 20 days ago
by
bbb42
reacted to
csabakecskemeti's
post with 🤗🚀
22 days ago
Post
2762
Testing Training on AMD/ROCm the first time!
I've got my hands on an AMD Instinct MI100. It's about the same price used as a V100 but on paper has more TOPS (V100 14TOPS vs MI100 23TOPS) also the HBM has faster clock so the memory bandwidth is 1.2TB/s.
For quantized inference it's a beast (MI50 was also surprisingly fast)
For LORA training with this quick test I could not make the bnb config works so I'm running the FT on the fill size model.
Will share all the install, setup and setting I've learned in a blog post, together with the cooling shroud 3D design.
I've got my hands on an AMD Instinct MI100. It's about the same price used as a V100 but on paper has more TOPS (V100 14TOPS vs MI100 23TOPS) also the HBM has faster clock so the memory bandwidth is 1.2TB/s.
For quantized inference it's a beast (MI50 was also surprisingly fast)
For LORA training with this quick test I could not make the bnb config works so I'm running the FT on the fill size model.
Will share all the install, setup and setting I've learned in a blog post, together with the cooling shroud 3D design.
-
- 8 replies