A chat between a curious user and an artificial intelligence assistant. The 
assistant gives helpful, detailed, and polite answers to the user's questions. 
USER: <im_start><image><im_end> User's prompt
ASSISTANT: Assistant answer
USER: Another prompt

class LLaVAChatBot:
    def __init__(self,
                 model_path: str = 'liuhaotian/llava-v1.5-7b',
                 device_map: str = 'auto',
                 load_in_8_bit: bool = True,
                 **quant_kwargs) -> None:
        self.model = None
        self.tokenizer = None
        self.image_processor = None
        self.conv = None
        self.conv_img = None
        self.img_tensor = None
        self.roles = None
        self.stop_key = None
        self.load_models(model_path,
                         device_map=device_map,
                         load_in_8_bit=load_in_8_bit,
                         **quant_kwargs)

    def load_models(self, model_path: str,
                    device_map: str,
                    load_in_8_bit: bool,
                    **quant_kwargs) -> None:
        """Load the model, processor and tokenizer."""
        quant_cfg = BitsAndBytesConfig(**quant_kwargs)
        self.model = LlavaLlamaForCausalLM.from_pretrained(model_path,
                                                           low_cpu_mem_usage=True,
                                                           device_map=device_map,
                                                           load_in_8bit=load_in_8_bit,
                                                           quantization_config=quant_cfg)
        self.tokenizer = AutoTokenizer.from_pretrained(model_path,
                                                       use_fast=False)
        vision_tower = self.model.get_vision_tower()
        vision_tower.load_model()
        vision_tower.to(device='cuda')
        self.image_processor = vision_tower.image_processor
        disable_torch_init()

    def setup_image(self, img_path: str) -> None:
        """Load and process the image."""
        if img_path.startswith('http') or img_path.startswith('https'):
            response = requests.get(img_path)
            self.conv_img = Image.open(BytesIO(response.content)).convert('RGB')
        else:
            self.conv_img = Image.open(img_path).convert('RGB')
        self.img_tensor = self.image_processor.preprocess(self.conv_img,
                                                          return_tensors='pt'
                                                          )['pixel_values'].half().cuda()

    def generate_answer(self, **kwargs) -> str:
        """Generate an answer from the current conversation."""
        raw_prompt = self.conv.get_prompt()
        input_ids = tokenizer_image_token(raw_prompt,
                                          self.tokenizer,
                                          IMAGE_TOKEN_INDEX,
                                          return_tensors='pt').unsqueeze(0).cuda()
        stopping = KeywordsStoppingCriteria([self.stop_key],
                                            self.tokenizer,
                                            input_ids)
        with torch.inference_mode():
            output_ids = self.model.generate(input_ids,
                                             images=self.img_tensor,
                                             stopping_criteria=[stopping],
                                             **kwargs)
        outputs = self.tokenizer.decode(
            output_ids[0, input_ids.shape[1]:]
        ).strip()
        self.conv.messages[-1][-1] = outputs

        return outputs.rsplit('</s>', 1)[0]

    def get_conv_text(self) -> str:
        """Return full conversation text."""
        return self.conv.get_prompt()

    def start_new_chat(self,
                       img_path: str,
                       prompt: str,
                       do_sample=True,
                       temperature=0.2,
                       max_new_tokens=1024,
                       use_cache=True,
                       **kwargs) -> str:
        """Start a new chat with a new image."""
        conv_mode = "v1"
        self.setup_image(img_path)
        self.conv = conv_templates[conv_mode].copy()
        self.roles = self.conv.roles
        first_input = (DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN +
                       DEFAULT_IM_END_TOKEN + '\n' + prompt)  # f"{self.roles[0]}: {prompt}")
        self.conv.append_message(self.roles[0], first_input)
        self.conv.append_message(self.roles[1], None)
        if self.conv.sep_style == SeparatorStyle.TWO:
            self.stop_key = self.conv.sep2
        else:
            self.stop_key = self.conv.sep
        answer = self.generate_answer(do_sample=do_sample,
                                      temperature=temperature,
                                      max_new_tokens=max_new_tokens,
                                      use_cache=use_cache,
                                      **kwargs)
        return answer

    def continue_chat(self,
                      prompt: str,
                      do_sample=True,
                      temperature=0.2,
                      max_new_tokens=1024,
                      use_cache=True,
                      **kwargs) -> str:
        """Continue the existing chat."""
        if self.conv is None:
            raise RuntimeError("No existing conversation found. Start a new"
                               "conversation using the `start_new_chat` method.")
        self.conv.append_message(self.roles[0], prompt)
        self.conv.append_message(self.roles[1], None)
        answer = self.generate_answer(do_sample=do_sample,
                                      temperature=temperature,
                                      max_new_tokens=max_new_tokens,
                                      use_cache=use_cache,
                                      **kwargs)
        return answer

A chat between a curious user and an artificial intelligence assistant. The 
assistant gives helpful, detailed, and polite answers to the user's questions. 

