Python server is ready!
Python: 2025-10-25 12:55:59,379 - INFO - Progress: loading - init - Initializing model loading... (0%)
2025-10-25 12:55:59,380 - INFO - Loading DeepSeek OCR model from deepseek-ai/DeepSeek-OCR...
2025-10-25 12:55:59,380 - INFO - Model will be cached in: H:\Temp\deepseek-ocr-client\backend..\cache\models
Python: 2025-10-25 12:55:59,385 - INFO - GPU available: NVIDIA GeForce RTX 4060 Ti
2025-10-25 12:55:59,385 - INFO - Progress: loading - tokenizer - Loading tokenizer... (10%)
2025-10-25 12:55:59,385 - INFO - Loading tokenizer...
Python: 2025-10-25 12:56:05,132 - INFO - Progress: loading - tokenizer - Tokenizer loaded (20%)
Python: 2025-10-25 12:56:05,133 - INFO - Progress: loading - model - Loading model from cache... (25%)
Python: 2025-10-25 12:56:05,133 - INFO - Loading model from cache...
Python: 2025-10-25 12:56:07,134 - INFO - Progress: loading - model - Loading model from cache... (25%)
Python: 2025-10-25 12:56:09,135 - INFO - Progress: loading - model - Loading model from cache... (25%)
Python: 2025-10-25 12:56:11,184 - INFO - Progress: loading - model - Loading model from cache... (25%)
Python: You are using a model of type deepseek_vl_v2 to instantiate a model of type DeepseekOCR. This is not supported for all configurations of models and can yield errors.
Python: 2025-10-25 12:56:13,186 - INFO - Progress: loading - model - Loading model from cache... (25%)
Python: 2025-10-25 12:56:17,547 - WARNING - Flash attention not available: FlashAttention2 has been toggled on, but it cannot be used due to the following error: the package flash_attn seems to be not installed. Please refer to the documentation of https://huggingface.co/docs/transformers/perf_infer_gpu_one#flashattention-2 to install Flash Attention 2., using default attention
Python: You are using a model of type deepseek_vl_v2 to instantiate a model of type DeepseekOCR. This is not supported for all configurations of models and can yield errors.
Python process exited with code 3221225477
Python server is ready!
Python: 2025-10-25 12:55:59,379 - INFO - Progress: loading - init - Initializing model loading... (0%)
2025-10-25 12:55:59,380 - INFO - Loading DeepSeek OCR model from deepseek-ai/DeepSeek-OCR...
2025-10-25 12:55:59,380 - INFO - Model will be cached in: H:\Temp\deepseek-ocr-client\backend..\cache\models
Python: 2025-10-25 12:55:59,385 - INFO - GPU available: NVIDIA GeForce RTX 4060 Ti
2025-10-25 12:55:59,385 - INFO - Progress: loading - tokenizer - Loading tokenizer... (10%)
2025-10-25 12:55:59,385 - INFO - Loading tokenizer...
Python: 2025-10-25 12:56:05,132 - INFO - Progress: loading - tokenizer - Tokenizer loaded (20%)
Python: 2025-10-25 12:56:05,133 - INFO - Progress: loading - model - Loading model from cache... (25%)
Python: 2025-10-25 12:56:05,133 - INFO - Loading model from cache...
Python: 2025-10-25 12:56:07,134 - INFO - Progress: loading - model - Loading model from cache... (25%)
Python: 2025-10-25 12:56:09,135 - INFO - Progress: loading - model - Loading model from cache... (25%)
Python: 2025-10-25 12:56:11,184 - INFO - Progress: loading - model - Loading model from cache... (25%)
Python: You are using a model of type deepseek_vl_v2 to instantiate a model of type DeepseekOCR. This is not supported for all configurations of models and can yield errors.
Python: 2025-10-25 12:56:13,186 - INFO - Progress: loading - model - Loading model from cache... (25%)
Python: 2025-10-25 12:56:17,547 - WARNING - Flash attention not available: FlashAttention2 has been toggled on, but it cannot be used due to the following error: the package flash_attn seems to be not installed. Please refer to the documentation of https://huggingface.co/docs/transformers/perf_infer_gpu_one#flashattention-2 to install Flash Attention 2., using default attention
Python: You are using a model of type deepseek_vl_v2 to instantiate a model of type DeepseekOCR. This is not supported for all configurations of models and can yield errors.
Python process exited with code 3221225477