Wei Huang's picture

3 14 8

Wei Huang

AaronHuangWei

·

AI & ML interests

Deep Learning; Efficient AI; Quantization; LLMs

Recent Activity

commented on an article 5 days ago

No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

commented on an article 10 days ago

No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

updated a dataset 21 days ago

LongVideo-Reason/longvideo-reason

View all activity

Organizations

AaronHuangWei 's models 23

AaronHuangWei/Qwen2.5-7B-GRPO-MATH500-lora32

Updated 26 days ago

AaronHuangWei/Qwen2.5-7B-Instruct-GRPO-MATH500-qlora32

Updated 26 days ago

AaronHuangWei/Qwen2.5-14B-GRPO-MATH500-lora32

Updated 26 days ago

AaronHuangWei/Qwen2.5-14B-GRPO-MATH500-lora64

Updated 26 days ago

AaronHuangWei/Qwen3-14B-GRPO-MATH500-lora64

Updated 26 days ago

AaronHuangWei/Qwen2.5-7B-GRPO-MATH500-qlora64

Updated 26 days ago

AaronHuangWei/Qwen2.5-7B-GRPO-MATH500-lora64

Updated 26 days ago

AaronHuangWei/Qwen2.5-7B-GRPO-MATH500

Text Generation • 8B • Updated 27 days ago • 12

AaronHuangWei/Qwen2.5-7B-GRPO-GSM8K

Updated 27 days ago

AaronHuangWei/Qwen2.5-7B-GRPO

Text Generation • 8B • Updated 27 days ago • 13

AaronHuangWei/Qwen2.5-7B-DAPO

Text Generation • 8B • Updated 27 days ago • 12

AaronHuangWei/Qwen3-8B-DAPO

Updated 27 days ago

AaronHuangWei/Qwen2.5-7B-GSM8k

Updated 27 days ago

AaronHuangWei/Qwen3-8B-GSM8k

Updated 27 days ago

AaronHuangWei/Qwen2.5-7B-GRPO-GSM8k-GRPO

Updated 27 days ago

AaronHuangWei/Qwen2.5-7B-DAPO-Math-GRPO

Updated about 1 month ago

AaronHuangWei/Qwen2.5-3B-Open-R1-Math-GRPO

AaronHuangWei/Qwen2.5-7B-Open-R1-Math-GRPO

AaronHuangWei/Qwen2.5-7B-Open-R1-Code-GRPO

AaronHuangWei/Qwen2.5-1.5B-Open-R1-GRPO

Text Generation • 3B • Updated Feb 21 • 6

AaronHuangWei/Qwen2.5-3B-Open-R1-Distill

Text Generation • 3B • Updated Feb 13 • 5 • 1

AaronHuangWei/SliM-LLM-plus_parameters

Updated May 27, 2024

AaronHuangWei/SliM-LLM_group-precision

Updated May 27, 2024 • 2