-
Reference implementation for DPO (Direct Preference Optimization)
-
emulated-fine-tuning Public
An Emulator for Fine-tuning Large Language Models using Small Language Models
-
-
-
detect-gpt Public
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
-
-
macaw Public
Code for "Offline Meta-Reinforcement Learning with Advantage Weighting" [ICML 2021]
-
-
-
serac Public
Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model
-
-
higher Public
Forked from facebookresearch/higherhigher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
-
macaw-min Public
Clean, extensible implementation of MACAW [ICML 2021]
-
transformers Public
Forked from huggingface/transformers🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
Python Apache License 2.0 UpdatedSep 23, 2021 -
-
KnowledgeEditor Public
Forked from nicola-decao/KnowledgeEditorCode for Editing Factual Knowledge in Language Models
Python MIT License UpdatedJul 2, 2021 -
-
-
-
oyster Public
Forked from katerakelly/oysterImplementation of Efficient Off-policy Meta-learning via Probabilistic Context Variables (PEARL)
Python MIT License UpdatedJan 10, 2020 -
world-models Public
Forked from ctallec/world-modelsReimplementation of World-Models (Ha and Schmidhuber 2018) in pytorch
Python MIT License UpdatedSep 3, 2019
{{ message }}