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, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- 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 OlmOCRBench evaluation results
Browse filesThis PR ensures your model shows up at https://huggingface.co/datasets/allenai/olmOCR-bench.
This is based on the new evaluation results feature: https://huggingface.co/docs/hub/eval-results.
.eval_results/olmocrbench.yaml
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: allenai/olmOCR-bench
|
| 3 |
+
task_id: arxiv_math
|
| 4 |
+
value: 82.0
|
| 5 |
+
source:
|
| 6 |
+
url: https://x.com/staghado/status/2016161372938117205/photo/1
|
| 7 |
+
name: Tweet by @staghado
|
| 8 |
+
user: nielsr
|
| 9 |
+
- dataset:
|
| 10 |
+
id: allenai/olmOCR-bench
|
| 11 |
+
task_id: old_scans_math
|
| 12 |
+
value: 72.0
|
| 13 |
+
source:
|
| 14 |
+
url: https://x.com/staghado/status/2016161372938117205/photo/1
|
| 15 |
+
name: Tweet by @staghado
|
| 16 |
+
user: nielsr
|
| 17 |
+
- dataset:
|
| 18 |
+
id: allenai/olmOCR-bench
|
| 19 |
+
task_id: table_tests
|
| 20 |
+
value: 77.4
|
| 21 |
+
source:
|
| 22 |
+
url: https://x.com/staghado/status/2016161372938117205/photo/1
|
| 23 |
+
name: Tweet by @staghado
|
| 24 |
+
user: nielsr
|
| 25 |
+
- dataset:
|
| 26 |
+
id: allenai/olmOCR-bench
|
| 27 |
+
task_id: old_scans
|
| 28 |
+
value: 33.8
|
| 29 |
+
source:
|
| 30 |
+
url: https://x.com/staghado/status/2016161372938117205/photo/1
|
| 31 |
+
name: Tweet by @staghado
|
| 32 |
+
user: nielsr
|
| 33 |
+
- dataset:
|
| 34 |
+
id: allenai/olmOCR-bench
|
| 35 |
+
task_id: multi_column
|
| 36 |
+
value: 79.0
|
| 37 |
+
source:
|
| 38 |
+
url: https://x.com/staghado/status/2016161372938117205/photo/1
|
| 39 |
+
name: Tweet by @staghado
|
| 40 |
+
user: nielsr
|
| 41 |
+
- dataset:
|
| 42 |
+
id: allenai/olmOCR-bench
|
| 43 |
+
task_id: long_tiny_text
|
| 44 |
+
value: 90.7
|
| 45 |
+
source:
|
| 46 |
+
url: https://x.com/staghado/status/2016161372938117205/photo/1
|
| 47 |
+
name: Tweet by @staghado
|
| 48 |
+
user: nielsr
|