gxdalu-yaya

awesome-chatgpt-prompts-zh

ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

google-research

Google Research

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

MOSS

An open-source tool-augmented conversational language model from Fudan University

Baichuan2

A series of large language models developed by Baichuan Intelligent Technology

ChatGLM-Tuning

基于ChatGLM-6B + LoRA的Fintune方案

Luotuo-Chinese-LLM

骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技

GLM

GLM (General Language Model)

pytorch-loss

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

multilingual-t5

moco-v3

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

simsiam

PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566

AMSoftmax

A simple yet effective loss function for face verification.

t5-pegasus-pytorch

distilling-step-by-step

coral-cnn

Rank Consistent Ordinal Regression for Neural Networks with Application to Age Estimation

BriVL

Bridging Vision and Language Model

coral-pytorch

CORAL and CORN implementations for ordinal regression with deep neural networks.

Vicuna-LoRA-RLHF-PyTorch

A full pipeline to finetune Vicuna LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the Vicuna architecture. Basically ChatGPT but with Vicuna

SCELoss-Reproduce

Reproduce Results for ICCV2019 "Symmetric Cross Entropy for Robust Learning with Noisy Labels" https://arxiv.org/abs/1908.06112

CamelBell-Chinese-LoRA

CamelBell（驼铃) is be a Chinese Language Tuning project based on LoRA. CamelBell is belongs to Project Luotuo(骆驼), an open sourced Chinese-LLM project created by 冷子昂 @ 商汤科技 & 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技

moco.tensorflow

A TensorFlow re-implementation of Momentum Contrast (MoCo): https://arxiv.org/abs/1911.05722

nlp-fluency

评估自然语言的流畅度

reward-modeling

contrastive-classification-keras

Implementation of self-supervised image-level contrastive pretraining methods using Keras.

llm-rankers

Zero-shot Document Ranking with Large Language Models.