The model is trained to generate document embeddings for math research papers and use the embeddings to find similar ranked documents.

LLaMa model that is trained with contrastive learning for sequence classification.

from transformers import AutoTokenizer, AutoModel import torch

sentences = ["Hello Who are you?", "I am fine thank you"]

tokenizer = AutoTokenizer.from_pretrained('AnkitSatpute/Llama-3.1-ReRank-AllFTbtAbstr')

model = AutoModel.from_pretrained('AnkitSatpute/Llama-3.1-ReRank-AllFTbtAbstr')

model.eval()

with torch.no_grad():

model_output = model(**encoded_input)

sentence_embeddings = model_output[0][:, 0]

sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1)

print("Sentence embeddings:", sentence_embeddings)