from transformers import AutoConfig, AutoProcessor
from transformers.image_utils import load_image
import onnxruntime
import numpy as np

# 1. Load models
## Load config and processor
model_id = "HuggingFaceTB/SmolVLM-256M-Instruct"
config = AutoConfig.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id)

## Load sessions
## !wget https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct/resolve/main/onnx/vision_encoder.onnx
## !wget https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct/resolve/main/onnx/embed_tokens.onnx
## !wget https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct/resolve/main/onnx/decoder_model_merged.onnx
vision_session = onnxruntime.InferenceSession("vision_encoder.onnx")
embed_session = onnxruntime.InferenceSession("embed_tokens.onnx")
decoder_session = onnxruntime.InferenceSession("decoder_model_merged.onnx")

## Set config values
num_key_value_heads = config.text_config.num_key_value_heads
head_dim = config.text_config.head_dim
num_hidden_layers = config.text_config.num_hidden_layers
eos_token_id = config.text_config.eos_token_id
image_token_id = config.image_token_id


# 2. Prepare inputs
## Create input messages
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "Can you describe this image?"}
        ]
    },
]

## Load image and apply processor
image = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image], return_tensors="np")

## Prepare decoder inputs
batch_size = inputs['input_ids'].shape[0]
past_key_values = {
    f'past_key_values.{layer}.{kv}': np.zeros([batch_size, num_key_value_heads, 0, head_dim], dtype=np.float32)
    for layer in range(num_hidden_layers)
    for kv in ('key', 'value')
}
image_features = None
input_ids = inputs['input_ids']
attention_mask = inputs['attention_mask']
position_ids = np.cumsum(inputs['attention_mask'], axis=-1)


# 3. Generation loop
max_new_tokens = 1024
generated_tokens = np.array([[]], dtype=np.int64)
for i in range(max_new_tokens):
  inputs_embeds = embed_session.run(None, {'input_ids': input_ids})[0]

  if image_features is None:
    ## Only compute vision features if not already computed
    image_features = vision_session.run(
        ['image_features'],  # List of output names or indices
        {
            'pixel_values': inputs['pixel_values'],
            'pixel_attention_mask': inputs['pixel_attention_mask'].astype(np.bool_)
        }
    )[0]
    
    ## Merge text and vision embeddings
    inputs_embeds[inputs['input_ids'] == image_token_id] = image_features.reshape(-1, image_features.shape[-1])

  logits, *present_key_values = decoder_session.run(None, dict(
      inputs_embeds=inputs_embeds,
      attention_mask=attention_mask,
      position_ids=position_ids,
      **past_key_values,
  ))

  ## Update values for next generation loop
  input_ids = logits[:, -1].argmax(-1, keepdims=True)
  attention_mask = np.ones_like(input_ids)
  position_ids = position_ids[:, -1:] + 1
  for j, key in enumerate(past_key_values):
    past_key_values[key] = present_key_values[j]

  generated_tokens = np.concatenate([generated_tokens, input_ids], axis=-1)
  if (input_ids == eos_token_id).all():
    break

  ## (Optional) Streaming
  print(processor.decode(input_ids[0]), end='')
print()

# 4. Output result
print(processor.batch_decode(generated_tokens))

 The image depicts a large, historic statue of Liberty situated on a small island in a body of water. The statue is a green, cylindrical structure with a human figure at the top, which is the actual statue of Liberty. The statue is mounted on a pedestal that is supported by a cylindrical tower. The pedestal is rectangular and appears to be made of stone or a similar material. The statue is surrounded by a large, flat, rectangular area that is likely a base for the statue.

In the background, there is a cityscape with a variety of buildings, including skyscrapers and high-rise buildings. The sky is clear with a gradient of colors, transitioning from a pale blue at the top to a deeper blue at the bottom. The buildings are mostly modern, with a mix of glass and concrete. The buildings are densely packed, with many skyscrapers and high-rise buildings visible.

There are trees and greenery visible on the left side of the image, indicating that the statue is located near a park or a park area. The water in the foreground is calm, with small ripples indicating that the statue is in the water.

The overall scene suggests a peaceful and serene environment, likely a public park or a park area in a city. The statue is likely a representation of liberty, representing the city's commitment to freedom and democracy.

### Analysis and Description:

#### Statue of Liberty:
- **Location**: The statue is located on a small island in a body of water.
- **Statue**: The statue is a green cylindrical structure with a human figure at the top, which is the actual statue of Liberty.
- **Pedestal**: The pedestal is rectangular and supports the statue.
- **Pedestrian**: The pedestal is surrounded by a flat rectangular area.
- **Water**: The water is calm, with small ripples indicating that the statue is in the water.

#### Cityscape:
- **Buildings**: The buildings are modern, with a mix of glass and concrete.
- **Sky**: The sky is clear with a gradient of colors, transitioning from a pale blue at the top to a deeper blue at the bottom.
- **Trees**: There are trees and greenery visible on the left side of the image, indicating that the statue is located near a park or a park area.

#### Environment:
- **Water**: The water is calm, with small ripples indicating that the statue is in the water.
- **Sky**: The sky is clear with a gradient of colors, transitioning from a pale blue at the top to a deeper blue at the bottom.

### Conclusion:
The image depicts a peaceful and serene public park or park area in a city, with the statue of Liberty prominently featured. The cityscape in the background includes modern buildings and a clear sky, suggesting a well-maintained public space.<end_of_utterance>