GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
kiel2
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
kiel2
Model Tree
Qwen/Qwen2.5-VL-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
You can load and run Kiel-2-OCR directly using Hugging Face transformers:
python
import torchfrom transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom PIL import Imageimport requests MODEL_ID = "kiel2/Kiel-2-OCR" print("Loading Kiel-2-OCR processor and model...")processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)model = Qwen2_5_VLForConditionalGeneration.from_pretrained( MODEL_ID, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)model.eval() # Prepare an image containing textimage_url = "[https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg)"image = Image.open(requests.get(image_url, stream=True).raw) conversation = [ { "role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": "Extract all readable text from this image accurately."}, ], }] # Apply chat templatetext_prompt = processor.apply_chat_template( conversation, tokenize=False, add_generation_prompt=True) # Process inputsinputs = processor( text=[text_prompt], images=[image], padding=True, return_tensors="pt").to(model.device) # Generate responsewith torch.no_grad(): output_ids = model.generate(**inputs, max_new_tokens=512) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)]response = processor.batch_decode( generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)[0] print("Extracted Text:\n", response)import torchfrom transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom PIL import Imageimport requests MODEL_ID = "kiel2/Kiel-2-OCR" print("Loading Kiel-2-OCR processor and model...")processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)model = Qwen2_5_VLForConditionalGeneration.from_pretrained( MODEL_ID, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)model.eval() # Prepare an image containing textimage_url = "[https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg)"image = Image.open(requests.get(image_url, stream=True).raw) conversation = [ { "role": "user", "content": [ {"type": "image", "image": image}, {"type": "text", "text": "Extract all readable text from this image accurately."}, ], }] # Apply chat templatetext_prompt = processor.apply_chat_template( conversation, tokenize=False, add_generation_prompt=True) # Process inputsinputs = processor( text=[text_prompt], images=[image], padding=True, return_tensors="pt").to(model.device) # Generate responsewith torch.no_grad(): output_ids = model.generate(**inputs, max_new_tokens=512) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)]response = processor.batch_decode( generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)[0] print("Extracted Text:\n", response)