wenhua cheng's picture

wenhua cheng

wenhuach

·

wenhuach21

AI & ML interests

Model Compression, CV

Recent Activity

reacted to their post with 🔥 1 day ago

🚀 SignRoundV2 for LLM quantization: PTQ-level cost, QAT-level accuracy — yes, even at 2 bits. https://huggingface.co/papers/2512.04746

new activity 1 day ago

Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound:Improve model card: Add pipeline tag, library name, and update paper/citation

authored a paper 3 days ago

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

View all activity

Organizations

liked 4 models 4 months ago

Intel/DeepSeek-V3.1-int4-mixed-AutoRound

Text Generation • Updated Sep 24 • 83 • 11

Intel/gpt-oss-20b-int4-AutoRound

2B • Updated Aug 7 • 223 • 7

Intel/Qwen3-30B-A3B-Instruct-2507-gguf-q2ks-mixed-AutoRound

31B • Updated Oct 9 • 313 • 26

Intel/Qwen3-30B-A3B-Instruct-2507-int4-AutoRound

0.6B • Updated Sep 17 • 426 • 6

liked 6 models 5 months ago

Intel/Qwen3-Coder-480B-A35B-Instruct-gguf-q2ks-mixed-AutoRound

480B • Updated Jul 28 • 86 • 13

Intel/Qwen3-235B-A22B-Instruct-2507-int4-mixed-AutoRound

1B • Updated Jul 28 • 88 • 11

Intel/Qwen3-235B-A22B-Instruct-2507-gguf-q4km-AutoRound

235B • Updated Jul 24 • 192 • 7

Intel/Qwen3-235B-A22B-Instruct-2507-int4-AutoRound

1B • Updated Jul 29 • 18 • 2

Intel/Qwen3-235B-A22B-Instruct-2507-gguf-q2ks-mixed-AutoRound

235B • Updated Oct 14 • 225 • 13

Intel/Kimi-K2-Instruct-gguf-q2ks-mixed-AutoRound

1T • Updated Jul 22 • 207 • 5

liked a model about 1 year ago

OPEA/Meta-Llama-3.1-70B-Instruct-int4-sym-inc

11B • Updated Apr 24 • 10 • 1

liked 9 models over 1 year ago

LnL-AI/TinyLlama-1.1B-intermediate-step-1341k-3T-autoround-lm_head-symFalse

Text Generation • 1B • Updated Jul 24, 2024 • 13 • 1

kaitchup/Meta-Llama-3.1-8B-Instruct-autoround-gptq-4bit-asym

Text Generation • 2B • Updated Aug 13, 2024 • 16 • 1

kaitchup/Meta-Llama-3.1-8B-Instruct-autoround-gptq-4bit-sym

Text Generation • 2B • Updated Aug 13, 2024 • 5 • 1

cstr/Spaetzle-v85-7b-int4-inc

Text Generation • 1B • Updated Jun 24, 2024 • 8 • 2

Intel/Qwen2-7B-int4-inc

Text Generation • 2B • Updated Oct 24, 2024 • 16 • 6

Qwen/Qwen-72B-Chat

Text Generation • 72B • Updated Oct 8, 2024 • 280 • 156

Intel/phi-2-int4-inc

Text Generation • 0.6B • Updated Oct 22, 2024 • 16 • 4

Intel/Mistral-7B-v0.1-int4-inc-lmhead

Text Generation • 1B • Updated May 29, 2024 • 9 • 1

cstr/Spaetzle-v60-7b-int4-inc

Text Generation • 1B • Updated May 15, 2024 • 5 • 2