robertalanm

safe-rlhf

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

alpaca-weight

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

CodingSubnet

langchain

⚡ Building applications with LLMs through composability ⚡

reward-modeling

text-generation-inference

Large Language Model Text Generation Inference

trlx

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

airoboros

Customizable implementation of the self-instruct paper.

alpaca-lora

Code for reproducing the Stanford Alpaca InstructLLaMA result on consumer hardware

autocrit

A repository for transformer critique learning and generation

axolotl

Go ahead and axolotl questions

ColossalAI

Making large AI models cheaper, faster and more accessible

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

discord

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

H3

Language Modeling with the H3 State Space Model

langflow

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

langfuse

open-source observability for LLM applications

langfuse-python

llama-trl

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

minimal-llama

OpenLLaMA2

A Ray-based High-performance LLaMA2 RLHF framework

opentensorAI-connector-template

orca

Experiments into reproducing orca

pfrl

PFRL: a PyTorch-based deep reinforcement learning library

raodottown

website for rao.town

substrate-indexer

indexer for substrate chain (bt)

t-jepa

validators

Repository for bittensor validators

vllm

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