wenhua cheng

wenhuach's activity

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

New activity in kaitchup/Qwen2.5-1.5B-Instruct-AutoRound-GPTQ-asym-4bit 17 days ago

AutoRound now supports full range sym

#1 opened 17 days ago by wenhuach

New activity in Satwik11/Phi-3.5-Mini-instruct-quantized-autoround-asym-2bit 2 months ago

GPTQ format has bug for asym kernel

#1 opened 2 months ago by wenhuach

New activity in Intel/Meta-Llama-3.1-8B-Instruct-int4-inc 4 months ago

Model files missing?

3

#1 opened 4 months ago by akashaero

New activity in Intel/low_bit_open_llm_leaderboard 6 months ago

Add support for AQLM

3

#1 opened 6 months ago by BlackSamorez

New activity in 01-ai/Yi-6B-Chat 7 months ago

Introducing AutoRound INT4 algorithm

4

#4 opened 7 months ago by wenhuach

commented a paper 7 months ago

How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study

Paper • 2404.14047 • Published Apr 22 • 44 •

12

New activity in baichuan-inc/Baichuan2-7B-Chat 7 months ago

Introducing AutoRound int4 algoirhtm

#14 opened 7 months ago by wenhuach

New activity in Qwen/Qwen1.5-7B-Chat 8 months ago

Introducing AutoRound INT4 Algorithm

#12 opened 8 months ago by wenhuach

commented a paper 8 months ago

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs

Paper • 2309.05516 • Published Sep 11, 2023 • 9 •

2