from transformers import Qwen3VLForConditionalGeneration, AutoProcessor, BitsAndBytesConfig
import torch
import gc

cache_dir = "./model_cache"

print("Freeing up memory...")
torch.cuda.empty_cache()
gc.collect()

model_kwargs = dict(
    #attn_implementation="eager", # Use "flash_attention_2" when running on Ampere or newer GPU
    torch_dtype=torch.bfloat16,#torch.float16,#torch.bfloat16, # What torch dtype to use, defaults to auto
    device_map="auto", # Let torch decide how to load the model
   
)

# BitsAndBytesConfig int-4 config
model_kwargs["quantization_config"] = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=model_kwargs["torch_dtype"],
    bnb_4bit_quant_storage=model_kwargs["torch_dtype"],
)

# default: Load the model on the available device(s)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen3-VL-2B-Instruct",cache_dir=cache_dir, **model_kwargs
)

# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
# model = Qwen3VLForConditionalGeneration.from_pretrained(
#     "Qwen/Qwen3-VL-4B-Instruct",
#     dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-2B-Instruct",cache_dir=cache_dir)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]







# Preparation for inference
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
)
inputs = inputs.to(model.device) #vedi che non gli passa immagine PIL come fa per gemma3

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)