farizikhwantri

llama

Inference code for LLaMA models

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

codon

A high-performance, zero-overhead, extensible Python compiler using LLVM

llama-recipes

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger

trl

Train transformer language models with reinforcement learning.

fairscale

PyTorch extensions for high performance and large scale training.

RL4LMs

A modular RL library to fine-tune language models to human preferences

pystack

🔍 🐍 Like pstack but for Python!

curated-transformers

🤖 A PyTorch library of curated Transformer models and their composable components

the-story-of-heads

This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" and the ACL 2021 paper "Analyzing Source and Target Contributions to NMT Predictions".

Diffusion-BERT

ACL'2023: DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models

Physics-Aware-Training

Instructional implementation of Physics-Aware Training (PAT) with demonstrations on simulated experiments.

xl-sum

This repository contains the code, data, and models of the paper titled "XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages" published in Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021.

trak

A fast, effective data attribution method for neural networks in PyTorch

eraserbenchmark

A benchmark for understanding and evaluating rationales: http://www.eraserbenchmark.com/

jestimator

Amos optimizer with JEstimator lib.

brmp

Bayesian Regression Models in Pyro

backpacks-flash-attn

The original Backpack Language Model implementation, a fork of FlashAttention

helm

torchscale

Transformers at any scale

time_interpret

Unified Model Interpretability Library for Time Series

tokenizations

Robust and Fast tokenizations alignment library for Rust and Python https://tamuhey.github.io/tokenizations/

learning-scaffold

This is the official implementation for the paper "Learning to Scaffold: Optimizing Model Explanations for Teaching"

robust-attribution-regularization

Robust Attribution Regularization

DiffuSum

codebase for paper DiffuSum: Generation Enhanced Extractive Summarization with Diffusion

cogbert

autoalign

Align then Summarize: Automatic Alignment Methods for Summarization Corpus Creation

WebQAmGaze

WebQAmGaze, a multilingual low-cost eye-tracking dataset (using webgazer)

human-interpretation-saliency