USER: <im_start><image><im_end>
Describe the image in details. 

ASSISTANT: The image features a white tiger laying down on a rocky surface, 
possibly a stone wall or a rock. The tiger appears to be relaxed and 
comfortable in its environment. The tiger's position is such that it covers a 
significant portion of the image, from the left side to almost the entire right
side. The rocky surface provides a natural and rugged backdrop for the scene.</s></s>

USER: What is unique about this tiger? 

ASSISTANT: This tiger is unique because it is a white tiger, which is an 
extremely rare and visually striking variation of the species. White tigers are
born with a genetic mutation that causes their fur to be predominantly white, 
with the rest of their body being a mix of orange and black stripes. This 
distinctive appearance sets them apart from the more common orange and black 
striped tigers.</s></s>

A chat between a curious user and an artificial intelligence assistant. The 
assistant gives helpful, detailed, and polite answers to the user's questions. 
USER: <im_start><image><im_end>
What can I cook with these ingredients? 

ASSISTANT: With the ingredients displayed on the table, you can prepare a 
delicious roast dinner. The meat, which is a large piece of beef, can be 
seasoned and cooked in the oven, while the vegetables, including carrots, 
potatoes, and onions, can be roasted alongside the meat. You can also prepare a
side dish with the potatoes, carrots, and onions, which can be served alongside
the roast dinner. The presence of a bowl of sauce suggests that you can use it 
as a dipping sauce or to enhance the flavors of the roast and vegetables. 
Overall, this combination of ingredients offers a hearty and flavorful meal 
that can be enjoyed with family and friends.</s></s>

USER: Could the recipe you suggested be included in a vegetarian diet? 

ASSISTANT: The recipe I suggested, which involves roasting a large piece of 
beef and vegetables, is not suitable for a vegetarian diet. The beef is the 
main protein source in the dish, and it is not suitable for vegetarians who 
avoid consuming meat. However, you can still create a vegetarian-friendly meal 
using the vegetables and sauce availableon the table. For example, you can 
prepare a vegetable roast with the carrots, potatoes, and onions, and serve it 
alongside a side of mashed potatoes or a vegetable-based sauce. This way, you 
can still enjoy the flavors and textures of the dish without including meat.</s></s>

USER: Can you suggest a vegetarian recipe with minimal modifications of the 
depicted ingredients? 

ASSISTANT: Certainly! Here's a vegetarian recipe that can be made using the 
ingredients available on the table:

Roasted Vegetable Medley with Sauce

Ingredients:

* Carrots
* Potatoes
* Onions
* Olive oil
* Salt
* Pepper
* Herbs (such as thyme, rosemary, or parsley)
* Sauce (optional)

Instructions:

1. Preheat your oven to 400°F (200°C).
2. Wash and peel the carrots, potatoes, and onions. Cut them into bite-sized 
pieces.
3. In a large bowl, toss the vegetables with olive oil, salt, and pepper.
4. Spread the vegetables evenly on a baking sheet lined with parchment paper.
5. Roast the vegetables in the preheated oven for 20-25 minutes, or until they 
are tender and slightly browned.
6. If desired, prepare a sauce by combining ingredients such as tomatoes, 
garlic, and herbs. You can use this sauce as a dipping sauce or to enhance the
flavors of the roasted vegetables.
7. Serve the roasted vegetable medley alongside a side of mashed potatoes or a 
vegetable-based sauce.

This vegetarian recipe allows you to enjoy the flavors and textures of the 
roasted vegetables without including meat. The sauce can be easily customized 
to suit your taste preferences, and the dish can be served alongside a variety 
of side dishes, such as mashed potatoes or a vegetable-based sauce.</s></s>

A chat between a curious user and an artificial intelligence assistant. The 
assistant gives helpful, detailed, and polite answers to the user's questions. 

USER: <im_start><image><im_end>
How can I renovate this café to make it look more vintage? 

ASSISTANT: To make the café look more vintage, you can consider the following 
changes:

1. Update the lighting: Replace the current lighting with vintage-style lamps 
or lanterns, which will create a warm and cozy atmosphere.

2. Add vintage decorations: Incorporate antique items, such as vintage clocks, 
artwork, or decorative plates, to create a nostalgic ambiance.

