AaronHuangWei/Wan2.1-I2V-14B-480P-INT8FakeQuant-per_tensor
Image-to-Video • 16B • Updated • 38
Wei Huang
AaronHuangWei
AI & ML interests
Deep Learning; Efficient AI; Quantization; LLMs
Recent Activity
updated a collection about 19 hours ago
Long-WAM updated a collection about 19 hours ago
Long-WAM updated a collection about 19 hours ago
Long-WAMOrganizations
AaronHuangWei/grpo_edit_qwen2.5-vl-7b_step310_v2
8B • Updated • 8
AaronHuangWei/grpo_edit_qwen2.5-vl-7b_step120_v2
8B • Updated • 15
AaronHuangWei/Llama-3.1-Nemotron-Nano-8B-v1-NVFP4A16
5B • Updated • 23
AaronHuangWei/qwen2.5-32B-Instruct-bigmath_awq-nvfp4-fake-ckpt_450
33B • Updated • 15
AaronHuangWei/qwen2.5-32B-Instruct-bigmath_awq-nvfp4-fake-ckpt_380
33B • Updated • 18
AaronHuangWei/qwen2.5-32B-Instruct-bigmath_awq-nvfp4-fake-ckpt_290
33B • Updated • 19
AaronHuangWei/qwen2.5-3B-Instruct-bigmath_awq-nvfp4-fake-ckpt_290
Updated
AaronHuangWei/qwen2.5-3B-Instruct-bigmath_lora_ckpt_320
33B • Updated • 6
AaronHuangWei/qwen2.5-3B-Instruct-awq-int4-fake
3B • Updated • 4
AaronHuangWei/qwen2.5-32B-Instruct-awq-nvfp4-fake
33B • Updated • 24
AaronHuangWei/Qwen2.5-7B-Instruct-bnb-4bit
Text Generation • 7B • Updated • 17
AaronHuangWei/Qwen2.5-14B-Instruct-bnb-4bit
Text Generation • 14B • Updated • 17
AaronHuangWei/Qwen2.5-7B-GRPO-MATH500-lora32
Updated
AaronHuangWei/Qwen2.5-7B-Instruct-GRPO-MATH500-qlora32
Updated
AaronHuangWei/Qwen2.5-14B-GRPO-MATH500-lora32
Updated
AaronHuangWei/Qwen2.5-14B-GRPO-MATH500-lora64
Updated
AaronHuangWei/Qwen3-14B-GRPO-MATH500-lora64
Updated
AaronHuangWei/Qwen2.5-7B-GRPO-MATH500-qlora64
Updated
AaronHuangWei/Qwen2.5-7B-GRPO-MATH500-lora64
Updated
AaronHuangWei/Qwen2.5-7B-GRPO-MATH500
Text Generation • 8B • Updated • 15
AaronHuangWei/Qwen2.5-7B-GRPO-GSM8K
Updated
AaronHuangWei/Qwen2.5-7B-GRPO
Text Generation • 8B • Updated • 16
AaronHuangWei/Qwen2.5-7B-DAPO
Text Generation • 8B • Updated • 13
AaronHuangWei/Qwen3-8B-DAPO
Updated
AaronHuangWei/Qwen2.5-7B-GSM8k
Updated
AaronHuangWei/Qwen3-8B-GSM8k
Updated
AaronHuangWei/Qwen2.5-7B-GRPO-GSM8k-GRPO
Updated
AaronHuangWei/Qwen2.5-7B-DAPO-Math-GRPO
Updated
AaronHuangWei/Qwen2.5-3B-Open-R1-Math-GRPO
Updated