Wei Huang's picture

4 17 8

Wei Huang

AaronHuangWei

·

AI & ML interests

Deep Learning; Efficient AI; Quantization; LLMs

Recent Activity

updated a model 7 days ago

AaronHuangWei/grpo_edit_qwen2.5-vl-7b_step310_v2

published a model 7 days ago

AaronHuangWei/grpo_edit_qwen2.5-vl-7b_step310_v2

authored a paper 9 days ago

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

View all activity

Organizations

Papers 12

arxiv:2510.15870

arxiv:2510.11696

arxiv:2509.22622

arxiv:2507.10548

models 36

AaronHuangWei/grpo_edit_qwen2.5-vl-7b_step310_v2

8B • Updated 7 days ago • 13

AaronHuangWei/grpo_edit_qwen2.5-vl-7b_step120_v2

8B • Updated 10 days ago • 8

AaronHuangWei/Llama-3.1-Nemotron-Nano-8B-v1-NVFP4A16-GPTQ

5B • Updated 27 days ago • 25

AaronHuangWei/Llama-3.1-Nemotron-Nano-8B-v1-NVFP4A16

5B • Updated 27 days ago • 1.43k

AaronHuangWei/qwen2.5-32B-Instruct-bigmath_awq-nvfp4-fake-ckpt_450

33B • Updated Sep 22 • 1

AaronHuangWei/qwen2.5-32B-Instruct-bigmath_awq-nvfp4-fake-ckpt_380

33B • Updated Sep 22 • 1

AaronHuangWei/qwen2.5-32B-Instruct-bigmath_awq-nvfp4-fake-ckpt_290

33B • Updated Sep 21 • 1

AaronHuangWei/qwen2.5-3B-Instruct-bigmath_awq-nvfp4-fake-ckpt_290

AaronHuangWei/qwen2.5-3B-Instruct-bigmath_lora_ckpt_320

33B • Updated Sep 21 • 1

AaronHuangWei/qwen2.5-3B-Instruct-awq-int4-fake

3B • Updated Sep 17 • 1

datasets 0

None public yet