tianbingsz Goto Github PK

alignment-handbook

Robust recipes for to align language models with human and AI preferences

alpaca_farm

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

codingpractise

c++ coding exercise

d3po

[CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"

dart

deep-learning-pytorch-huggingface

epg

Open-sourced code for Evolved Policy Gradients

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

halos

A library with extensible implementations of DPO, KTO, PPO, and other human-centered loss functions (HALOs).

install-guides

Various installation guides for Large Language Models

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

llama-adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

llava

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

llm

Sharing LLM basic ideas and code

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

mit-6.824

Basic Sources for MIT 6.824 Distributed Systems Class

mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

mlresearch

My machine learning, reinforcement learning and deep learning research and engineering work.

moss-rlhf

MOSS-RLHF

nanogpt

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

neftune

Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning

ng-video-lecture

Build GPT

openai

The repository for all Azure OpenAI Samples complementing the OpenAI cookbook.

openai-cookbook

Examples and guides for using the OpenAI API

openrlhf

A Ray-based High-performance RLHF framework (for large models)

paddle

PArallel Distributed Deep LEarning

peft

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