zyds

EasyContext

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

llama3

The official Meta Llama 3 GitHub site

ReAlign

Reformatted Alignment

Simple-Trl-Training

基于DPO算法微调语言大模型，简单好上手。

GitHub-Chinese-Top-Charts

:cn: GitHub中文排行榜，各语言分设「软件 | 资料」榜单，精准定位中文好项目。各取所需，高效学习。

nanotron

Minimalistic large language model 3D-parallelism training

NeurIPS-WANT-submission-efficient-parallelization-layouts

EmoLLM

心理健康大模型、LLM、The Big Model of Mental Health、Finetune、InternLM2、Qwen、ChatGLM、Baichuan、DeepSeek、Mixtral、LLama3

BCEmbedding

Netease Youdao's open-source embedding and reranker models for RAG products.

llamafia.github

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

awesome-llm-interpretability

A curated list of Large Language Model (LLM) Interpretability resources.

openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

HuggingFace-Download-Accelerator

利用HuggingFace的官方下载工具从镜像网站进行高速下载。

mamba

LongBench

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

punica

Serving multiple LoRA finetuned LLM as one

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

autodistill

Images to inference with no labeling (use foundation models to train supervised models).

X-AnyLabeling

Effortless data labeling with AI support from Segment Anything and other awesome models.

Grounded-Segment-Anything

Grounded-SAM: Marrying Grounding-DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

ChatGLM3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

lm-format-enforcer

Enforce the output format (JSON Schema, Regex etc) of a language model

awesome_LLMs_interview_notes

LLMs interview notes and answers:该仓库主要记录大模型（LLMs）算法工程师相关的面试题和参考答案

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！

MOSS-RLHF

MOSS-RLHF

NEFTune

Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning

alignment-handbook

Robust recipes to align language models with human and AI preferences

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks