GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Jakelolipopp
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Jakelolipopp
Model Tree
unsloth/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
unsloth/Qwen3.5-9BJakelolipopp/Qwen3.5-9B-AltText-v4-LORAbfloat16python
import torchfrom transformers import AutoProcessor, AutoModelForImageTextToTextfrom PIL import Image model_id = "Jakelolipopp/Qwen3.5-9B-AltText-v4-merged"processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForImageTextToText.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True) image = Image.open("example.jpg")messages = [ { "role": "user", "content": [ {"type": "image"}, {"type": "text", "text": "Provide detailed alternative text describing this image:"} ] }] text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[text], images=[image], return_tensors="pt").to("cuda") with torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=256) generated_ids = outputs[:, inputs.input_ids.shape[1]:]print(processor.batch_decode(generated_ids, skip_special_tokens=True)[0])import torchfrom transformers import AutoProcessor, AutoModelForImageTextToTextfrom PIL import Image model_id = "Jakelolipopp/Qwen3.5-9B-AltText-v4-merged"processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForImageTextToText.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True) image = Image.open("example.jpg")messages = [ { "role": "user", "content": [ {"type": "image"}, {"type": "text", "text": "Provide detailed alternative text describing this image:"} ] }] text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[text], images=[image], return_tensors="pt").to("cuda") with torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=256) generated_ids = outputs[:, inputs.input_ids.shape[1]:]print(processor.batch_decode(generated_ids, skip_special_tokens=True)[0])