GitHub / DolbyUUU / Reinforcement-Calibration-SimCSE
Reinforcement Calibration SimCSE, combining contrastive learning, artificial potential fields, perceptual loss, and RLHF to achieve improved Semantic Textual Similarity (STS) embeddings. PyTorch-based implementations of PerceptualBERT and ForceBasedInfoNCE, along with fine-tuning capabilities via RLHF and evaluation using SentEval.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DolbyUUU%2FReinforcement-Calibration-SimCSE
PURL: pkg:github/DolbyUUU/Reinforcement-Calibration-SimCSE
Stars: 0
Forks: 0
Open issues: 0
License: None
Language: Python
Size: 371 KB
Dependencies parsed at: Pending
Created at: 7 months ago
Updated at: 7 months ago
Pushed at: 7 months ago
Last synced at: 7 months ago
Topics: artificial-potential-fields, contrastive-learning, nlp, rlhf, self-supervised-learning, semantic-textual-similarity, sentence-embeddings, senteval, simcse