Image-Text-to-Text
Transformers
Safetensors
deepseek_vl_v2
feature-extraction
forkjoin-ai
edge-deployment
aether
custom_code
Instructions to use forkjoin-ai/deepseek-ocr-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use forkjoin-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="forkjoin-ai/deepseek-ocr-2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("forkjoin-ai/deepseek-ocr-2", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use forkjoin-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 "forkjoin-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": "forkjoin-ai/deepseek-ocr-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/forkjoin-ai/deepseek-ocr-2
- SGLang
How to use forkjoin-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 "forkjoin-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": "forkjoin-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 "forkjoin-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": "forkjoin-ai/deepseek-ocr-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use forkjoin-ai/deepseek-ocr-2 with Docker Model Runner:
docker model run hf.co/forkjoin-ai/deepseek-ocr-2
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -7,20 +7,20 @@ tags:
|
|
| 7 |
- gguf
|
| 8 |
- vision
|
| 9 |
- multimodal
|
| 10 |
-
-
|
| 11 |
base_model: deepseek-ai/DeepSeek-OCR-2
|
| 12 |
pipeline_tag: image-text-to-text
|
| 13 |
---
|
| 14 |
|
| 15 |
# Deepseek Ocr 2
|
| 16 |
|
| 17 |
-
|
| 18 |
|
| 19 |
## Model Details
|
| 20 |
|
| 21 |
- **Source Model**: [deepseek-ai/DeepSeek-OCR-2](https://huggingface.co/deepseek-ai/DeepSeek-OCR-2)
|
| 22 |
- **Format**: GGUF
|
| 23 |
-
- **Converted by**: [
|
| 24 |
|
| 25 |
## Usage
|
| 26 |
|
|
@@ -42,9 +42,9 @@ ollama create deepseek-ocr-2-gguf -f Modelfile
|
|
| 42 |
ollama run deepseek-ocr-2-gguf
|
| 43 |
```
|
| 44 |
|
| 45 |
-
## About
|
| 46 |
|
| 47 |
-
[
|
| 48 |
|
| 49 |
All conversions are optimized for edge deployment within browser and mobile memory constraints.
|
| 50 |
|
|
|
|
| 7 |
- gguf
|
| 8 |
- vision
|
| 9 |
- multimodal
|
| 10 |
+
- forkjoin-ai
|
| 11 |
base_model: deepseek-ai/DeepSeek-OCR-2
|
| 12 |
pipeline_tag: image-text-to-text
|
| 13 |
---
|
| 14 |
|
| 15 |
# Deepseek Ocr 2
|
| 16 |
|
| 17 |
+
Forkjoin.ai conversion of [deepseek-ai/DeepSeek-OCR-2](https://huggingface.co/deepseek-ai/DeepSeek-OCR-2) to GGUF format for edge deployment.
|
| 18 |
|
| 19 |
## Model Details
|
| 20 |
|
| 21 |
- **Source Model**: [deepseek-ai/DeepSeek-OCR-2](https://huggingface.co/deepseek-ai/DeepSeek-OCR-2)
|
| 22 |
- **Format**: GGUF
|
| 23 |
+
- **Converted by**: [Forkjoin.ai](https://forkjoin.ai)
|
| 24 |
|
| 25 |
## Usage
|
| 26 |
|
|
|
|
| 42 |
ollama run deepseek-ocr-2-gguf
|
| 43 |
```
|
| 44 |
|
| 45 |
+
## About Forkjoin.ai
|
| 46 |
|
| 47 |
+
[Forkjoin.ai](https://forkjoin.ai) runs AI models at the edge -- in-browser, on-device, zero cloud cost. These converted models power real-time inference, speech recognition, and natural language capabilities.
|
| 48 |
|
| 49 |
All conversions are optimized for edge deployment within browser and mobile memory constraints.
|
| 50 |
|