pip install -q transformers accelerate flash_attn torchcodec

from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration
import torch
model_id = "llava-hf/llava-onevision-qwen2-0.5b-ov-hf"

device = torch.accelerator.current_accelerator().type if torch.accelerator.is_available() else "cpu"
processor = AutoProcessor.from_pretrained(model_id, device=device)

model = LlavaForConditionalGeneration.from_pretrained(model_id, device_map="auto", dtype=torch.float16)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "video", "video": "https://huggingface.co/spaces/merve/llava-interleave/resolve/main/cats_1.mp4"},
            {"type": "text", "text": "Describe what is happening in this video."},
        ],
    }
]

inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
    num_frames=10,
    do_sample_frames=True
)
inputs.to(model.device)

generated_ids = model.generate(**inputs, max_new_tokens=128)
input_length = len(inputs["input_ids"][0])
output_text = processor.batch_decode(
    generated_ids[:, input_length:], skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = processor.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text[0])

#"The video features a fluffy, long-haired cat with a mix of brown and white fur, lying on a beige carpeted floor. The cat's eyes are wide open, and its whiskers are prominently visible. The cat appears to be in a relaxed state, with its head slightly"

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Here's a video."},
            {"type": "video", "video": "https://huggingface.co/spaces/merve/llava-interleave/resolve/main/cats_1.mp4"},
            {"type": "text", "text": "Here's another video."},
            {"type": "video", "video": "https://huggingface.co/spaces/merve/llava-interleave/resolve/main/cats_2.mp4"},
            {"type": "text", "text": "Describe similarities in these videos."},
        ],
    }
]

inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
    num_frames=100,
    do_sample_frames=True
)
inputs.to(model.device)

generated_ids = model.generate(**inputs, max_new_tokens=50)
input_length = len(inputs["input_ids"][0])
output_text = processor.batch_decode(
    generated_ids[:, input_length:], skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)
#['Both videos feature a cat with a similar appearance, characterized by a fluffy white coat with black markings, a pink nose, and a pink tongue. The cat\'s eyes are wide open, and it appears to be in a state of alertness or excitement. ']