Eric Wallace

rag-convincingness. Python

Poisoning-Instruction-Tuned-Models. Python

onestep-extraction. Python

open_llama. OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

EasyLM. Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

long_tail_knowledge. Repo for the paper "Large Language Models Struggle to Learn Long-Tail Knowledge"

incoder. Generative model for code infilling and synthesis

LM_Memorization. Training data extraction on GPT-2

DPR. Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

aiorobinhood. Asynchronous Robinhood HTTP client built using asyncio and aiohttp

few-shot-learning. Few-shot Learning of GPT-3

interpretability-tutorial-emnlp2020. Materials for the EMNLP 2020 Tutorial on "Interpreting Predictions of NLP Models"

BERT-related-papers. BERT-related papers

pathologies. EMNLP 2019 "Pathologies of Neural Models Make Interpretations Difficult"

universal-triggers. Universal Adversarial Triggers for Attacking and Analyzing NLP (EMNLP 2019)

FewRel. A Large-Scale Few-Shot Relation Extraction Dataset

trfl. TensorFlow Reinforcement Learning

loss-landscape. Code for visualizing the loss landscape of neural nets

jiant. jiant is an nlp toolkit

model-subspace. Pytorch hooks to save the subspace associated with a model so it can be used as input to SVCCA.

finetune. Scikit-learn style model finetuning for NLP

pytorch-maml-rl. Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch

sears. Code for "Semantically Equivalent Adversarial Rules for Debugging NLP Models"

gensen. Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning

DifferentiableNeuralComputer. Optimized Differentiable Neural Computer In Chainer

ContextualDecomposition. Demo for method introduced in "Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs"

WorldModels. Full World Models Implementation in Chainer

scalable_agent. A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.

scpn. syntactically controlled paraphrase networks

kuro. Experiment manager for ML experiments

ray. Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

rl-car. Reinforcement learning for Robotics with V-Rep

LEAR. Specialising Word Vectors for Lexical Entailment

pysc2-RLagents. Notes and scripts for SC2LE released by DeepMind and Blizzard, more details [here](https://github.com/deepmind/pysc2).

Reinforcement-learning-with-tensorflow. Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学

deeplearning-papernotes. Summaries and notes on Deep Learning research papers

reinforcement-learning. Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

summary. summaries of all the papers I read

pytorch-rl. Deep Reinforcement Learning with pytorch & visdom

pretrained.ml. [DEPRECATED] Compilation of pre-trained deep learning models with demos and code.

test-tube. Python library to easily log experiments and parallelize hyperparameter search for neural networks

autocraft. AI for SCII built with deepminds pysc2 package

DeepMoji. State-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc.

nlp_tasks. Natural Language Processing Tasks and References

the-incredible-pytorch. The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

awd-lstm-lm. LSTM and QRNN Language Model Toolkit for PyTorch

ELL. Embedded Learning Library

EdgeML. This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.

np-to-tf-embeddings-visualiser. Quick function to go from a dictionary of sets of (images, labels, feature vectors) to checkpoints that can be opened in Tensorboard