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

cpu_count = os.cpu_count()
print(f"Number of CPU cores in the system: {cpu_count}")
half_cpu_count = cpu_count // 2
os.environ["MKL_NUM_THREADS"] = str(half_cpu_count)
os.environ["OMP_NUM_THREADS"] = str(half_cpu_count)
torch.set_num_threads(half_cpu_count)

MODEL_ID = "huihui-ai/Huihui-Qwen3-VL-4B-Thinking-abliterated"

# default: Load the model on the available device(s)
model = Qwen3VLForConditionalGeneration.from_pretrained(
    MODEL_ID, 
    device_map="auto", 
    trust_remote_code=True,
    dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
)
# 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-235B-A22B-Thinking",
#     dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

processor = AutoProcessor.from_pretrained(MODEL_ID)


image_path = "/png/cars.jpg"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image", "image": f"{image_path}",
            },
            {"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"
).to(model.device)

# 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)