samutamm

makemore

An autoregressive character-level language model for making more things

autogen

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

optimum-quanto

A pytorch quantization backend for optimum

OpenDevin

🐚 OpenDevin: Code Less, Make More

ann-benchmarks

Benchmarks of approximate nearest neighbor libraries in Python

hnsw

HNSW tutorial

gpt4all

GPT4All: Chat with Local LLMs on Any Device

axolotl

Go ahead and axolotl questions

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

llama-cpp-python

Python bindings for llama.cpp

neural-ranking-kd

Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation

annoy

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

llm-routing-agent

Agent that routes to different tools - LLM classifier SDK

rank_bm25

A Collection of BM25 Algorithms in Python

yfinance

Download market data from Yahoo! Finance's API

transformers-interpret

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

eli5

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

bandits

Python library for Multi-Armed Bandits

trl

Train transformer language models with reinforcement learning.

levenpandas

fuzzy merge pandas dataframes with Levenshtein distance and parallel support

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

lamini

selfcheckgpt

SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

langchain

🦜🔗 Build context-aware reasoning applications

guardrails

Adding guardrails to large language models.

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

LLMDrift

awesome-totally-open-chatgpt

A list of totally open alternatives to ChatGPT

NeMo-Guardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

TVSM-dataset