File size: 1,193 Bytes
ded2015 |
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 |
from transformers import AutoProcessor, Gemma3ForConditionalGeneration
import torch
model_id = "GaMS-Beta/gemma-3-4b-fine-tuned-slo-VLM"
model = Gemma3ForConditionalGeneration.from_pretrained(
model_id, device_map="auto"
).eval()
processor = AutoProcessor.from_pretrained(model_id)
messages = [
{
"role": "system",
"content": [{"type": "text", "text": ""}]
},
{
"role": "user",
"content": [
{"type": "image", "image": "https://sensa.metropolitan.si/media/cache/upload/Photo/2025/02/07/france-preseren_ofmivtT_biggalleryimage.jpg"},
{"type": "text", "text": "Kdo je na sliki?"}
]
}
]
print(processor.apply_chat_template(messages, tokenize=False))
inputs = processor.apply_chat_template(
messages, add_generation_prompt=True, tokenize=True,
return_dict=True, return_tensors="pt"
).to(model.device, dtype=torch.bfloat16)
input_len = inputs["input_ids"].shape[-1]
with torch.inference_mode():
generation = model.generate(**inputs, max_new_tokens=500, do_sample=False)
generation = generation[0][input_len:]
decoded = processor.decode(generation, skip_special_tokens=True)
print(decoded)
|