Image-Text-to-Text
Transformers
Safetensors
Vietnamese
English
Chinese
internvl_chat
feature-extraction
conversational
custom_code
Instructions to use 5CD-AI/Vintern-3B-R-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 5CD-AI/Vintern-3B-R-beta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="5CD-AI/Vintern-3B-R-beta", 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)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("5CD-AI/Vintern-3B-R-beta", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use 5CD-AI/Vintern-3B-R-beta with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "5CD-AI/Vintern-3B-R-beta" # 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-3B-R-beta", "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-3B-R-beta
- SGLang
How to use 5CD-AI/Vintern-3B-R-beta 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-3B-R-beta" \ --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-3B-R-beta", "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-3B-R-beta" \ --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-3B-R-beta", "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-3B-R-beta with Docker Model Runner:
docker model run hf.co/5CD-AI/Vintern-3B-R-beta
Update README.md
Browse files
README.md
CHANGED
|
@@ -62,5 +62,49 @@ iá cao nhất là Lầu bò với giá 69k.</REASONING>
|
|
| 62 |
```
|
| 63 |
|
| 64 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
..............
|
| 66 |
..............
|
|
|
|
| 62 |
```
|
| 63 |
|
| 64 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
<div align="center">
|
| 69 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/msklqHxFL0JTRw_Yf7LhQ.jpeg" width="300"/>
|
| 70 |
+
</div>
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
```
|
| 74 |
+
User: <image>
|
| 75 |
+
Liệt kê toàn bộ văn bản.
|
| 76 |
+
Assistant: CHÍNH PHỦ
|
| 77 |
+
Số: 626/QĐ-TTg
|
| 78 |
+
CỘNG HÒA XÃ HỘI CHỦ NGHĨA VIỆT NAM
|
| 79 |
+
Độc lập - Tự do - Hạnh phúc
|
| 80 |
+
Hà Nội, ngày 29 tháng 7 năm 2002
|
| 81 |
+
QUYẾT ĐỊNH CỦA THỦ TƯỚNG CHÍNH PHỦ
|
| 82 |
+
Phê duyệt Báo cáo nghiên cứu khả thi dự án đầu tư
|
| 83 |
+
Nhà máy sản xuất phân bón diamôn phốt phát (DAP) tại khu
|
| 84 |
+
Kinh tế Đình Vũ, thành phố Hải Phòng
|
| 85 |
+
THỦ TƯỚNG (CHÍNH PHỦ)
|
| 86 |
+
Căn cứ Luật Tổ chức Chính phủ ngày 25 tháng 12 năm 2001;
|
| 87 |
+
Căn cứ Nghị định số 52/1999/NĐ-CP ngày 8 tháng 7 năm 1999 của Chính phủ
|
| 88 |
+
ban hành (Quy chế quản lý đầu tư và xây dựng và Ngành dịch số 12/2000/ND-CP
|
| 89 |
+
ngày 05 tháng 5 năm 2000) của Chính phủ quy định sửa đổi, bổ sung một số
|
| 90 |
+
điều của Quy chế quản lý đầu tư và xây dựng.
|
| 91 |
+
Xét đề nghị của Tổng công ty Hoá chất Việt Nam (công văn số 916/ CV-HĐQT
|
| 92 |
+
ngày 01 tháng 11 năm 2001), ý kiến thẩm định của Bộ Kế hoạch và Đầu tư tại
|
| 93 |
+
công văn số 1944 BKH/VPTD ngày 01 tháng 4 năm 2002, về việc phê duyệt
|
| 94 |
+
Báo cáo nghiên cứu khả thi dự án đầu tư Nhà máy sản xuất phân bón diamôn
|
| 95 |
+
phốt phát tại khu kinh tế Đình Vũ, thành phố Hải Phòng và ý kiến của các Bộ,
|
| 96 |
+
ngành tại cuộc họp ngày 19 tháng 6 năm 2002,
|
| 97 |
+
QUYẾT ĐỊNH:
|
| 98 |
+
Điều 1. Phê duyệt Báo cáo nghiên cứu khả thi dự án đầu tư Nhà máy sản
|
| 99 |
+
xuất phân bón DAP tại khu kinh tế Đình Vũ, thành phố Hải Phòng với các nội
|
| 100 |
+
dung chính sau :
|
| 101 |
+
1. Tên dự án : Nhà máy sản xuất phân bón DAP tại khu kinh tế Đình Vũ,
|
| 102 |
+
thành phố Hải Phòng.
|
| 103 |
+
2. Mục tiêu đầu tư: góp phần đảm bảo ổn định và chủ động trong việc cung
|
| 104 |
+
cấp phân bón DAP cho phát triển nông nghiệp, hạn chế nhập khẩu, sử dụng có
|
| 105 |
+
hiệu quả hơn nguồn tài nguyên quặng apatit trong nước.
|
| 106 |
+
3. Chủ đầu tư : Tổng công ty Hoá chất Việt Nam.
|
| 107 |
+
```
|
| 108 |
+
|
| 109 |
..............
|
| 110 |
..............
|