Helium1-VL-2B

import torch
from transformers.models.auto.modeling_auto import AutoModel
from transformers.models.auto.processing_auto import AutoProcessor

model_id = "kyutai/Helium1-VL-2B"
model = AutoModel.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    trust_remote_code=True,
).cuda()
processor = AutoProcessor.from_pretrained(
    model_id,
    trust_remote_code=True,
)

conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.png",
            },
            {
                "type": "text",
                "text": "Describe this image.",
            },
        ],
    },
]

inputs = processor.tokenize_messages(messages=conversation)
inputs = inputs.to(model.device)
input_len = inputs["input_ids"].shape[1]

output_ids = model.generate_from_image(
  **inputs,
  max_new_tokens=512,
  pre_image_tokens=processor.pre_image_tokens,
  post_image_tokens=processor.post_image_tokens,
  eos_token_id=model.generation_config.eos_token_id,
)[0, input_len:]

response = processor.tokenizer.decode(output_ids, skip_special_tokens=True)
print(response)