Image-Text-to-Text
Transformers
Safetensors
multilingual
deepseek_vl_v2
feature-extraction
deepseek
vision-language
ocr
custom_code
Eval Results
Instructions to use deepseek-ai/DeepSeek-OCR-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepseek-ai/DeepSeek-OCR-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="deepseek-ai/DeepSeek-OCR-2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("deepseek-ai/DeepSeek-OCR-2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use deepseek-ai/DeepSeek-OCR-2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "deepseek-ai/DeepSeek-OCR-2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/DeepSeek-OCR-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/deepseek-ai/DeepSeek-OCR-2
- SGLang
How to use deepseek-ai/DeepSeek-OCR-2 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 "deepseek-ai/DeepSeek-OCR-2" \ --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": "deepseek-ai/DeepSeek-OCR-2", "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 "deepseek-ai/DeepSeek-OCR-2" \ --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": "deepseek-ai/DeepSeek-OCR-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use deepseek-ai/DeepSeek-OCR-2 with Docker Model Runner:
docker model run hf.co/deepseek-ai/DeepSeek-OCR-2
Add Real5-OmniDocBench evaluation results for Deepseek-OCR 2
Browse files# Real5-OmniDocBench evaluation results for Deepseek-OCR 2
This PR adds the evaluation file for Deepseek-OCR 2 under the Hugging Face
evaluation-results workflow.
This is based on the new evaluation results feature: https://huggingface.co/docs/hub/eval-results.
## Dataset
- [PaddlePaddle/Real5-OmniDocBench](https://huggingface.co/datasets/PaddlePaddle/Real5-OmniDocBench)
## File
- `.eval_results/real5_omnidocbench.yaml`
## Tasks
- overall
- scanning
- warping
- screen_photography
- illumination
- skew
.eval_results/real5_omnidocbench.yaml
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: PaddlePaddle/Real5-OmniDocBench
|
| 3 |
+
task_id: overall
|
| 4 |
+
value: 73.01
|
| 5 |
+
source:
|
| 6 |
+
url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
|
| 7 |
+
name: Real5-OmniDocBench leaderboard data
|
| 8 |
+
user: PaddlePaddle
|
| 9 |
+
notes: Deepseek-OCR 2; official Real5-OmniDocBench result
|
| 10 |
+
- dataset:
|
| 11 |
+
id: PaddlePaddle/Real5-OmniDocBench
|
| 12 |
+
task_id: scanning
|
| 13 |
+
value: 89.59
|
| 14 |
+
source:
|
| 15 |
+
url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
|
| 16 |
+
name: Real5-OmniDocBench leaderboard data
|
| 17 |
+
user: PaddlePaddle
|
| 18 |
+
notes: Deepseek-OCR 2; official Real5-OmniDocBench result
|
| 19 |
+
- dataset:
|
| 20 |
+
id: PaddlePaddle/Real5-OmniDocBench
|
| 21 |
+
task_id: warping
|
| 22 |
+
value: 66.53
|
| 23 |
+
source:
|
| 24 |
+
url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
|
| 25 |
+
name: Real5-OmniDocBench leaderboard data
|
| 26 |
+
user: PaddlePaddle
|
| 27 |
+
notes: Deepseek-OCR 2; official Real5-OmniDocBench result
|
| 28 |
+
- dataset:
|
| 29 |
+
id: PaddlePaddle/Real5-OmniDocBench
|
| 30 |
+
task_id: screen_photography
|
| 31 |
+
value: 71.65
|
| 32 |
+
source:
|
| 33 |
+
url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
|
| 34 |
+
name: Real5-OmniDocBench leaderboard data
|
| 35 |
+
user: PaddlePaddle
|
| 36 |
+
notes: Deepseek-OCR 2; official Real5-OmniDocBench result
|
| 37 |
+
- dataset:
|
| 38 |
+
id: PaddlePaddle/Real5-OmniDocBench
|
| 39 |
+
task_id: illumination
|
| 40 |
+
value: 76.02
|
| 41 |
+
source:
|
| 42 |
+
url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
|
| 43 |
+
name: Real5-OmniDocBench leaderboard data
|
| 44 |
+
user: PaddlePaddle
|
| 45 |
+
notes: Deepseek-OCR 2; official Real5-OmniDocBench result
|
| 46 |
+
- dataset:
|
| 47 |
+
id: PaddlePaddle/Real5-OmniDocBench
|
| 48 |
+
task_id: skew
|
| 49 |
+
value: 61.28
|
| 50 |
+
source:
|
| 51 |
+
url: https://paddle-model-ecology.bj.bcebos.com/PPOCRVL/AIStudio/real5_omnidocbench/leaderboard_data.json
|
| 52 |
+
name: Real5-OmniDocBench leaderboard data
|
| 53 |
+
user: PaddlePaddle
|
| 54 |
+
notes: Deepseek-OCR 2; official Real5-OmniDocBench result
|