kshitijthakkar/qwen3.5-0.8b-moe-from-scratch

from transformers import AutoModelForImageTextToText, AutoProcessor

model = AutoModelForImageTextToText.from_pretrained(
    "kshitijthakkar/qwen3.5-0.8b-moe-from-scratch",
    torch_dtype="bfloat16",
    device_map="auto",
)
processor = AutoProcessor.from_pretrained("kshitijthakkar/qwen3.5-0.8b-moe-from-scratch")

messages = [{"role": "user", "content": "Explain the Qwen3.5 architecture."}]
inputs = processor.apply_chat_template(
    messages, add_generation_prompt=True,
    tokenize=True, return_dict=True, return_tensors="pt"
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=200)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))