Instructions to use 5CD-AI/Vintern-1B-v3_5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 5CD-AI/Vintern-1B-v3_5 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="5CD-AI/Vintern-1B-v3_5", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("5CD-AI/Vintern-1B-v3_5", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 5CD-AI/Vintern-1B-v3_5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "5CD-AI/Vintern-1B-v3_5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "5CD-AI/Vintern-1B-v3_5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/5CD-AI/Vintern-1B-v3_5

SGLang

How to use 5CD-AI/Vintern-1B-v3_5 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 "5CD-AI/Vintern-1B-v3_5" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "5CD-AI/Vintern-1B-v3_5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "5CD-AI/Vintern-1B-v3_5" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "5CD-AI/Vintern-1B-v3_5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use 5CD-AI/Vintern-1B-v3_5 with Docker Model Runner:
```
docker model run hf.co/5CD-AI/Vintern-1B-v3_5
```

khang119966 commited on Jan 12, 2025

Commit

01d21d9

verified ·

1 Parent(s): fd0ddc6

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -39

README.md CHANGED Viewed

@@ -10,16 +10,19 @@ base_model:
 pipeline_tag: image-text-to-text
 ---
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/-G297bBqMzYvTbD6_Bkd9.png)
 # Vintern-1B-v3.5 ❄️ (Viet-InternVL2-1B-v3.5) - The Ultimate Multimodal Solution 🌏
 We introduce **Vintern-1B-v3.5**, the latest version in the Vintern series, offering significant improvements over v2 across all evaluation benchmarks. This model has been fine-tuned from **InternVL-1B-2.5**, which already good in Vietnamese tasks because it used [Viet-ShareGPT-4o-Text-VQA](https://huggingface.co/datasets/5CD-AI/Viet-ShareGPT-4o-Text-VQA) data during its fine-tuning process by the InternVL 2.5 [1] team.
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/a1V1DA1o4Gf_MJblWTz-L.png)
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/36jb5bgyYCoVKx3NE8Iuv.png)
 To further enhance its performance in Vietnamese while maintaining robust capabilities on existing English datasets, **Vintern-1B-v3.5** has been fine-tuned using a vast amount of Vietnamese-specific data. This results in a model that is exceptionally powerful in text recognition, OCR, and understanding Vietnam-specific documents.
@@ -41,7 +44,9 @@ The model can be customized for specific tasks with minimal effort.
 ## Benchmarks 📈
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/DrUCZuXuMz47uVU4zqnJ4.png)
 | Benchmark     | InternVL2_5 1B | Vintern-1B-v2 | Vintern-1B-v3.5 |
 |:-------------:|:--------------:|:-------------:|:---------------:|
@@ -57,54 +62,26 @@ The model can be customized for specific tasks with minimal effort.
 ## Examples
 <div align="center">
-  <img src="ex_images/1.png" width="500"/>
 </div>
-```
-```
 <div align="center">
-  <img src="ex_images/4.jpg" width="500"/>
 </div>
-```
-```
 <div align="center">
-  <img src="ex_images/2.jpg" width="500"/>
 </div>
-```
-```
-<div align="center">
-  <img src="ex_images/3.png" width="400"/>
-</div>
-```
-```
 <div align="center">
-  <img src="ex_images/5.jpg" width="400"/>
 </div>
-```
-```
-<div align="center">
-  <img src="ex_images/6.png" width="400"/>
-</div>
-```
-```
 ## Quickstart
 Here provides a code snippet to show you how to load the tokenizer and model and how to generate contents.

 pipeline_tag: image-text-to-text
 ---
+<div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/-G297bBqMzYvTbD6_Bkd9.png" width="500"/>
+</div>
 # Vintern-1B-v3.5 ❄️ (Viet-InternVL2-1B-v3.5) - The Ultimate Multimodal Solution 🌏
 We introduce **Vintern-1B-v3.5**, the latest version in the Vintern series, offering significant improvements over v2 across all evaluation benchmarks. This model has been fine-tuned from **InternVL-1B-2.5**, which already good in Vietnamese tasks because it used [Viet-ShareGPT-4o-Text-VQA](https://huggingface.co/datasets/5CD-AI/Viet-ShareGPT-4o-Text-VQA) data during its fine-tuning process by the InternVL 2.5 [1] team.
+<div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/a1V1DA1o4Gf_MJblWTz-L.png" width="500"/>
+</div>
+<div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/36jb5bgyYCoVKx3NE8Iuv.png" width="500"/>
+</div>
 To further enhance its performance in Vietnamese while maintaining robust capabilities on existing English datasets, **Vintern-1B-v3.5** has been fine-tuned using a vast amount of Vietnamese-specific data. This results in a model that is exceptionally powerful in text recognition, OCR, and understanding Vietnam-specific documents.
 ## Benchmarks 📈
+<div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/DrUCZuXuMz47uVU4zqnJ4.png" width="500"/>
+</div>
 | Benchmark     | InternVL2_5 1B | Vintern-1B-v2 | Vintern-1B-v3.5 |
 |:-------------:|:--------------:|:-------------:|:---------------:|
 ## Examples
 <div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/1yos0APs6laTCAGhUbN9n.png" width="300"/>
 </div>
 <div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/L5n35_3sz_Wp9fo0C7snq.png" width="300"/>
 </div>
 <div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/E6aqBwFqK38XE1LL9lF2W.png" width="500"/>
 </div>
 <div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/Lkt8YLYlDP_VByFjFQX_t.png" width="500"/>
 </div>
 ## Quickstart
 Here provides a code snippet to show you how to load the tokenizer and model and how to generate contents.