Feature Extraction
Transformers
Safetensors
deepseek_vl_v2
ocr
vision-language
fp8
quantized
deepseek
custom_code
compressed-tensors
Instructions to use richarddavison/DeepSeek-OCR-2-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use richarddavison/DeepSeek-OCR-2-FP8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="richarddavison/DeepSeek-OCR-2-FP8", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("richarddavison/DeepSeek-OCR-2-FP8", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "additional_special_tokens": [ | |
| "<|User|>", | |
| "<|Assistant|>" | |
| ], | |
| "bos_token": { | |
| "content": "<|begin▁of▁sentence|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "<|end▁of▁sentence|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "<|▁pad▁|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |