lulia0228

Cherry_LLM

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

Hermes-Function-Calling

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

NeMo-Aligner

Scalable toolkit for efficient model alignment

Megatron-LM

Ongoing research training transformer models at scale

llama3

The official Meta Llama 3 GitHub site

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Awesome-Chinese-LLM

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

open-webui

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

LeetCode021

🚀 LeetCode From Zero To One & 题单整理 & 题解分享 & 算法模板 & 刷题路线，持续更新中...

transformers_tasks

⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.

DeepLearing-Interview-Awesome-2024

AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目

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

LiveSum-TTT

Codes and Datasets for the Paper: Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction

LLM-data-aug-survey

The official GitHub page for the survey paper "A Survey on Data Augmentation in Large Model Era"

SALAD-BENCH

【ACL 2024】 SALAD benchmark & MD-Judge

bold

Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation" paper

TOXIGEN

This repo contains the code for generating the ToxiGen dataset, published at ACL 2022.

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

ethics

Aligning AI With Shared Human Values (ICLR 2021)

lost-in-the-middle

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

CValues

面向中文大模型价值观的评估与对齐研究

DecodingTrust

A Comprehensive Assessment of Trustworthiness in GPT Models

LLM-RGB

LLM Reasoning and Generation Benchmark. Evaluate LLMs in complex scenarios systematically.

red-instruct

Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

LLMs-Finetuning-Safety

We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.

Safety-Evaluating

本文提出了一个基于“文心一言”的**LLMs的安全评估基准，其中包括8种典型的安全场景和6种指令攻击类型。此外，本文还提出了安全评估的框架和过程，利用手动编写和收集开源数据的测试Prompts，以及人工干预结合利用LLM强大的评估能力作为“共同评估者”。

CipherChat

A framework to evaluate the generalization capability of safety alignment for LLMs