hxxiang/opticaldna-rice-2048

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "hxxiang/opticaldna-rice-2048"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    torch_dtype="auto",
).cuda().eval()

# Visual features only: the language Decoder is not executed.
features = model.extract_features("page.png", pooling="mean", to_cpu=True)

# Decoder inference: short T1 / Free OCR.
prompt = model.build_prompt("t1_full_ocr", length="short")
text = model.generate_document(
    tokenizer,
    "page.png",
    prompt=prompt,
    max_new_tokens=256,
)

# Prompt-conditioned Decoder hidden states.
decoder_features = model.extract_decoder_features(
    tokenizer,
    "page.png",
    prompt=prompt,
    pooling="mean",
    to_cpu=True,
)