jamesliu

nanoPPO

An efficient implementation of the Proximal Policy Optimization (PPO) algorithm with linear and attention policy for reinforcement learning.

nanoDPO

A nimble and innovative implementation of the Direct Preference Optimization (DPO) algorithm with Causal Transformer and LSTM model, inspired by the paper of DPO in fine-tuning unsupervised Language Models

nanoTransformer

A PyTorch-based featuring an efficiently implemented Transformer model. The core of our attention mechanisms is powered by torch.einsum, ensuring clean, readable, and highly optimized tensor operations.

nChain

a flexible and efficient implementation to create LLM bots over extensible dataset.

amago

a simple and scalable agent for training adaptive policies with sequence-based RL

anthropic-cookbook

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

autogen

Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

bayjarvis-app

devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

lag-llama

litgpt

Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

LLaMA-Factory

Unify Efficient Fine-tuning of 100+ LLMs

llm-foundry

LLM training code for MosaicML foundation models

llm.c

LLM training in simple, raw C/CUDA

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

llmtime

long-range-arena

Long Range Arena for Benchmarking Efficient Transformers

magicoder

Magicoder: Source Code Is All You Need

mamba

network_architecture

OpenMoE

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

package-stats

pypi-bayjarvis-packages

recommendation_system

routerbench

The code for the paper ROUTERBENCH: A Benchmark for Multi-LLM Routing System

ScaleLLM

A high-performance inference system for large language models, designed for production environments.

SPIN

The official implementation of Self-Play Fine-Tuning (SPIN)

Time-LLM

[ICLR 2024] Official implementation of "Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Transformers_Are_What_You_Dont_Need

The best repository showing why transformers don’t work in time series forecasting and showcasing the best SOTA non transformer models.