wenhua cheng

wenhuach's activity

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

New activity in Intel/GLM-4.7-int4-mixed-AutoRound 3 days ago

AutoRound request: GLM-4.5-Air

1

#1 opened 3 days ago by

babytifa

updated a model 3 days ago

Intel/GLM-4.5-Air-int4-mixed-AutoRound

Text Generation • 1B • Updated 3 days ago • 13

published a model 3 days ago

Intel/GLM-4.5-Air-int4-mixed-AutoRound

Text Generation • 1B • Updated 3 days ago • 13

updated a model 3 days ago

Intel/GLM-4.7-int4-mixed-AutoRound

Text Generation • 2B • Updated 3 days ago • 126 • 18

liked a model 3 days ago

Intel/GLM-4.7-int4-mixed-AutoRound

Text Generation • 2B • Updated 3 days ago • 126 • 18

New activity in Intel/Qwen3-30B-A3B-Instruct-2507-gguf-q2ks-mixed-AutoRound 3 days ago

2507 Thinking model release

11

#4 opened 3 months ago by

anjeysapkovski

liked 4 datasets 4 days ago

BAAI/CCI3-HQ

Viewer • Updated Nov 11, 2024 • 54.8M • 4.26k • 51

wikimedia/wikipedia

Viewer • Updated Jan 9, 2024 • 61.6M • 69.5k • 1.06k

HuggingFaceFW/fineweb

Viewer • Updated Jul 11, 2025 • 52.5B • 183k • 2.58k

nvidia/Nemotron-CC-v2.1

Viewer • Updated 12 days ago • 3.8B • 34.1k • 96

New activity in kernels-community/quantization-gptq 4 days ago

How to use this kernel

#1 opened 4 days ago by

wenhuach

liked a dataset 5 days ago

liwu/MNBVC

Updated about 1 month ago • 117k • 574

upvoted an article 9 days ago

view article

Article

Understanding InstaFlow/Rectified Flow

• 

Oct 6, 2023

•

35

upvoted an article 10 days ago

view article

Article

The Annotated Diffusion Model

• 
• 

Jun 7, 2022

•

306

updated a model 11 days ago

Intel/Qwen3-8B-w2g64-AutoRound-test

2B • Updated 11 days ago • 36 • 1

published a model 11 days ago

Intel/Qwen3-8B-w2g64-AutoRound-test

2B • Updated 11 days ago • 36 • 1

New activity in Intel/Qwen3-235B-A22B-Instruct-2507-gguf-q2ks-mixed-AutoRound 20 days ago

Thinking version has been deleted?

1

#2 opened 20 days ago by

reswewr

reacted to their post with 🔥 27 days ago

view post

Post

2939

🚀 SignRoundV2 for LLM quantization: PTQ-level cost, QAT-level accuracy — yes, even at 2 bits.

SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs (2512.04746)

See translation

🔥

3

3

+

Reply

New activity in Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound 27 days ago

Improve model card: Add pipeline tag, library name, and update paper/citation

🔥 1

#1 opened 29 days ago by

nielsr

authored a paper 29 days ago

SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

Paper • 2512.04746 • Published 30 days ago • 13