GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
chaser2
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
chaser2
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Qwen3VLForConditionalGenerationqwen3_vlbfloat16python
import torchfrom transformers import Qwen3VLForConditionalGeneration, AutoProcessor model_id = "chaser2/VIG-Qwen3-VL-Thinking-4B"model = Qwen3VLForConditionalGeneration.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto")processor = AutoProcessor.from_pretrained(model_id) messages = [{ "role": "user", "content": [ {"type": "image", "image": "path/to/image.jpg"}, {"type": "text", "text": "Describe the image and explain your reasoning."} ]}]prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[prompt], images=["path/to/image.jpg"], return_tensors="pt", padding=True).to(model.device)with torch.inference_mode(): outputs = model.generate(**inputs, max_new_tokens=1024)answer = outputs[:, inputs.input_ids.shape[1]:]print(processor.batch_decode(answer, skip_special_tokens=True)[0])The repository contains the complete model weights, configuration, tokenizer, processor, and generation configuration for reproducible use.