AXERA-TECH/Qwen2.5-Omni-3B
By AXERA-TECH · ↓ 0 · ♥ 0 · Updated 2025-08-05
What's in this repo
This page lists the files in AXERA-TECH/Qwen2.5-Omni-3B, including thinker_to_talker_proj_decode.onnx, thinker_to_talker_proj_prefill_512.onnx.
- 2 ONNX models (.onnx files)
- 109 files, including 66 .axmodel, 22 .json, 7 .py, 4 .bin, 2 .txt, 2 .npy
- Last updated 2025-08-05
ONNX files
| File | Size | Download |
|---|---|---|
| Qwen2.5-Omni-3B-AX650-talker-chunk_prefill_512/thinker_to_talker_proj_decode.onnx | — | Download |
| Qwen2.5-Omni-3B-AX650-talker-chunk_prefill_512/thinker_to_talker_proj_prefill_512.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
license: mit language:
- en
- zh base_model:
- Qwen/Qwen2.5-Omni-3B pipeline_tag: image-text-to-text library_name: transformers tags:
- Qwen2.5-Omni
- Qwen2.5-Omni-3B
- Int8
- Omni
Qwen2.5-Omni-3B
This version of Qwen2.5-Omni-3B has been converted to run on the Axera NPU using w8a16 quantization.
Compatible with Pulsar2 version: 3.4
Convert tools links:
For those who are interested in model conversion, you can try to export axmodel through the original repo : https://huggingface.co/Qwen/Qwen2.5-Omni-3B
Pulsar2 Link, How to Convert LLM from Huggingface to axmodel
Support Platform
- AX650
- AX650N DEMO Board
- M4N-Dock(爱芯派Pro)
- M.2 Accelerator card
Audio Process 待补充
Image Process 待补充
Video Process 待补充
The DDR capacity refers to the CMM memory that needs to be consumed. Ensure that the CMM memory allocation on the development board is greater than this value.
How to use
Download all files from this repository to the device
If you using AX650 Board
(base) lihongjie@ai-dev1:~/axera-tech/Qwen2.5-Omni-3B$ tree -L 2
.
├── python
│ ├── modeling_axinfer.py
│ ├── preprocess.py
│ ├── run_axinfer.py
│ ├── utils_axinfer.py
│ ├── utils_lm.py
│ ├── utils.py
│ └── utils_vl.py
├── Qwen2.5-Omni-3B-AX650-talker-chunk_prefill_512
│ ├── config.json
│ ├── qwen2_5_omni_talker_p128_l0_together.axmodel
......
│ ├── qwen2_5_omni_talker_post.axmodel
│ ├── special_tokens_map.json
│ ├── spk_dict.pt
│ ├── thinker_to_talker_proj_decode.axmodel
│ ├── thinker_to_talker_proj_prefill_512.axmodel
│ ├── token2wav_bigvgan.axmodel
│ ├── token2wav_dit.axmodel
│ ├── tokenizer_config.json
│ ├── tokenizer.json
│ └── vocab.json
├── Qwen2.5-Omni-3B-AX650-thinker-chunk_prefill_512
│ ├── config.json
......
│ ├── Qwen2.5-Omni-3B_vision.axmodel
│ ├── qwen2_5_omni_text_p128_l0_together.axmodel
......
│ ├── qwen2_5_omni_text_post.axmodel
├── README.md
└── videos
Demo
运行命令
cd python
python3 run_axinfer.py
output
text
It's a Nord Electro 6 keyboard. It's a really popular one. It has a lot of features like different sounds and effects. Have you played with it much?
audio
Model info
Created: 2025-08-01
Updated: 2025-08-05
View on Hugging Face