from transformers import LlavaNextProcessor

processor = LlavaNextProcessor.from_pretrained("llava-hf/llava-v1.6-mistral-7b-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)
>>> "[INST] <image>\nWhat's shown in this image? [/INST] This image shows a red stop sign. [INST] Describe the image in more details. [/INST]"

"[INST] <image>\nWhat is shown in this image? [/INST]"

"A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions. USER: <image>\nWhat is shown in this image? ASSISTANT:"

"<|im_start|>system\nAnswer the questions.<|im_end|><|im_start|>user\n<image>\nWhat is shown in this image?<|im_end|><|im_start|>assistant\n"

"<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language.<|eot_id|><|start_header_id|><|start_header_id|>user<|end_header_id|>\n\n<image>\nWhat is shown in this image?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"

"<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<image>\nWhat is shown in this image?<|im_end|>\n<|im_start|>assistant\n"

from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration
import torch
from PIL import Image
import requests

processor = LlavaNextProcessor.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf")

model = LlavaNextForConditionalGeneration.from_pretrained("llava-hf/llava-v1.6-mistral-7b-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(image, prompt, return_tensors="pt").to("cuda:0")

# autoregressively complete prompt
output = model.generate(**inputs, max_new_tokens=100)

print(processor.decode(output[0], skip_special_tokens=True))

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

# Load the model in half-precision
model = LlavaNextForConditionalGeneration.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf", torch_dtype=torch.float16, device_map="auto")
processor = AutoProcessor.from_pretrained("llava-hf/llava-v1.6-mistral-7b-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
# Each "<image>" token uses one image leaving the next for the subsequent "<image>" tokens
inputs = processor(images=[image_stop, image_cats, image_snowman], text=prompts, padding=True, return_tensors="pt").to(model.device)

# Generate
generate_ids = model.generate(**inputs, max_new_tokens=30)
processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)

from transformers import LlavaNextForConditionalGeneration, 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 = LlavaNextForConditionalGeneration.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf", quantization_config=quantization_config, device_map="auto")

from transformers import LlavaNextForConditionalGeneration

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