from transformers import AutoProcessor

processor = AutoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-7b-si-hf")

conversation = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What’s shown in this image?"},
        ],
    },
    {
        "role": "assistant",
        "content": [{"type": "text", "text": "This image shows a red stop sign."},]
    },
    {

        "role": "user",
        "content": [
            {"type": "text", "text": "Describe the image in more details."},
        ],
    },
]

text_prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)

# Note that the template simply formats your prompt, you still have to tokenize it and obtain pixel values for your images
print(text_prompt)
>>> "<|im_start|>user\n<image>What is shown in this image?<|im_end|>\n<|im_start|>assistant\nPage showing the list of options.<|im_end|>"

from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration
import torch
from PIL import Image
import requests

processor = AutoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf") 
model = LlavaOnevisionForConditionalGeneration.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf", torch_dtype=torch.float16, low_cpu_mem_usage=True) 
model.to("cuda:0")

# prepare image and text prompt, using the appropriate prompt template
url = "https://github.com/haotian-liu/LLaVA/blob/1a91fc274d7c35a9b50b3cb29c4247ae5837ce39/images/llava_v1_5_radar.jpg?raw=true"
image = Image.open(requests.get(url, stream=True).raw)

conversation = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What is shown in this image?"},
        ],
    },
]
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
inputs = processor(images=image, text=prompt, return_tensors="pt").to("cuda:0", torch.float16)

# autoregressively complete prompt
output = model.generate(**inputs, max_new_tokens=100)
print(processor.decode(output[0], skip_special_tokens=True))
'user\n\nWhat is shown in this image?\nassistant\nThe image shows a radar chart, also known as a spider chart or a star chart, which is used to compare multiple quantitative variables. Each axis represents a different variable, and the chart is filled with'

import requests
from PIL import Image
import torch
from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration

# Load the model in half-precision
model = LlavaOnevisionForConditionalGeneration.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf", torch_dtype=torch.float16, device_map="auto")
processor = AutoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf")

# Get three different images
url = "https://www.ilankelman.org/stopsigns/australia.jpg"
image_stop = Image.open(requests.get(url, stream=True).raw)

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image_cats = Image.open(requests.get(url, stream=True).raw)

url = "https://huggingface.co/microsoft/kosmos-2-patch14-224/resolve/main/snowman.jpg"
image_snowman = Image.open(requests.get(url, stream=True).raw)

# Prepare a batch of two prompts, where the first one is a multi-turn conversation and the second is not
conversation_1 = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What is shown in this image?"},
            ],
    },
    {
        "role": "assistant",
        "content": [
            {"type": "text", "text": "There is a red stop sign in the image."},
            ],
    },
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What about this image? How many cats do you see?"},
            ],
    },
]

conversation_2 = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What is shown in this image?"},
            ],
    },
]

prompt_1 = processor.apply_chat_template(conversation_1, add_generation_prompt=True)
prompt_2 = processor.apply_chat_template(conversation_2, add_generation_prompt=True)
prompts = [prompt_1, prompt_2]

# We can simply feed images in the order they have to be used in the text prompt
inputs = processor(images=[image_stop, image_cats, image_snowman], text=prompts, padding=True, return_tensors="pt").to(model.device, torch.float16)

# Generate
generate_ids = model.generate(**inputs, max_new_tokens=30)
processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
['user\n\nWhat is shown in this image?\nassistant\nThere is a red stop sign in the image.\nuser\n\nWhat about this image? How many cats do you see?\nassistant\ntwo', 'user\n\nWhat is shown in this image?\nassistant\n']

import av
import numpy as np
from huggingface_hub import hf_hub_download

import torch
from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration

# Load the model in half-precision
model = LlavaOnevisionForConditionalGeneration.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf", torch_dtype=torch.float16, device_map="auto")
processor = AutoProcessor.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf")


def read_video_pyav(container, indices):
    '''
    Decode the video with PyAV decoder.
    Args:
        container (`av.container.input.InputContainer`): PyAV container.
        indices (`List[int]`): List of frame indices to decode.
    Returns:
        result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
    '''
    frames = []
    container.seek(0)
    start_index = indices[0]
    end_index = indices[-1]
    for i, frame in enumerate(container.decode(video=0)):
        if i > end_index:
            break
        if i >= start_index and i in indices:
            frames.append(frame)
    return np.stack([x.to_ndarray(format="rgb24") for x in frames])

# Load the video as an np.array, sampling uniformly 8 frames (can sample more for longer videos, up to 32 frames)
video_path = hf_hub_download(repo_id="raushan-testing-hf/videos-test", filename="sample_demo_1.mp4", repo_type="dataset")
container = av.open(video_path)
total_frames = container.streams.video[0].frames
indices = np.arange(0, total_frames, total_frames / 8).astype(int)
video = read_video_pyav(container, indices)

# For videos we have to feed a "video" type instead of "image"
conversation = [
    {

        "role": "user",
        "content": [
            {"type": "video"},
            {"type": "text", "text": "Why is this video funny?"},
            ],
    },
]

prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
inputs = processor(videos=list(video), text=prompt, return_tensors="pt").to("cuda:0", torch.float16)

out = model.generate(**inputs, max_new_tokens=60)
processor.batch_decode(out, skip_special_tokens=True, clean_up_tokenization_spaces=True)
["user\n\nWhy is this video funny?\nassistant\nThe video appears to be humorous because it shows a young child, who is wearing glasses and holding a book, seemingly reading with a serious and focused expression. The child's glasses are a bit oversized for their face, which adds a comical touch, as it's a common trope to see children wearing"]

from transformers import LlavaOnevisionForConditionalGeneration, BitsAndBytesConfig

# specify how to quantize the model
quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)

model = LlavaOnevisionForConditionalGeneration.from_pretrained(model_id, quantization_config=quantization_config, device_map="auto")

from transformers import LlavaOnevisionForConditionalGeneration

model = LlavaOnevisionForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True,
    use_flash_attention_2=True
).to(0)