Spaces:
Sleeping
Sleeping
File size: 1,583 Bytes
0483ead e623f79 0483ead e623f79 0483ead e623f79 0483ead |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
import gradio as gr
from transformers import AutoProcessor, AutoModelForImageTextToText
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
model = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
def launch(input):
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
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")
# 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
)
return(output_text)
iface = gr.Interface(launch,
inputs=gr.Image(type='pil'),
outputs="text")
iface.launch() |