RanchiZhao

RUCQA

A possible QA application on local database based on langchain and llama-index

DialogEvaluation

a demo of DialogEvaluation based on LLM

CPM-Bee

百亿参数的中英文双语基座大模型

OpenDelta

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

BMCook

Model Compression for Big Models

BMTools

Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins

BMTrain

Efficient Training (including pre-training and fine-tuning) for Big Models

bmtrain_qlora

compress_llama

CPM-Bee-qlora

百亿参数的中英文双语基座大模型

cpm_kernels

cpm_live

cpm_live_series

Efficient-Tuning-LLMs

大模型高效量化训练+部署 (Efficient Finetuning of QLoRA LLMs). QLoRA, LLama, bloom, baichuan-7B, GLM

FIGA

This is the repository of FIGA, an alignment method for LLMs using fine-grained quality signals.

Llama2-Chinese

Llama中文社区，最好的中文Llama大模型，完全开源可商用

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (LLaMA, LLaMa2, ChatGLM2, ChatGPT, Claude, etc) over 50+ datasets.

OpenLLaMA2

LLaMA2 SFT/RLHF trainning framework

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

RanchiZhao

for me

RanchiZhao.github.io

resume

基于LaTeX编译生成的中英文个人简历

safe-rlhf

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

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.