Total runs:
1.2K
Run Growth:
-506
Growth Rate:
-41.82%
Sponsored by
AdsCreator.com
AXERA-TECH / InternVL3-2B
Model's Last Updated: September 25 2025
visual-question-answering
Introduction of InternVL3-2B
Model Details of InternVL3-2B
InternVL3-2B-Int8
This version of InternVL3-2B has been converted to run on the Axera NPU using w8a16 quantization.
This model has been optimized with the following LoRA:
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/deepseek-ai/InternVL3-2B
Support Platform
- AX650
| chips | image encoder 448 | ttft | w8a16 |
|---|---|---|---|
| AX650 | 364.870 ms | 4588.79 ms | 11.50 tokens/sec |
How to use
Download all files from this repository to the device.
Using AX650 Board
root@ax650 ~/yongqiang/push_hugging_face/InternVL3-2B # tree -L 1
.
├── config.json
├── examples
├── infer.py
├── internvl3_2b_axmodel
├── internvl3_2b_tokenizer
├── README.md
└── vit_axmodel
4 directories, 3 files
Inference with AX650 Host, such as M4N-Dock(爱芯派Pro) or AX650N DEMO Board
Text Generation
input text:
Please calculate the derivative of the function [y=2x^ 2-2] and provide the reasoning process in markdown format.
log information:
root@ax650 ~/yongqiang/push_hugging_face/InternVL3-2B # python3 infer.py --hf_model internvl3_2b_tokenizer/ --axmodel_path internvl3_2b_axmodel/ --question "Please calculate the derivative of the function [y=2x^ 2-2] and provide the reasoning process in markdown format"
Init InferenceSession: 100%|██████████████████████████████████████████████████████████| 28/28 [00:16<00:00, 1.74it/s]
model load done!
prefill token_len: 85
slice_indexs is [0]
slice prefill done 0
Decode: 9%|██████▎ | 232/2559 [00:19<05:14, 7.39it/s]Decode: 17%|████████████ | 440/2559 [00:48<04:51, 7.26it/s]hit eos!
Decode: 17%|████████████ | 440/2559 [00:48<03:53, 9.06it/s]
Certainly! Let's calculate the derivative of the function \( y = 2x^2 - 2 \ \ using the rules of differentiation.
### Step-by-Step Reasoning:
1. **Identify the Function:**
The given function is \( y = 2x^2 - 2 \\).
2. **Differentiate Term by Term:**
We will differentiate each term of the function separately.
- **First Term: \( 2x^2 \ \**
- The derivative of \( x^n \ \ (where n is a constant) is \( nx^{n-1} \ \).
- Here, \( n = 2 \ \.
- Therefore, the derivative of \( 2x^2 \ \ is \( 2 \ \ times \( 2x^{2-1} \ \ which simplifies to \( 4x \ \.
- **Second Term: \( -2 \ \**
- The derivative of a constant (a term without \( x \\ is 0 \.
- Therefore, the derivative of \( -2 \ \ is \( 0 \.
3. **Combine the Derivatives:**
- The derivative of the entire function is the sum of the derivatives of each term.
- So, the derivative of \( y = 2x^2 - 2 \\ is \( 4x + 0 \\ which simplifies to \( 4x \.
### Final Answer:
The derivative of the function \( y = 2x^2 - 2 \ is \( 4x \.
### Summary:
The derivative of \( y = 2x^2 - 2 \ is \( 4x \.
Multimodal Understanding
- input image
input text:
"Please describe this picture in detail."
log information:
root@ax650 ~/yongqiang/push_hugging_face/InternVL3-2B # python3 infer.py --hf_model internvl3_2b_tokenizer/ --axmodel_path internvl3_2b_axmodel/ --question "Please describe this picture in detail" -i examples/image_1.jpg --vit_model vit_axmodel/internvl3_2b_vit_slim.axmodel
[INFO] Available providers: ['AxEngineExecutionProvider']
Init InferenceSession: 0%| | 0/24 [00:00<?, ?it/s][INFO] Chip type: ChipType.MC50
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Engine version: 2.11.0a
Init InferenceSession: 100%|██████████████████████████████████████████████████████████| 28/28 [00:14<00:00, 1.92it/s]
model load done!
prefill token_len: 325
slice_indexs is [0, 1, 2]
slice prefill done 0
slice prefill done 1
slice prefill done 2
Decode: 13%|████████▋ | 326/2559 [00:00<00:01, 1829.15it/s]Decode: 19%|█████████████▍ | 489/2559 [00:22<02:26, 14.17it/s]hit eos!
Decode: 20%|██████████████▏ | 517/2559 [00:26<01:43, 19.71it/s]
**Image Description:**
The image depicts a giant panda in a naturalistic enclosure, likely within a zoo or wildlife sanctuary. The panda is prominently positioned in the foreground, surrounded by lush green bamboo plants. Its distinctive black and white fur is clearly visible, with the panda's face, ears, and limbs being black, while its body and the rest of its face are white. The panda appears to be eating bamboo, with its front paws holding a piece of bamboo close to its mouth. The panda's expression is calm and curious, with its eyes looking directly at the camera.
