soroushjavdan

LLM4CodeSummarization

DenseRetrieval

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

shortformer

Code for the Shortformer model, from the ACL 2021 paper by Ofir Press, Noah A. Smith and Mike Lewis.

bleurt

BLEURT is a metric for Natural Language Generation based on transfer learning.

amazon-denseclus

Clustering for mixed-type data

Clustering-Mixed-Data

A repository with various methods for clustering mixed datasets in python

interpretable_clustering

Interpretable Clustering: Voronoi Feature Importance

CodeXGLUE

CodeXGLUE

gumtree

An awesome code differencing tool

athena-rr

A Transformer-based Response Evaluator for Open-Domain Spoken Conversation

beams-commit-message-checker

Check commit message quality according to Chris Beams' guideline using machine learning, including "what" and "why" vs "how".

seqeval

A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)

BARTScore

BARTScore: Evaluating Generated Text as Text Generation

commitgen

Code and data for the paper "A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes"

commit_message_generation

🌟 replication package for 📜 From Commit Message Generation to History-Aware Commit Message Completion, ASE 2023

guidance

A guidance language for controlling large language models.

setfit

Efficient few-shot learning with Sentence Transformers

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

MOSS-RLHF

MOSS-RLHF

LMOps

General technology for enabling AI capabilities w/ LLMs and MLLMs

convert_checkpoint_to_lsg

Efficient Attention for Long Sequence Processing

torchscale

Transformers at any scale

attention_with_linear_biases

Code for the ALiBi method for transformer language models (ICLR 2022)

MetaAdaptRank

Code and data of the ACL 2021 paper: Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision

anserini

Anserini is a Lucene toolkit for reproducible information retrieval research

pygrok

python implementation of jordansissel's grok regular expression library

Extractive-Summarization-of-a-News-Corpus-Using-BERT

MsMarco

Re-ranking task using MS MARCO dataset and Hugging Face library

MetaLearning-TF2.0

Meta learning framework with Tensorflow 2.0