lzy37ld

-token-loss-token-

111

alpaca-lora

Instruct-tune LLaMA on consumer hardware

attack_sql

awesome-instruction-learning

Papers and Datasets on Instruction Learning / Instruction Tuning. ✨✨✨

catwalk

This project studies the performance and robustness of language models and task-adaptation methods.

dataset_difficulty_v_information

"Understanding Dataset Difficulty with V-Usable Information" (ICML 2022, outstanding paper)

debug_atlas

llmattack

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

lzy37ld.github.io

lzy_autodan

openai-cookbook

Examples and guides for using the OpenAI API

papers-attack

promptsource

Toolkit for creating, sharing and using natural language prompts.

pythia

python-package-template

A template repo for Python packages

quinine

A library to create and manage configuration files, especially for machine learning projects.

starter-academic

surface-form-competition-has-a-way-to-calculate-gpt3-probs-

trlx

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

web_malicisous