lipiji

lipiji.github.io

LLaMA-Efficient-Tuning

Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)

baichuan-7B

A large-scale 7B pretraining language model developed by Baichuan

FindTheChatGPTer

ChatGPT爆火，开启了通往AGI的关键一步，本项目旨在汇总那些ChatGPT的开源平替们，包括文本大模型、多模态大模型等，为大家提供一些便利

akshare

AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库

ChatGLM-Efficient-Tuning

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

civrealm

CivRealm: A Learning and Reasoning Odyssey for Decision-Making Agents: https://civrealm.github.io/civrealm/

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

methane-gapfill-ml

Python codebase for gap-filling eddy covariance methane fluxes at FLUXNET-CH4 wetlands with machine learning.

UltraChat

Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)

Yuan-2.0

Yuan 2.0 Large Language Model

agents

An Open-source Framework for Autonomous Language Agents

aidea

AIdea 是一款支持 GPT 以及国产大语言模型通义千问、文心一言等，支持 Stable Diffusion 文生图、图生图、 SDXL1.0、超分辨率、图片上色的全能型 APP。

Chat-Haruhi-Suzumiya

Chat凉宫春日, 由李鲁鲁, 冷子昂等同学开发的模仿二次元对话的聊天机器人。

ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

chatglm_finetuning

chatglm 6b finetuning and alpaca finetuning

dify

An Open-Source Assistants API and GPTs alternative. Dify.AI is an LLM application development platform. It integrates the concepts of Backend as a Service and LLMOps, covering the core tech stack required for building generative AI-native applications, including a built-in RAG engine.

FastEdit

🩹Editing large language models within 10 seconds⚡

finetune-gpt2xl

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed

llama-recipes

Examples and recipes for Llama 2 model

mistral-src

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

Neural-Brain-Decoding

The purpose of this repository is to collect and investigate language oriented neural decoding work

Pai-Megatron-Patch

SwinLLama

SwinLLama for medical report generation

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

transformers

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

transpeeder

train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism

XAgent

An Autonomous LLM Agent for Complex Task Solving

Yi

A series of large language models trained from scratch by developers @01-ai

zero_nlp

中文nlp应用(大模型、数据、模型、训练、推理)