Wei Huang's picture

4 18 8

Wei Huang

AaronHuangWei

·

AI & ML interests

Deep Learning; Efficient AI; Quantization; LLMs

Recent Activity

upvoted a paper 8 days ago

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

updated a model 16 days ago

AaronHuangWei/grpo_edit_qwen2.5-vl-7b_step310_v2

published a model 16 days ago

AaronHuangWei/grpo_edit_qwen2.5-vl-7b_step310_v2

View all activity

Organizations

AaronHuangWei 's models 36

AaronHuangWei/grpo_edit_qwen2.5-vl-7b_step310_v2

8B • Updated 16 days ago • 13

AaronHuangWei/grpo_edit_qwen2.5-vl-7b_step120_v2

8B • Updated 19 days ago • 8

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

5B • Updated Oct 5 • 5

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

5B • Updated Oct 5 • 24

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

33B • Updated Sep 22 • 2

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

33B • Updated Sep 22 • 3

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 • 2

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

3B • Updated Sep 17 • 2

AaronHuangWei/qwen2.5-32B-Instruct-awq-nvfp4-fake

33B • Updated Sep 15 • 2

AaronHuangWei/Qwen2.5-7B-Instruct-bnb-4bit

Text Generation • 4B • Updated Sep 14 • 15

AaronHuangWei/Qwen2.5-14B-Instruct-bnb-4bit

Text Generation • 14B • Updated Sep 14 • 5

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

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

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

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

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

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

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

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

Text Generation • 8B • Updated Aug 14 • 3

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

AaronHuangWei/Qwen2.5-7B-GRPO

Text Generation • 8B • Updated Aug 14 • 4

AaronHuangWei/Qwen2.5-7B-DAPO

Text Generation • 8B • Updated Aug 13 • 2

AaronHuangWei/Qwen3-8B-DAPO

AaronHuangWei/Qwen2.5-7B-GSM8k

AaronHuangWei/Qwen3-8B-GSM8k

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

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

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