joelrorseth

llama.cpp

LLM inference in C/C++

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

xgboost

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

guidance

A guidance language for controlling large language models.

ml-stable-diffusion

Stable Diffusion with Core ML on Apple Silicon

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

EdgeGPT

Reverse engineered API of Microsoft's Bing Chat AI

ai-notes

notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references under the /Resources folder.

lit

The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

eli5

A library for debugging/inspecting machine learning classifiers and explaining their predictions

ColBERT

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

TransformerLens

A library for mechanistic interpretability of GPT-style language models

automated-interpretability

Treasure-of-Transformers

💁 Awesome Treasure of Transformers Models for Natural Language processing contains papers, videos, blogs, official repo along with colab Notebooks. 🛫☑️

bleurt

BLEURT is a metric for Natural Language Generation based on transfer learning.

rome

Locating and editing factual associations in GPT (NeurIPS 2022)

memit

Mass-editing thousands of facts into a transformer memory (ICLR 2023)

landmark-attention

Landmark Attention: Random-Access Infinite Context Length for Transformers

honest_llama

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

tuned-lens

Tools for understanding how transformer predictions are built layer-by-layer

rax

Rax is a Learning-to-Rank library written in JAX.

lost-in-the-middle

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

ToolQA

ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.

FlexNeuART

Flexible classic and NeurAl Retrieval Toolkit

baukit

polyjuice

belief-localization

This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Can Be Injected in Language Models."

CNN-Units-in-NLP

:scissors: Repository for our ICLR 2019 paper: Discovery of Natural Language Concepts in Individual Units of CNNs