AI & ML interests
Edge AI Compute, CNN, Visual Transformer, LLM, VLM
Recent Activity
Organization Card
AXera Models Research
This is the home for Axera's npu model(axmodel) and npu's tools (Pulsar2). We released(such as):
- MiniCPM4 : MiniCPM4-0.5B
- Qwen3 : Qwen3-0.6B, Qwen3-1.7B, Qwen3-4B
- Qwen2.5 : Qwen2.5-0.5B, Qwen2.5-1.5B, Qwen2.5-3B, Qwen2.5-7B
- DeepSeek
- HuggingFaceTB : SmolLM, SmolVLM, SmolVLM2
- Multimodal Models : CLIP, JinaCLIP, StableDiffusion, Qwen3-VL-2B/4B, Qwen2.5-VL-3B/7B, InternelVL3-1B/2B, Janus-Pro-1B, MiniCPM4-V
- Vision Models : Ultralytics, Depth-Anything-V2, MixFormerV2, LivePortrait, Real-ESRGAN
- Audio Models : Whisper, SenseVoice, CosyVoice2, MeloTTS, FireRed-AED, SileroVAD
Solution
- Frigate NVR : AI NVR solution, support AX650 and AXCL
- Immich : High performance self-hosted photo and video management solution
Tools
- Pulsar2 : The NPU Toolchain for AX650/AX8850, AX630C/AX620Q, AX615, AX637
- PPQ-XS : The NPU Toolchain for AX520/AX513
Other
models
90
AXERA-TECH/DeOldify
Image-to-Image
•
Updated
AXERA-TECH/FG-CLIP
Updated
AXERA-TECH/Qwen3-VL-2B-Instruct-GPTQ-Int4
Image-Text-to-Text
•
Updated
•
46
AXERA-TECH/SileroVAD
Updated
•
39
•
1
AXERA-TECH/Qwen2.5-1.5B-Instruct
Text Generation
•
Updated
•
24
AXERA-TECH/Qwen2.5-1.5B-Instruct-python
Text Generation
•
Updated
AXERA-TECH/Qwen3-VL-4B-Instruct-GPTQ-Int4
Image-Text-to-Text
•
Updated
•
46
AXERA-TECH/Qwen3-VL-4B-Instruct
Image-Text-to-Text
•
Updated
•
22
AXERA-TECH/Qwen3-VL-2B-Instruct
Image-Text-to-Text
•
Updated
•
32
AXERA-TECH/MeloTTS
Text-to-Speech
•
Updated
•
25
•
1
datasets
0
None public yet