random search, hill climbing, policy gradient

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch

An implementation of PPO in Pytorch

A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.

LLM KV cache compression made easy

Curated list of datasets and tools for post-training.

LLM101n: Let's build a Storyteller

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

An autoregressive character-level language model for making more things

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

A simple, performant and scalable Jax LLM!

PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"

LLM inference in C/C++

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-re…

Jlama is a modern LLM inference engine for Java

Inference code for Llama models

Implementation of Direct Preference Optimization

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

structured outputs for llms

[NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

Implementation for MatMul-free LM.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

Code for "Supermasks in Superposition"

Collection of reinforcement learning algorithms

Implementation of the "Online learning of long-range dependencies" paper, NeurIPS 2023

🦄 Unitxt is a Python library for enterprise-grade evaluation of AI performance, offering the world's largest catalog of tools and data for end-to-end AI benchmarking