Image-Text-to-Text
Transformers
Safetensors
multilingual
deepseek_vl_v2
feature-extraction
deepseek
vision-language
ocr
custom_code
Instructions to use tphage/DeepSeek-OCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tphage/DeepSeek-OCR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="tphage/DeepSeek-OCR", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("tphage/DeepSeek-OCR", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use tphage/DeepSeek-OCR with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tphage/DeepSeek-OCR" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tphage/DeepSeek-OCR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/tphage/DeepSeek-OCR
- SGLang
How to use tphage/DeepSeek-OCR 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 "tphage/DeepSeek-OCR" \ --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": "tphage/DeepSeek-OCR", "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 "tphage/DeepSeek-OCR" \ --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": "tphage/DeepSeek-OCR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use tphage/DeepSeek-OCR with Docker Model Runner:
docker model run hf.co/tphage/DeepSeek-OCR
Upload vllm-0.8.5+cu118-cp38-abi3-manylinux1_x86_64.whl with huggingface_hub
Browse files
.gitattributes
CHANGED
|
@@ -38,3 +38,4 @@ assets/show1.jpg filter=lfs diff=lfs merge=lfs -text
|
|
| 38 |
assets/show2.jpg filter=lfs diff=lfs merge=lfs -text
|
| 39 |
assets/show3.jpg filter=lfs diff=lfs merge=lfs -text
|
| 40 |
assets/show4.jpg filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 38 |
assets/show2.jpg filter=lfs diff=lfs merge=lfs -text
|
| 39 |
assets/show3.jpg filter=lfs diff=lfs merge=lfs -text
|
| 40 |
assets/show4.jpg filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
vllm-0.8.5+cu118-cp38-abi3-manylinux1_x86_64.whl filter=lfs diff=lfs merge=lfs -text
|
vllm-0.8.5+cu118-cp38-abi3-manylinux1_x86_64.whl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54230c11150a8d6314fb9d4856b045b3d5bf80092fa1901f3e1ef3b9afcd6e3f
|
| 3 |
+
size 213618745
|