Image-to-Text
Transformers
Safetensors
deepseek_vl_v2
feature-extraction
vision
ocr
quantized
qvlm
4-bit precision
deepseek
custom_code
8-bit precision
Instructions to use SamMikaelson/deepseek-ocr-qvlm-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SamMikaelson/deepseek-ocr-qvlm-4bit with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-text", model="SamMikaelson/deepseek-ocr-qvlm-4bit", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SamMikaelson/deepseek-ocr-qvlm-4bit", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from SamMikaelson/deepseek-ocr-qvlm-4bit: direct link, hf CLI and curl.
- Browser
- Download file 460 Bytes
-
https://huggingface.co/SamMikaelson/deepseek-ocr-qvlm-4bit/resolve/main/processor_config.json
- Command line
-
hf download hf://SamMikaelson/deepseek-ocr-qvlm-4bit/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/SamMikaelson/deepseek-ocr-qvlm-4bit/resolve/main/processor_config.json
460 Bytes
| { | |
| "add_special_token": false, | |
| "candidate_resolutions": [ | |
| [ | |
| 1024, | |
| 1024 | |
| ] | |
| ], | |
| "downsample_ratio": 4, | |
| "ignore_id": -100, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_token": "<image>", | |
| "mask_prompt": false, | |
| "normalize": true, | |
| "pad_token": "<\uff5c\u2581pad\u2581\uff5c>", | |
| "patch_size": 16, | |
| "processor_class": "DeepseekVLV2Processor", | |
| "sft_format": "deepseek" | |
| } | |