3. Use vintage furniture: Replace the current stools with vintage-style chairs 
or barstools, which can add character and charm to the space.

4. Incorporate greenery: Add more greenery, such as potted plants or vines, to 
create a lush and inviting atmosphere.

5. Update the bar: Replace the current bar with a vintage-style bar, complete 
with a vintage-inspired backsplash and countertop.

6. Use vintage-style glassware: Replace the current glassware with vintage-style
glasses, such as wine glasses, beer mugs, or cocktail shakers.
7. Add vintage-style signage: Replace the current signage with vintage-style 
menu boards or chalkboards, which can add a touch of nostalgia to the space.

8. Use vintage-style wallpaper or paint: Apply a vintage-style wallpaper or 
paint to the walls, which can create a unique and charming atmosphere.

By implementing these changes, the café will appear more vintage and inviting, 
creating a memorable experience for its patrons.</s></s>

A chat between a curious user and an artificial intelligence assistant. The 
assistant gives helpful, detailed, and polite answers to the user's questions. 

USER: <im_start><image><im_end>
Write an advertisment for this chair 

ASSISTANT: Introducing the modern and stylish black and wood chair, perfect for
any contemporary setting. This chair features a sleek black seat and a wooden 
base, creating a striking contrast against any background. Its minimalist 
design makes it a versatile addition to any room, whether it's used as a dining
chair, a side table, or a statement piece in a living space. The chair's sturdy
construction ensures it can withstand daily use, while its clean lines and 
sleek appearance add a touch of sophistication to any room. Upgrade your living
space with this stylish and functional chair today.</s></s>

USER: Write now an advertisement for the same chair but targeting cafes 

ASSISTANT: Attention café owners and design enthusiasts! Introducing the black
and wood chair, the perfect addition to your café's seating area. This stylish
and functional chair offers a modern touch to your establishment, with its 
sleek black seat and wooden base creating a striking contrast against any 
background. Its minimalist design makes it a versatile choice for any café 
setting, whether it's used as a dining chair, a side table, or a statement 
piece in a lounge area. The chair's sturdy construction ensures it can 
withstand daily use, while its clean lines and sleek appearance add a touch of 
sophistication to any room. Upgrade your café's ambiance with this stylish and 
functional chair today.</s></s>

A chat between a curious user and an artificial intelligence assistant. The 
assistant gives helpful, detailed, and polite answers to the user's questions. 

USER: <im_start><image><im_end>
Would the fish depicted in the image float if thrown in water? Think step by 
step. 

ASSISTANT: The fish depicted in the image is a large white fish sculpture or 
statue, which is lying on the ground on a brick walkway near a body of water. 
If thrown into the water, the fish would not float because it is a solid, 
inanimate object. It would sink to the bottom of the water, as it is not 
buoyant due to its composition and size. The fish's position on the ground and 
its lack of buoyancy make it impossible for it to float in water.</s></s>

USER: What material could be used to make a fish sculpture that floats on 
water? 

ASSISTANT: To make a fish sculpture that floats on water, one could use a 
lightweight, buoyant material such as expanded polystyrene foam or polyethylene
foam. These materials are commonly used for making buoyant objects like life 
jackets, flotation devices, and fishing floats. By shaping the foam into the 
desired fish form, it would be able to float on the water's surface, 
simulating the behavior of a real fish.</s></s>

A chat between a curious user and an artificial intelligence assistant. The 
assistant gives helpful, detailed, and polite answers to the user's questions.

USER: <im_start><image><im_end>
Would the fish depicted in the image float if thrown in water? 

ASSISTANT: No, the fish depicted in the image would not float if thrown in 
water. It is a large, white, stone fish sculpture, which is not a real fish 
and does not have the buoyancy properties of a natural fish.</s></s>

A chat between a curious user and an artificial intelligence assistant. The 
assistant gives helpful, detailed, and polite answers to the user's questions. 

USER: <im_start><image><im_end>
How many car are inside the parking lot? 

ASSISTANT: There are several cars parked inside the parking lot.</s></s>

USER: List the numbers of the parking spots occupied by cars 

ASSISTANT: The parking spots occupied by cars are 66, 67, 68, 69, 70, and 71.</s></s>

A chat between a curious user and an artificial intelligence assistant. The 
assistant gives helpful, detailed, and polite answers to the user's questions. 

USER: <im_start><image><im_end>
Tell me the species of the fish in this image 

ASSISTANT: The fish in this image is a desert fish, which is a species adapted 
to living in desert environments.</s></s>