TayaVision — Tiny Aya Vision (Instruct)
import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoProcessor
repo = "TrishanuDas/tayavision-multilingual"
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype=torch.bfloat16, trust_remote_code=True)
model = model.to("cuda").eval()
processor = AutoProcessor.from_pretrained(repo, trust_remote_code=True)
image = Image.open("your_image.jpg").convert("RGB")
messages = [
{"role": "user", "content": [
{"type": "image"},
{"type": "text", "text": "Describe this image in detail."},
]},
]
inputs = processor.apply_chat_template(
messages, images=image, add_generation_prompt=True, return_tensors="pt",
)
inputs = {k: v.to("cuda") for k, v in inputs.items()}
with torch.no_grad():
output_ids = model.generate(**inputs, max_new_tokens=256)
response = processor.tokenizer.decode(
output_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True,
)
print(response)
