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 7 days ago

Loss exploding to nan

27

#1 opened 15 days ago by

tony0278611

liked 2 models 12 days ago

openai/gpt-oss-20b

Text Generation • 22B • Updated 4 days ago • 3.42M • • 3.06k

openai/gpt-oss-120b

Text Generation • 120B • Updated 4 days ago • 788k • • 3.44k

upvoted a collection 12 days ago

gpt-oss

Collection

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated 11 days ago • 293

updated a collection 12 days ago

SigLIP 2

Collection

OpenCLIP and timm SigLIP 2 models • 47 items • Updated 12 days ago • 23

upvoted an article 13 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 13 days ago

Error

1

#2 opened 13 days ago by

viks555

updated 2 models 13 days ago

timm/naflexvit_base_patch16_siglip.v2_webli

Image Feature Extraction • Updated 13 days ago • 29

timm/naflexvit_so400m_patch16_siglip.v2_webli

Image Feature Extraction • Updated 13 days ago • 25

published 2 models 13 days ago

timm/naflexvit_base_patch16_siglip.v2_webli

Image Feature Extraction • Updated 13 days ago • 29

timm/naflexvit_so400m_patch16_siglip.v2_webli

Image Feature Extraction • Updated 13 days ago • 25

updated a model 16 days ago

timm/mobilenetv5_300m.gemma3n

Image Feature Extraction • Updated 16 days ago • 88

published a model 16 days ago

timm/mobilenetv5_300m.gemma3n

Image Feature Extraction • Updated 16 days ago • 88

reacted to merve's post with 🚀 16 days ago

view post

Post

2176

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 16 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 16 days ago • 2

updated a collection 16 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 16 days ago • 2