eugeneyan

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

dspy

DSPy: The framework for programming—not prompting—foundation models

semantic

Parsing, analyzing, and comparing source code across many languages

trl

Train transformer language models with reinforcement learning.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

ml-ferret

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

axolotl

Go ahead and axolotl questions

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

instructor

structured outputs for llms

captum

Model interpretability and understanding for PyTorch

trlx

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

alignment-handbook

Robust recipes to align language models with human and AI preferences

higgsfield

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

picoGPT

An unnecessarily tiny implementation of GPT-2 in NumPy.

CTranslate2

Fast inference engine for Transformer models

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

lm-human-preferences

Code for the paper Fine-Tuning Language Models from Human Preferences

hallucination-leaderboard

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

summarize-from-feedback

Code for "Learning to summarize from human feedback"

obsidian-kindle-plugin

Sync your Kindle notes and highlights directly into your Obsidian vault

bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

Platypus

Code for fine-tuning Platypus fam LLMs using LoRA

llm_distillation_playbook

Best practices for distilling large language models.

evol-instruct

n-levels-of-rag

datagen

a pipeline for using api calls to agnostically convert unstructured data into structured training data

visualizing-finetunes

get-lambda

Use Actions to acquire those precious lambda GPUs

swe-study-group

Code for the SWE study group