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

# Define your input image and instruction here:
## image 
url = "https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/bRu85CWwP9129bSCRzos2.png"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")

instruction = "What's in the image?"

model_path='AdaptLLM/food-LLaVA-NeXT-Llama3-8B'

# =========================== Do NOT need to modify the following ===============================
# Load the processor
processor = LlavaNextProcessor.from_pretrained(model_path)

# Define image token
image_token = "<|reserved_special_token_4|>"

# Format the prompt
prompt = (
    f"<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n"
    f"You 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."
    f"<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n"
    f"{image_token}\n{instruction}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
)

# Load the model
model = LlavaNextForConditionalGeneration.from_pretrained(model_path, torch_dtype=torch.float16, device_map="auto")

# Prepare inputs and generate output
inputs = processor(images=image, text=prompt, return_tensors="pt").to(model.device)
answer_start = int(inputs["input_ids"].shape[-1])
output = model.generate(**inputs, max_new_tokens=512)

# Decode predictions
pred = processor.decode(output[0][answer_start:], skip_special_tokens=True)
print(pred)

2. To Evaluate Any MLLM on Domain-Specific Benchmarks

Refer to the food-VQA-benchmark to reproduce our results and evaluate many other MLLMs on domain-specific benchmarks.

3. To Reproduce this Domain-Adapted MLLM

See Post-Train Guide to adapt MLLMs to domains.

Citation

If you find our work helpful, please cite us.

Adapt MLLM to Domains (EMNLP 2025 Findings)

bibtex

@article{adamllm,
  title={On Domain-Adaptive Post-Training for Multimodal Large Language Models},
  author={Cheng, Daixuan and Huang, Shaohan and Zhu, Ziyu and Zhang, Xintong and Zhao, Wayne Xin and Luan, Zhongzhi and Dai, Bo and Zhang, Zhenliang},
  journal={arXiv preprint arXiv:2411.19930},
  year={2024}
}

Adapt LLM to Domains (ICLR 2024)

bibtex

@inproceedings{
cheng2024adapting,
title={Adapting Large Language Models via Reading Comprehension},
author={Daixuan Cheng and Shaohan Huang and Furu Wei},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=y886UXPEZ0}
}