knowledgehacker

chromium

Chroium source code

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

langchain

⚡ Building applications with LLMs through composability ⚡

machine_learning

Frequently used machine learning algorithms implemented in C++

nginx-1.4.1

spdy/2-to-http/1.1 proxy server

tensorflow-examples

Deep Learning examples implemented in TensorFlow, including textcnn, seq2seq, etc.

text_classifier

Text classification using DNN models, including TextCNN, Transformer, etc.

trlx-examples

xfm

xFM, including fm, nfm, implementation on Tensorflow

yolo

YOLO v1~3 implementation

knowledgehacker/trlx-examples

knowledgehacker/Alpaca-CoT

We extend CoT data to Alpaca to boost its reasoning ability. We are constantly expanding our collection of instruction-tuning data, and integrating more LLMs together for easy use. （我们将CoT数据扩展到Alpaca以提高其推理能力，同时我们将不断收集更多的instruction-tuning数据集,并在我们框架下集成进更多的LLM，打造一个通用的LLM-IFT平台。）

knowledgehacker/awesome-pretrained-chinese-nlp-models

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型集合

knowledgehacker/baichuan-7B

A large-scale 7B pretraining language model developed by Baichuan

knowledgehacker/chatglm_finetuning

chatglm 6b finetuning and alpaca finetuning

knowledgehacker/codealpaca

knowledgehacker/DeepSpeedExamples

Example models using DeepSpeed

knowledgehacker/Dromedary

Dromedary: towards helpful, ethical and reliable LLMs.

knowledgehacker/fairscale

PyTorch extensions for high performance and large scale training.

knowledgehacker/fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

knowledgehacker/FastChat

An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.

knowledgehacker/Fengshenbang-LM

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

knowledgehacker/FlagAI

FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.

knowledgehacker/generative-agents

An attempt to build a working, locally-running cheap version of Generative Agents: Interactive Simulacra of Human Behavior

knowledgehacker/GLM-130B

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

knowledgehacker/google-research

Google Research

knowledgehacker/GPT-4-LLM

Instruction Tuning with GPT-4

knowledgehacker/gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

knowledgehacker/Huatuo-Llama-Med-Chinese

Repo for HuaTuo (华驼), Llama-7B tuned with Chinese medical knowledge. 华驼模型仓库，基于中文医学知识的LLaMA模型指令微调

knowledgehacker/HuatuoGPT

HuatuoGPT, Towards Taming Language Models To Be a Doctor.

knowledgehacker/langchain-ChatGLM

langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ 基于本地知识的 ChatGLM 问答

knowledgehacker/LLMZoo

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

knowledgehacker/MOSS

An open-source tool-augmented conversational language model from Fudan University

knowledgehacker/PMC-LLaMA

The official codes for "PMC-LLaMA: Continue Training LLaMA on Medical Papers"

knowledgehacker/prompt-tuning

Original Implementation of Prompt Tuning from Lester, et al, 2021

knowledgehacker/SpanBERT

Code for using and evaluating SpanBERT.

knowledgehacker/text-to-text-transfer-transformer

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

knowledgehacker/tree-of-thoughts

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

knowledgehacker/xlnet

XLNet: Generalized Autoregressive Pretraining for Language Understanding

knowledgehacker/zero_nlp

中文nlp应用(大模型、数据、模型、训练、推理)