LLM2CLIP EVA02 L 14 336

🚀 LLM2CLIP: Extending the Capability Boundaries of CLIP through Large Language Models

This project proposes LLM2CLIP, a novel approach leveraging LLMs to unlock CLIP’s potential, significantly improving performance in cross - modal tasks.

🚀 Quick Start

In this paper, we propose LLM2CLIP, a novel approach that embraces the power of LLMs to unlock CLIP’s potential. By fine - tuning the LLM in the caption space with contrastive learning, we extract its textual capabilities into the output embeddings, significantly improving the output layer’s textual discriminability. We then design an efficient training process where the fine - tuned LLM acts as a powerful teacher for CLIP’s visual encoder. Thanks to the LLM’s presence, we can now incorporate longer and more complex captions without being restricted by vanilla CLIP text encoder’s context window and ability limitations. Our experiments demonstrate that this approach brings substantial improvements in cross - modal tasks. Our method directly boosted the performance of the previously SOTA EVA02 model by 16.5% on both long - text and short - text retrieval tasks, transforming a CLIP model trained solely on English data into a state - of - the - art cross - lingual model. Moreover, when integrated into multi - modal training with models like Llava 1.5, it consistently outperformed CLIP across nearly all benchmarks, demonstrating comprehensive performance improvements.

✨ Features

LLM2CLIP performance

⚠️ Important Note

It's important to note that all results presented in the paper are evaluated using PyTorch weights. There may be differences in performance when using Hugging Face (hf) models.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

Go to GitHub

import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"

from transformers import AutoModel, AutoConfig, AutoTokenizer
from eva_clip import create_model_and_transforms
from llm2vec import LLM2Vec
from PIL import Image
import torch


model, _, preprocess_val  = create_model_and_transforms('EVA02-CLIP-L-14-336', force_custom_clip=True)
ckpt = torch.load('LLM2CLIP-EVA02-L-14-336.pt')
model.load_state_dict(ckpt)
model = model.cuda().eval()

llm_model_name = 'microsoft/LLM2CLIP-Llama-3-8B-Instruct-CC-Finetuned'
config = AutoConfig.from_pretrained(
    llm_model_name, trust_remote_code=True
)
llm_model = AutoModel.from_pretrained(llm_model_name, torch_dtype=torch.bfloat16, config=config, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(llm_model_name)
llm_model.config._name_or_path = 'meta-llama/Meta-Llama-3-8B-Instruct' #  Workaround for LLM2VEC
l2v = LLM2Vec(llm_model, tokenizer, pooling_mode="mean", max_length=512, doc_max_length=512)

image_path = "CLIP.png"
captions = ["a diagram", "a dog", "a cat"]

image = preprocess_val(Image.open(image_path)).cuda().unsqueeze(dim=0)
text_features = l2v.encode(captions, convert_to_tensor=True).to('cuda')

with torch.no_grad(), torch.cuda.amp.autocast():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text_features)

    image_features /= image_features.norm(dim=-1, keepdim=True)
    text_features /= text_features.norm(dim=-1, keepdim=True)

    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs)

📚 Documentation

Model Details

📄 License

The project is licensed under the Apache - 2.0 license.

BibTeX & Citation

@misc{huang2024llm2clippowerfullanguagemodel,
      title={LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation}, 
      author={Weiquan Huang and Aoqi Wu and Yifan Yang and Xufang Luo and Yuqing Yang and Liang Hu and Qi Dai and Xiyang Dai and Dongdong Chen and Chong Luo and Lili Qiu},
      year={2024},
      eprint={2411.04997},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2411.04997}, 
}