File size: 1,753 Bytes
e1ce3ad |
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 68 |
---
datasets:
- scta/scta-htr-training-data
base_model:
- Qwen/Qwen2-VL-2B-Instruct
---
import torch
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info
device = "cuda" if torch.cuda.is_available() else "cpu"
model_dir = "medieval-data/qwen2-vl-2b-scta"
model = Qwen2VLForConditionalGeneration.from_pretrained(
model_dir, torch_dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
image_url ="""https://loris2.scta.info/lon/L28v.jpg/full/full/0/default.jpg"""
messages = [
{
"role": "user",
"content": [
{
"type": "image",
"image": image_url,
},
{"type": "text", "text": "Convert this image to text."},
],
}
]
# 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(device)
# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=4000)
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)
# Import required libraries if not already imported
from IPython.display import display, Image
# Display the output text
print(output_text)
# Display the image
display(Image(url=image_url)) |