LLaVA Vision-Language Model

# Clone repository
git clone https://github.com/haotian-liu/LLaVA
cd LLaVA

# Install
pip install -e .

from llava.model.builder import load_pretrained_model
from llava.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token
from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN
from llava.conversation import conv_templates
from PIL import Image
import torch

# Load model
model_path = "liuhaotian/llava-v1.5-7b"
tokenizer, model, image_processor, context_len = load_pretrained_model(
    model_path=model_path,
    model_base=None,
    model_name=get_model_name_from_path(model_path)
)

# Load image
image = Image.open("image.jpg")
image_tensor = process_images([image], image_processor, model.config)
image_tensor = image_tensor.to(model.device, dtype=torch.float16)

# Create conversation
conv = conv_templates["llava_v1"].copy()
conv.append_message(conv.roles[0], DEFAULT_IMAGE_TOKEN + "\nWhat is in this image?")
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()

# Generate response
input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).to(model.device)

with torch.inference_mode():
    output_ids = model.generate(
        input_ids,
        images=image_tensor,
        do_sample=True,
        temperature=0.2,
        max_new_tokens=512
    )

response = tokenizer.decode(output_ids[0], skip_special_tokens=True).strip()
print(response)

# Load different models
model_7b = "liuhaotian/llava-v1.5-7b"
model_13b = "liuhaotian/llava-v1.5-13b"
model_34b = "liuhaotian/llava-v1.6-34b"

# 4-bit quantization for lower VRAM
load_4bit = True  # Reduces VRAM by ~4×

# Single image query
python -m llava.serve.cli \
    --model-path liuhaotian/llava-v1.5-7b \
    --image-file image.jpg \
    --query "What is in this image?"

# Multi-turn conversation
python -m llava.serve.cli \
    --model-path liuhaotian/llava-v1.5-7b \
    --image-file image.jpg
# Then type questions interactively

# Launch Gradio interface
python -m llava.serve.gradio_web_server \
    --model-path liuhaotian/llava-v1.5-7b \
    --load-4bit  # Optional: reduce VRAM

# Access at http://localhost:7860

# Initialize conversation
conv = conv_templates["llava_v1"].copy()

# Turn 1
conv.append_message(conv.roles[0], DEFAULT_IMAGE_TOKEN + "\nWhat is in this image?")
conv.append_message(conv.roles[1], None)
response1 = generate(conv, model, image)  # "A dog playing in a park"

# Turn 2
conv.messages[-1][1] = response1  # Add previous response
conv.append_message(conv.roles[0], "What breed is the dog?")
conv.append_message(conv.roles[1], None)
response2 = generate(conv, model, image)  # "Golden Retriever"

# Turn 3
conv.messages[-1][1] = response2
conv.append_message(conv.roles[0], "What time of day is it?")
conv.append_message(conv.roles[1], None)
response3 = generate(conv, model, image)

question = "Describe this image in detail."
response = ask(model, image, question)

question = "How many people are in the image?"
response = ask(model, image, question)

question = "List all the objects you can see in this image."
response = ask(model, image, question)

question = "What is happening in this scene?"
response = ask(model, image, question)

question = "What is the main topic of this document?"
response = ask(model, document_image, question)

# Stage 1: Feature alignment (558K image-caption pairs)
bash scripts/v1_5/pretrain.sh

# Stage 2: Visual instruction tuning (150K instruction data)
bash scripts/v1_5/finetune.sh

# 4-bit quantization
tokenizer, model, image_processor, context_len = load_pretrained_model(
    model_path="liuhaotian/llava-v1.5-13b",
    model_base=None,
    model_name=get_model_name_from_path("liuhaotian/llava-v1.5-13b"),
    load_4bit=True  # Reduces VRAM ~4×
)

# 8-bit quantization
load_8bit=True  # Reduces VRAM ~2×

from langchain.llms.base import LLM

class LLaVALLM(LLM):
    def _call(self, prompt, stop=None):
        # Custom LLaVA inference
        return response

llm = LLaVALLM()

import gradio as gr

def chat(image, text, history):
    response = ask_llava(model, image, text)
    return response

demo = gr.ChatInterface(
    chat,
    additional_inputs=[gr.Image(type="pil")],
    title="LLaVA Chat"
)
demo.launch()