GIST-all-MiniLM-L6-v2

import torch.nn.functional as F
from sentence_transformers import SentenceTransformer

revision = None  # Replace with the specific revision to ensure reproducibility if the model is updated.

model = SentenceTransformer("avsolatorio/GIST-all-MiniLM-L6-v2", revision=revision)

texts = [
    "Illustration of the REaLTabFormer model. The left block shows the non-relational tabular data model using GPT-2 with a causal LM head. In contrast, the right block shows how a relational dataset's child table is modeled using a sequence-to-sequence (Seq2Seq) model. The Seq2Seq model uses the observations in the parent table to condition the generation of the observations in the child table. The trained GPT-2 model on the parent table, with weights frozen, is also used as the encoder in the Seq2Seq model.",
    "Predicting human mobility holds significant practical value, with applications ranging from enhancing disaster risk planning to simulating epidemic spread. In this paper, we present the GeoFormer, a decoder-only transformer model adapted from the GPT architecture to forecast human mobility.",
    "As the economies of Southeast Asia continue adopting digital technologies, policy makers increasingly ask how to prepare the workforce for emerging labor demands. However, little is known about the skills that workers need to adapt to these changes"
]

# Compute embeddings
embeddings = model.encode(texts, convert_to_tensor=True)

# Compute cosine-similarity for each pair of sentences
scores = F.cosine_similarity(embeddings.unsqueeze(1), embeddings.unsqueeze(0), dim=-1)

print(scores.cpu().numpy())

Epochs = 40
Warmup ratio = 0.1
Learning rate = 5e-6
Batch size = 16
Checkpoint step = 102000
Contrastive loss temperature = 0.01

@article{solatorio2024gistembed,
    title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
    author={Aivin V. Solatorio},
    journal={arXiv preprint arXiv:2402.16829},
    year={2024},
    URL={https://arxiv.org/abs/2402.16829}
    eprint={2402.16829},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}