How to use tnkchaseme/DeepSeek-OCR-2-CROHME-LORA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-OCR-2") model = PeftModel.from_pretrained(base_model, "tnkchaseme/DeepSeek-OCR-2-CROHME-LORA")
How to use tnkchaseme/DeepSeek-OCR-2-CROHME-LORA 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="tnkchaseme/DeepSeek-OCR-2-CROHME-LORA")
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("tnkchaseme/DeepSeek-OCR-2-CROHME-LORA", device_map="auto")
