happyme531's picture

Open to Work

happyme531

happyme531

·

happyme531

AI & ML interests

NPU-accelerated large model for edge devices. Need help? I offer freelance services for porting various deep learning models to RK35xx's NPU. email me at happyme5315@gmail.com. 需要模型部署帮助吗？我提供部署各种模型到RK35xx NPU的服务，邮件联系：happyme5315@gmail.com。

Recent Activity

new activity 9 days ago

AEON-7/Qwen3.6-35B-A3B-heretic-NVFP4:Image crash

updated a model 23 days ago

happyme531/whisper-large-v3-turbo-RKNN2

new activity 23 days ago

happyme531/whisper-large-v3-turbo-RKNN2:Hello, may I ask where the Qwen3-ASR-RKNN2 model mentioned in the post was published? I couldn't find it on your profile page.

View all activity

Organizations

None yet

New activity in AEON-7/Qwen3.6-35B-A3B-heretic-NVFP4 9 days ago

Image crash

#1 opened about 1 month ago by

New activity in happyme531/whisper-large-v3-turbo-RKNN2 23 days ago

Hello, may I ask where the Qwen3-ASR-RKNN2 model mentioned in the post was published? I couldn't find it on your profile page.

#2 opened 3 months ago by

New activity in happyme531/Stable-Diffusion-1.5-LCM-ONNX-RKNN2 about 2 months ago

fix: NHWC data_format for UNet/VAE decoder under librknnrt 2.3.2

#6 opened about 2 months ago by

New activity in happyme531/Qwen3-ASR-1.7B-RKLLM about 2 months ago

请问是否能开放导出脚本？

#1 opened about 2 months ago by

New activity in happyme531/classical-chinese-poetry-benchmark-70 2 months ago

[bot] Conversion to Parquet

#1 opened over 1 year ago by

parquet-converter

New activity in happyme531/YiMeng-JiangHu-WorldChat-1k 2 months ago

[bot] Conversion to Parquet

#1 opened 2 months ago by

parquet-converter

New activity in happyme531/VoxCPM1.5-RKNN2 2 months ago

请问在 RK3588 上的 RTF 能做到多少呢？

#1 opened 3 months ago by

New activity in happyme531/VoxCPM-0.5B-RKNN2 2 months ago

what's wrong

#1 opened 2 months ago by

New activity in happyme531/whisper-large-v3-turbo-RKNN2 2 months ago

Inquiry about the "Qwen3-ASR-RKNN2" project link

#1 opened 3 months ago by

New activity in happyme531/Qwen2.5-VL-3B-Instruct-RKLLM 4 months ago

运行提示：已杀死！

#1 opened 7 months ago by

New activity in happyme531/Stable-Diffusion-1.5-LCM-ONNX-RKNN2 7 months ago

Error Running

#4 opened 7 months ago by

New activity in fredzzp/open-dcoder-0.5B 9 months ago

AttributeError: 'Qwen2ForCausalLM' object has no attribute 'diffusion_generate'

#1 opened 9 months ago by

New activity in happyme531/FastVLM-1.5B-RKLLM 9 months ago

FastVLM-0.5B?

#1 opened 9 months ago by

New activity in happyme531/SenseVoiceSmall-RKNN2 12 months ago

您好，我在运行到最后一步flask_server.py时报错Segmentation fault

#1 opened 12 months ago by

New activity in happyme531/Florence-2-base-ft-ONNX-RKNN2 about 1 year ago

The model inference results are inconsistent with those from the Python Transformers version.

#2 opened about 1 year ago by

New activity in microsoft/Phi-4-multimodal-instruct about 1 year ago

`tokenizer.model` is missing

#30 opened about 1 year ago by

New activity in happyme531/Florence-2-base-ft-ONNX-RKNN2 about 1 year ago

Load model from vision_encoder.onnx failed:Protobuf parsing failed.

#1 opened over 1 year ago by

New activity in happyme531/MiniCPM-V-2_6-rkllm over 1 year ago

Segmentation fault

#7 opened over 1 year ago by

RK3588运行一直挂起

#5 opened over 1 year ago by

New activity in happyme531/rwkv-7-world-ONNX-RKNN2 over 1 year ago

Different behaviour..

#1 opened over 1 year ago by