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
- Multimodal Models : CLIP, StableDiffusion, Qwen2.5-VL-3B, InternelVL3-2B, Janus-Pro-1B
- Vision Models : Ultralytics, Depth-Anything-V2, MixFormerV2, LivePortrait, Real-ESRGAN
- Audio Models : Whisper, SenseVoice, MeloTTS, Demucs
- Tools : Pulsar2
Other
models
62
AXERA-TECH/SuperResolution
Image-to-Image
•
Updated
AXERA-TECH/DeepSeek-R1-Distill-Qwen-7B
Updated
•
12
•
1
AXERA-TECH/DeepSeek-R1-Distill-Qwen-1.5B
Text Generation
•
Updated
•
32
•
5
AXERA-TECH/LibCLIP
Zero-Shot Image Classification
•
Updated
•
34
AXERA-TECH/Qwen2.5-7B-Instruct
Text Generation
•
Updated
•
17
•
1
AXERA-TECH/Pulsar2
Updated
•
6
•
5
AXERA-TECH/InternVL3-1B
Image-Text-to-Text
•
Updated
•
15
AXERA-TECH/ViT-L-14-336-CN__axera
Updated
•
10
AXERA-TECH/ViT-L-14-336__axera
Updated
•
2
AXERA-TECH/Qwen2.5-VL-3B-Instruct
Image-Text-to-Text
•
Updated
•
23
datasets
0
None public yet