from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated", torch_dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
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
)
output_text = output_text[0]

print(output_text)

Donation

Your donation helps us continue our further development and improvement, a cup of coffee can do it.

bitcoin:

bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge