LLM2CLIP Llama 3 8B Instruct CC Finetuned

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

This paper presents LLM2CLIP, a novel approach leveraging the power of LLMs to unlock CLIP's potential. By fine - tuning the LLM in the caption space with contrastive learning, it enhances the output layer's textual discriminability. An efficient training process is designed where the fine - tuned LLM serves as a teacher for CLIP's visual encoder. This approach significantly improves cross - modal tasks, boosts the performance of existing models, and enables cross - lingual capabilities.

🚀 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

• Enhanced Textual Discriminability: By fine - tuning the LLM in the caption space with contrastive learning, the output layer's textual discriminability is significantly improved.
• Efficient Training Process: The fine - tuned LLM serves as a powerful teacher for CLIP's visual encoder, enabling the use of longer and more complex captions.
• Improved Cross - Modal Performance: Substantial improvements in cross - modal tasks, such as boosting the performance of the EVA02 model and enabling cross - lingual capabilities.

📦 Installation

No specific installation steps are provided in the original README.

💻 Usage Examples

Basic Usage

Image Embeddings

from PIL import Image
from transformers import AutoModel
from transformers import CLIPImageProcessor
import torch

image_path = "CLIP.png"
model_name_or_path = "LLM2CLIP-Openai-L-14-336" # or /path/to/local/LLM2CLIP-Openai-L-14-336

processor = CLIPImageProcessor.from_pretrained("openai/clip-vit-large-patch14-336")
model = AutoModel.from_pretrained(
    model_name_or_path, 
    torch_dtype=torch.float16,
    trust_remote_code=True).to('cuda').eval()

image = Image.open(image_path)
input_pixels = processor(images=image, return_tensors="pt").pixel_values.to('cuda')

with torch.no_grad(), torch.cuda.amp.autocast():
    outputs = model.get_image_features(input_pixels)

Retrieval

from PIL import Image
from transformers import AutoModel, AutoConfig, AutoTokenizer
from transformers import CLIPImageProcessor
import torch
from llm2vec import LLM2Vec
import os

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

processor = CLIPImageProcessor.from_pretrained("openai/clip-vit-large-patch14-336")
model_name_or_path = "microsoft/LLM2CLIP-Openai-L-14-336" # or /path/to/local/LLM2CLIP-Openai-L-14-336
model = AutoModel.from_pretrained(
    model_name_or_path, 
    torch_dtype=torch.bfloat16,
    trust_remote_code=True).to('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)

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

image = Image.open(image_path)
input_pixels = processor(images=image, return_tensors="pt").pixel_values.to('cuda')
text_features = l2v.encode(captions, convert_to_tensor=True).to('cuda')

with torch.no_grad(), torch.cuda.amp.autocast():
    image_features = model.get_image_features(input_pixels)
    text_features = model.get_text_features(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

LLM2CLIP performance

Model Details

📄 License

This 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}, 
}