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
Input Modalities
Output Modalities
Supported Functionality
Qwen2_5_VLForConditionalGeneration)You can load and run Kiel-2-VQA directly using Hugging Face transformers and bitsandbytes for memory-efficient execution:
python
import torchfrom transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom PIL import Imageimport requests MODEL_ID = "kiel2/Kiel-2-VQA" print("Loading Kiel-2-VQA processor and model...")processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)model = Qwen2_5_VLForConditionalGeneration.from_pretrained( MODEL_ID, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)model.eval() # Prepare an image and a text queryimage_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": "Describe the key elements and setting of this image in detail."}, ], }] # 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=256) 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("Model Response:\n", response)Citation Code snippet@misc{kiel2-Kiel-2-VQA-2026, author = {KielTech}, title = {Kiel-2-VQA: High-Performance Multimodal Vision-Language Model}, year = {2026}, publisher = {Hugging Face}, journal = {Hugging Face Repository}, howpublished = {\url{[https://huggingface.co/kiel2/Kiel-2-VQA](https://huggingface.co/kiel2/Kiel-2-VQA)}}}import torchfrom transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom PIL import Imageimport requests MODEL_ID = "kiel2/Kiel-2-VQA" print("Loading Kiel-2-VQA processor and model...")processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)model = Qwen2_5_VLForConditionalGeneration.from_pretrained( MODEL_ID, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)model.eval() # Prepare an image and a text queryimage_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": "Describe the key elements and setting of this image in detail."}, ], }] # 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=256) 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("Model Response:\n", response)Citation Code snippet@misc{kiel2-Kiel-2-VQA-2026, author = {KielTech}, title = {Kiel-2-VQA: High-Performance Multimodal Vision-Language Model}, year = {2026}, publisher = {Hugging Face}, journal = {Hugging Face Repository}, howpublished = {\url{[https://huggingface.co/kiel2/Kiel-2-VQA](https://huggingface.co/kiel2/Kiel-2-VQA)}}}