Expert68's repositories
aider
aider is AI pair programming in your terminal
alignment-handbook
Robust recipes for to align language models with human and AI preferences
Anima
第一个开源的基于QLoRA的33B中文大语言模型First QLoRA based open source 33B Chinese LLM
baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
buffer-of-thought-llm
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
chronos-forecasting
Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting
CUT
Source code of "Reasons to Reject? Aligning Language Models with Judgments"
data-juicer
A one-stop data processing system to make data higher-quality, juicier, and more digestible for LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大语言模型提供更高质量、更丰富、更易”消化“的数据！
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
h2o-llmstudio
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://h2oai.github.io/h2o-llmstudio/
HuatuoGPT-II
HuatuoGPT2, One-stage Training for Medical Adaption of LLMs. (An Open Medical GPT)
iTransformer
Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting".
koodo-reader
A modern ebook manager and reader with sync and backup capacities for Windows, macOS, Linux and Web
KunQuant
A compiler, optimizer and executor for financial expressions and factors
LLaMA-Efficient-Tuning
Fine-tuning LLaMA with PEFT (PT+SFT+RLHF with QLoRA)
llama2.c
Inference Llama 2 in one file of pure C
LLM-Pretrain-SFT
Scripts of LLM pre-training and fine-tuning (w/wo LoRA, DeepSpeed)
LongLM
LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
magicoder
Magicoder: Source Code Is All You Need
Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
OptimalLinearSignal
This repository contains the implementation of an unsupervised machine learning model designed to optimize Profit and Loss (PnL) in quantitative finance. This model utilizes linear signals constructed from exogenous variables to maximize the Sharpe ratio.
orpo
Official repository for ORPO
PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
SPIN
The official implementation of Self-Play Fine-Tuning (SPIN)
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
unitxt
🦄 Unitxt: a python library for getting data fired up and set for training and evaluation
VL-GPT
VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation