alexrame

llama

Inference code for LLaMA models

ColossalAI

Making large AI models cheaper, faster and more accessible

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

alpaca-lora

Instruct-tune LLaMA on consumer hardware

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

FlexGen

Running large language models on a single GPU for throughput-oriented scenarios.

nebuly

The user analytics platform for LLMs

trl

Train transformer language models with reinforcement learning.

acme

A library of reinforcement learning components and agents

hh-rlhf

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

prismer

The implementation of "Prismer: A Vision-Language Model with Multi-Task Experts".

Dromedary

Dromedary: towards helpful, ethical and reliable LLMs.

alpaca_farm

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

cabrita

Finetuning InstructLLaMA with portuguese data

minimal-llama

ConstitutionalHarmlessnessPaper

git-theta

git extension for {collaborative, communal, continual} model development

PreferenceTransformer

Preference Transformer: Modeling Human Preferences using Transformers for RL (ICLR2023 Accepted)

catwalk

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

ties-merging

machiavelli

cbtm

Code repository for the c-BTM paper

ELM

[ICML 2023] Exploring the Benefits of Training Expert Language Models over Instruction Tuning

ExpansionNet_v2

Implementation code of the work "Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning"

tangent_task_arithmetic

Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".

rewardedsoups

Rewarded soups official implementation

weather4cast-2022

WeatherFusionNet - our solution to the NeurIPS 2022 Weather4cast competition

Robust_Weight_Signatures

[ICML 2023] "Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?" by Ruisi Cai, Zhenyu Zhang, Zhangyang Wang

iclmlp

Experiments for "A Closer Look at In-Context Learning under Distribution Shifts"

erm_plusplus