In the background, there is another panda partially obscured by the foliage and a wooden structure, possibly part of the enclosure's design. The ground is covered with a layer of mulch or wood chips, providing a naturalistic habitat for the pandas. The overall setting is serene and well-maintained, designed to mimic the panda's natural habitat while ensuring the animals' well-being.
Runs of AXERA-TECH InternVL3-2B on huggingface.co
37
Total runs
-3
24-hour runs
-5
3-day runs
-9
7-day runs
8
30-day runs
More Information About InternVL3-2B huggingface.co Model
Url of InternVL3-2B
InternVL3-2B huggingface.co Url
Provider of InternVL3-2B huggingface.co
Other API from AXERA-TECH
Updated:August 26 2026
Total runs:
207
Run Growth:
69
Growth Rate:
33.33%
Total runs:
192
Run Growth:
-311
Growth Rate:
-161.98%
Total runs:
98
Run Growth:
-366
Growth Rate:
-373.47%
Total runs:
68
Run Growth:
60
Growth Rate:
88.24%
Total runs:
61
Run Growth:
22
Growth Rate:
36.07%
Total runs:
56
Run Growth:
56
Growth Rate:
100.00%
Total runs:
48
Run Growth:
26
Growth Rate:
54.17%
Total runs:
48
Run Growth:
25
Growth Rate:
52.08%
Total runs:
46
Run Growth:
4
Growth Rate:
8.70%
Total runs:
44
Run Growth:
14
Growth Rate:
31.82%
Total runs:
44
Run Growth:
-1
Growth Rate:
-2.27%
Total runs:
44
Run Growth:
-1
Growth Rate:
-2.27%
Total runs:
43
Run Growth:
15
Growth Rate:
34.88%
Total runs:
42
Run Growth:
26
Growth Rate:
61.90%
Total runs:
41
Run Growth:
12
Growth Rate:
29.27%
Total runs:
41
Run Growth:
28
Growth Rate:
68.29%
Total runs:
40
Run Growth:
-197
Growth Rate:
-492.50%
Total runs:
39
Run Growth:
-9
Growth Rate:
-23.08%
Total runs:
38
Run Growth:
13
Growth Rate:
34.21%
Total runs:
36
Run Growth:
20
Growth Rate:
55.56%
Total runs:
36
Run Growth:
5
Growth Rate:
13.89%
Total runs:
35
Run Growth:
11
Growth Rate:
31.43%
Total runs:
33
Run Growth:
25
Growth Rate:
75.76%
Total runs:
33
Run Growth:
22
Growth Rate:
66.67%
Total runs:
33
Run Growth:
-39
Growth Rate:
-118.18%
Total runs:
32
Run Growth:
12
Growth Rate:
37.50%
Total runs:
32
Run Growth:
10
Growth Rate:
31.25%
Total runs:
32
Run Growth:
1
Growth Rate:
3.13%
Total runs:
32
Run Growth:
-1
Growth Rate:
-3.13%
Total runs:
31
Run Growth:
30
Growth Rate:
100.00%
Total runs:
31
Run Growth:
11
Growth Rate:
35.48%
Total runs:
31
Run Growth:
5
Growth Rate:
16.13%
Total runs:
31
Run Growth:
13
Growth Rate:
41.94%
Total runs:
30
Run Growth:
7
Growth Rate:
23.33%
Total runs:
30
Run Growth:
18
Growth Rate:
60.00%
Total runs:
30
Run Growth:
12
Growth Rate:
40.00%
Total runs:
28
Run Growth:
-16
Growth Rate:
-57.14%
Total runs:
28
Run Growth:
0
Growth Rate:
0.00%
Total runs:
28
Run Growth:
7
Growth Rate:
25.00%
Total runs:
28
Run Growth:
18
Growth Rate:
64.29%
Total runs:
28
Run Growth:
12
Growth Rate:
42.86%
Total runs:
27
Run Growth:
15
Growth Rate:
55.56%
Total runs:
26
Run Growth:
-34
Growth Rate:
-130.77%
Total runs:
26
Run Growth:
2
Growth Rate:
7.69%
Total runs:
24
Run Growth:
16
Growth Rate:
66.67%
Total runs:
24
Run Growth:
4
Growth Rate:
16.67%
Total runs:
24
Run Growth:
11
Growth Rate:
45.83%
Total runs:
23
Run Growth:
0
Growth Rate:
0.00%
Total runs:
23
Run Growth:
8
Growth Rate:
34.78%
Total runs:
23
Run Growth:
16
Growth Rate:
69.57%
Total runs:
22
Run Growth:
13
Growth Rate:
59.09%
Total runs:
22
Run Growth:
13
Growth Rate:
59.09%