Spaces:
Runtime error
Runtime error
File size: 1,870 Bytes
ec9d468 1e8121a ec9d468 1e8121a ec9d468 98ca294 1e8121a 98ca294 1e8121a ec9d468 98ca294 ec9d468 |
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 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
import gradio as gr
import spaces
import torch
import os
import subprocess
os.system("pip install git+https://github.com/huggingface/transformers")
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info
model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-7B-Instruct").cuda()
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
@spaces.GPU
def infer(u, t):
if len(u) < 1:
u = "https://lf3-static.bytednsdoc.com/obj/eden-cn/pbovhozuha/screenshot-20240923-164458.png"
if len(t) < 1:
t = "请将图里文字转成markdown"
messages = [
{
"role": "user",
"content": [
{
"type": "image",
"image": u,
},
{
"type": "text",
"text": t,
},
],
}
]
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(model.device)
generated_ids = model.generate(**inputs, max_new_tokens=512)
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
demo = gr.Interface(
fn=infer,
inputs=[
gr.Text(label="url"),
gr.Text(label="text"),
],
outputs=gr.Text(),
)
demo.launch()
|