Go ahead and axolotl questions

A repository for transformer critique learning and generation

LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA

A Ray-based High-performance LLaMA2 RLHF framework

Safe-RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Reference implementation for DPO (Direct Preference Optimization)

Customizable implementation of the self-instruct paper.

A high-throughput and memory-efficient inference and serving engine for LLMs

Large Language Model Text Generation Inference

open-source observability for LLM applications

PFRL: a PyTorch-based deep reinforcement learning library

Repository for bittensor validators

Making large AI models cheaper, faster and more accessible

⚡ Building applications with LLMs through composability ⚡

⛓️ LangFlow is a UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows.

Train llama with lora on one 4090 and merge weight of lora to work as stanford alpaca.

Code for reproducing the Stanford Alpaca InstructLLaMA result on consumer hardware

Language Modeling with the H3 State Space Model

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