SuperXiang

DeepSeek-MoE

AgentLite

alphageometry

AppAgent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

babilong

BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.

Cherry_LLM

[NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other models

CS-Eval

CS-Eval is a comprehensive evaluation suite for fundamental cybersecurity models or large language models' cybersecurity ability.

data-juicer

A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

deepeval

The LLM Evaluation Framework

demonstrated-feedback

devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

dsir

DSIR large-scale data selection framework for language model training

EasyContext

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

leetcode-hard-gym

A hard gym for programming

Linly

Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集

List-of-Dirty-Naughty-Obscene-and-Otherwise-Bad-Words

List of Dirty, Naughty, Obscene, and Otherwise Bad Words

LLMTest_NeedleInAHaystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

magikarp

ollama

Get up and running with Llama 2, Mistral, and other large language models.

opro

official code for "Large Language Models as Optimizers"

orpo

Official repository for ORPO

PentestGPT

A GPT-empowered penetration testing tool

PiSSA

Qwen1.5

Qwen1.5 is the improved version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.

scaling_laws_data_filtering

SecEval

simple-one-api

OpenAI 接口接入适配，支持千帆大模型平台、讯飞星火大模型、腾讯混元以及MiniMax、Deep-Seek，等兼容OpenAI接口，仅单可执行文件，配置超级简单，一键部署，开箱即用.

small-LMs-Task-Planning

Can only LLMs do Reasoning?: Potential of Small Language Models in Task Planning

Superfiltering

transformer-debugger