Evaluate your LLM's response with Prometheus and GPT4 💯

Unsupervised text tokenizer for Neural Network-based text generation.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Official inference library for Mistral models

Repo for the paper "Detecting Logical Fallacies: From Quiz to Climate Change News" (2021)

WinoGrande: An Adversarial Winograd Schema Challenge at Scale

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

DadmaTools is a Persian NLP tools developed by Dadmatech Co.

SemEval2024-task8: Multidomain, Multimodel and Multilingual Machine-Generated Text Detection

M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection

A tool for extracting plain text from Wikipedia dumps

18.06 course at MIT

Open source code for paper "Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere" ICML 2020

MoCo with Alignment and Uniformity Loss.

PromptBERT: Improving BERT Sentence Embeddings with Prompts

TensorFlow implementation of On the Sentence Embeddings from Pre-trained Language Models (EMNLP 2020)

A prize for finding tasks that cause large language models to show inverse scaling

List of AI Residency Programs

TensorFlow code and pre-trained models for BERT

Multi-Task Deep Neural Networks for Natural Language Understanding

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

State-of-the-Art Text Embeddings

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

The implementation of DeBERTa

Datasets, tools, and benchmarks for representation learning of code.

A free and unlimited python API for google translate.

Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle