Hothan01

Llama-X

Open Academic Research on Improving LLaMA to SOTA LLM

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

LLM-eval-survey

The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".

DeepSeek-Math

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

OlympiadBench

An Olympiad-level bilingual multimodal scientific benchmark, featuring 8,952 questions from Olympiad-level mathematics and physics competitions, including the Chinese college entrance exam.

acl-style-files

Official style files for papers submitted to venues of the Association for Computational Linguistics

MiniCPM

MiniCPM-2B: An end-side LLM outperforming Llama2-13B.

IFEval

Evaluator for LLMs

mistral-inference

Official inference library for Mistral models

lm-evaluation-harness

A framework for few-shot evaluation of language models.

InfiniteBench

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718

UltraEval

An open source framework for evaluating foundation models.

The-Art-of-Linear-Algebra

Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"

ChatGPTBook

《ChatGPT原理与实战：大型语言模型的算法、技术和私有化》

llama

Inference code for Llama models

chain-of-thought-hub

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

SuperCLUE

SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese

awesome-LLMs-In-China

**大模型

hands_on_Ml_with_Sklearn_and_TF

OReilly Hands On Machine Learning with Scikit Learn and TensorFlow (Sklearn与TensorFlow机器学习实用指南)

CPM-Bee

百亿参数的中英文双语基座大模型

pythia

The hub for EleutherAI's work on interpretability and learning dynamics

BIG-bench

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

ml-stable-diffusion

Stable Diffusion with Core ML on Apple Silicon

ChatPaper

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

leetcode-master

《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

NLPDataSet

记录本人整理的一些数据集

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

DictBERT

Author: Wenhao Yu (wyu1@nd.edu). ACL 2022 Dict-BERT: Enhancing Language Model Pre-training with Dictionary

NLP-model