Ross Wightman

rwightman's activity

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

New activity in timm/vit_little_patch16_reg4_gap_256.sbb_in1k 5 days ago

Loss exploding to nan

30

#1 opened 22 days ago by

tony0278611

liked 2 models 19 days ago

openai/gpt-oss-20b

Text Generation • 22B • Updated 11 days ago • 6.7M • • 3.22k

openai/gpt-oss-120b

Text Generation • 120B • Updated 11 days ago • 1.59M • • 3.56k

upvoted a collection 19 days ago

gpt-oss

Collection

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated 17 days ago • 316

updated a collection 19 days ago

SigLIP 2

Collection

OpenCLIP and timm SigLIP 2 models • 47 items • Updated 19 days ago • 23

upvoted an article 19 days ago

view article

Article

An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct

By •

Jun 11, 2024

• 64

New activity in UCSC-VLAA/openvision-vit-base-patch16-384 20 days ago

Error

1

#2 opened 20 days ago by

viks555

updated 2 models 20 days ago

timm/naflexvit_base_patch16_siglip.v2_webli

Image Feature Extraction • Updated 20 days ago • 45

timm/naflexvit_so400m_patch16_siglip.v2_webli

Image Feature Extraction • Updated 20 days ago • 32

published 2 models 20 days ago

timm/naflexvit_base_patch16_siglip.v2_webli

Image Feature Extraction • Updated 20 days ago • 45

timm/naflexvit_so400m_patch16_siglip.v2_webli

Image Feature Extraction • Updated 20 days ago • 32

updated a model 23 days ago

timm/mobilenetv5_300m.gemma3n

Image Feature Extraction • Updated 23 days ago • 102

published a model 23 days ago

timm/mobilenetv5_300m.gemma3n

Image Feature Extraction • Updated 23 days ago • 102

reacted to merve's post with 🚀 23 days ago

view post

Post

2203

Cohere just dropped CohereLabs/command-a-vision-07-2025, a 112B (dense!) vision LM
> based on SigLIP2 & Command-A
> built for enterprise use cases 🔥
> use with Inference Providers or transformers 🤗
read their blog https://huggingface.co/blog/CohereLabs/introducing-command-a-vision-07-2025

See translation

• 

• 
• 
• 2 replies

·

🚀

4

4

🔥

2

2

👍

2

2

+

Reply

upvoted a collection 23 days ago

MetaCLIP

Collection

MetaCLIP & MetaCLIP2 OpenCLIP and timm models. All models are dual timm + OpenCLIP (or just timm for specific vit encoders). • 24 items • Updated 23 days ago • 2

updated a collection 23 days ago

MetaCLIP

Collection

MetaCLIP & MetaCLIP2 OpenCLIP and timm models. All models are dual timm + OpenCLIP (or just timm for specific vit encoders). • 24 items • Updated 23 days ago • 2