Instructions to use AXERA-TECH/InternVL3_5-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AXERA-TECH/InternVL3_5-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="AXERA-TECH/InternVL3_5-1B")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AXERA-TECH/InternVL3_5-1B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AXERA-TECH/InternVL3_5-1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AXERA-TECH/InternVL3_5-1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AXERA-TECH/InternVL3_5-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AXERA-TECH/InternVL3_5-1B
- SGLang
How to use AXERA-TECH/InternVL3_5-1B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "AXERA-TECH/InternVL3_5-1B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AXERA-TECH/InternVL3_5-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "AXERA-TECH/InternVL3_5-1B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AXERA-TECH/InternVL3_5-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AXERA-TECH/InternVL3_5-1B with Docker Model Runner:
docker model run hf.co/AXERA-TECH/InternVL3_5-1B
yongqiang commited on
Commit ·
ead75a3
1
Parent(s): e160560
Update README
Browse files
README.md
CHANGED
|
@@ -96,7 +96,6 @@ Image understanding:
|
|
| 96 |
Run the following command on the Axera board to start a chat conversation:
|
| 97 |
|
| 98 |
```sh
|
| 99 |
-
$ cd InternVL3_5-1B.axera/python
|
| 100 |
$ python3 infer_axmodel.py --hf_model internvl3-5_tokenizer/ --axmodel_path internvl3-5_axmodel/ --question "请计算函数[y=2x^2+2]的导数, 并提供 markdown 格式的推理过程"
|
| 101 |
```
|
| 102 |
|
|
@@ -129,7 +128,6 @@ y' = 4x
|
|
| 129 |
Enter the following command to perform the single-image understanding task:
|
| 130 |
|
| 131 |
```sh
|
| 132 |
-
$ cd InternVL3_5-1B.axera/python
|
| 133 |
$ python3 infer_axmodel.py --hf_model internvl3-5_tokenizer/ --axmodel_path internvl3-5_axmodel/ --question "请描述这幅图" -i examples/image_0.jpg --vit_model vit-models/internvl_vit_model_1x3x448x448.axmodel
|
| 134 |
```
|
| 135 |
|
|
|
|
| 96 |
Run the following command on the Axera board to start a chat conversation:
|
| 97 |
|
| 98 |
```sh
|
|
|
|
| 99 |
$ python3 infer_axmodel.py --hf_model internvl3-5_tokenizer/ --axmodel_path internvl3-5_axmodel/ --question "请计算函数[y=2x^2+2]的导数, 并提供 markdown 格式的推理过程"
|
| 100 |
```
|
| 101 |
|
|
|
|
| 128 |
Enter the following command to perform the single-image understanding task:
|
| 129 |
|
| 130 |
```sh
|
|
|
|
| 131 |
$ python3 infer_axmodel.py --hf_model internvl3-5_tokenizer/ --axmodel_path internvl3-5_axmodel/ --question "请描述这幅图" -i examples/image_0.jpg --vit_model vit-models/internvl_vit_model_1x3x448x448.axmodel
|
| 132 |
```
|
| 133 |
|