Gemma2-9B

Usage

Below is a code snippet to run Ovis with multimodal inputs. For additional usage instructions, including inference wrapper and Gradio UI, please refer to Ovis GitHub.

pip install torch==2.2.0 transformers==4.44.2 numpy==1.24.3 pillow==10.3.0

import torch
from PIL import Image
from transformers import AutoModelForCausalLM

# load model
model = AutoModelForCausalLM.from_pretrained("mobenta/Gemma2-9B",
                                             torch_dtype=torch.bfloat16,
                                             multimodal_max_length=8192,
                                             trust_remote_code=True).cuda()
text_tokenizer = model.get_text_tokenizer()
visual_tokenizer = model.get_visual_tokenizer()

# enter image path and prompt
image_path = input("Enter image path: ")
image = Image.open(image_path)
text = input("Enter prompt: ")
query = f'<image>\n{text}'

# format conversation
prompt, input_ids, pixel_values = model.preprocess_inputs(query, [image])
attention_mask = torch.ne(input_ids, text_tokenizer.pad_token_id)
input_ids = input_ids.unsqueeze(0).to(device=model.device)
attention_mask = attention_mask.unsqueeze(0).to(device=model.device)
pixel_values = [pixel_values.to(dtype=visual_tokenizer.dtype, device=visual_tokenizer.device)]

# generate output
with torch.inference_mode():
    gen_kwargs = dict(
        max_new_tokens=1024,
        do_sample=False,
        top_p=None,
        top_k=None,
        temperature=None,
        repetition_penalty=None,
        eos_token_id=model.generation_config.eos_token_id,
        pad_token_id=text_tokenizer.pad_token_id,
        use_cache=True
    )
    output_ids = model.generate(input_ids, pixel_values=pixel_values, attention_mask=attention_mask, **gen_kwargs)[0]
    output = text_tokenizer.decode(output_ids, skip_special_tokens=True)
    print(f'Output:\n{output}')

<details> <summary>Batch inference</summary>

batch_inputs = [
    ('example_image1.jpeg', 'Describe the content of this image.'),
    ('example_image2.jpeg', 'What is the equation in the image?')
]

batch_input_ids = []
batch_attention_mask = []
batch_pixel_values = []

for image_path, text in batch_inputs:
    image = Image.open(image_path)
    query = f'<image>\n{text}'
    prompt, input_ids, pixel_values = model.preprocess_inputs(query, [image])
    attention_mask = torch.ne(input_ids, text_tokenizer.pad_token_id)
    input_ids = input_ids.unsqueeze(0).to(device=model.device)
    attention_mask = attention_mask.unsqueeze(0).to(device=model.device)
    pixel_values = [pixel_values.to(dtype=visual_tokenizer.dtype, device=visual_tokenizer.device)]
    batch_input_ids.append(input_ids.squeeze())
    batch_attention_mask.append(attention_mask.squeeze())
    batch_pixel_values.append(pixel_values)

pad_batch_input_ids = torch.nn.utils.rnn.pad_sequence([i.flip(dims=[0]) for i in batch_input_ids],batch_first=True, padding_value=0.0).flip(dims=[1])
pad_batch_input_ids =  pad_batch_input_ids[:,-model.config.multimodal_max_length:]
pad_batch_attention_mask = torch.nn.utils.rnn.pad_sequence([i.flip(dims=[0]) for i in batch_attention_mask],batch_first=True, padding_value=False).flip(dims=[1])
pad_batch_attention_mask = pad_batch_attention_mask[:,-model.config.multimodal_max_length:]
pad_batch_pixel_values = [item for sublist in batch_pixel_values for item in sublist]

# generate output
with torch.inference_mode():
    gen_kwargs = dict(
        max_new_tokens=1024,
        do_sample=False,
        top_p=None,
        top_k=None,
        temperature=None,
        repetition_penalty=None,
        eos_token_id=model.generation_config.eos_token_id,
        pad_token_id=text_tokenizer.pad_token_id,
        use_cache=True
    )
    output_ids = model.generate(pad_batch_input_ids, pixel_values=pad_batch_pixel_values, attention_mask=pad_batch_attention_mask, **gen_kwargs)

for i in range(len(batch_input_ids)):
    output = text_tokenizer.decode(output_ids[i], skip_special_tokens=True)
    print(f'Output_{i}:\n{output}')

</details>

License

The project is licensed under the Apache 2.0 License and is restricted to uses that comply with the license agreements of Gemma2 and Siglip.