SuperXiang

AgentLite

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！

dclm

DataComp for Language Models

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.

distillm

Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)

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.

GPU-Benchmarks-on-LLM-Inference

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

magikarp

MambaInLlama

Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models

Minitron

A family of compressed models obtained via pruning and knowledge distillation

ollama

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

OpenDevin

🐚 OpenDevin: Code Less, Make More

opro

official code for "Large Language Models as Optimizers"

orpo

Official repository for ORPO

PentestGPT

A GPT-empowered penetration testing tool

persona-hub

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

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

InternLM

Official release of InternLM2.5 7B base and chat models. 1M context support