RisanLi

Risan's starred repositories

MediaCrawler

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频｜评论爬虫、微博帖子｜评论爬虫

Language:PythonNOASSERTION15371 88 242

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Language:PythonApache-2.012779 98 1032

ggml

Tensor library for machine learning

Language:C++MIT10414 122 387

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

Language:Jupyter NotebookMIT9740 84 247

open_clip

An open source implementation of CLIP.

Language:PythonNOASSERTION9310 76 454

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

Language:Jupyter NotebookBSD-3-Clause9293 97 630

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Language:PythonMIT8194 69 172

cudf

cuDF - GPU DataFrame Library

Language:C++Apache-2.08077 149 6274

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

Language:PythonMIT6174 37 884

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Language:PythonMIT4154 33 434

VisualGLM-6B

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

Language:PythonApache-2.04046 40 346

pandarallel

A simple and efficient tool to parallelize Pandas operations on all available CPUs

Language:PythonBSD-3-Clause3599 27 218

LASER

Language-Agnostic SEntence Representations

Language:Jupyter NotebookNOASSERTION3568 90 210

img2dataset

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Language:PythonMIT3471 31 253

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

MIT3119 25 71

MedicalGPT

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。

Language:PythonApache-2.03015 33 369

chatglm.cpp

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4

Language:C++MIT2845 41 243

CPM-Bee

百亿参数的中英文双语基座大模型

Language:Python2679 34 107

NLP-Interview-Notes

该仓库主要记录 NLP 算法工程师相关的面试题

2378 23 14

Chinese-Llama-2-7b

开源社区第一个能下载、能运行的中文 LLaMA2 模型！

Language:PythonApache-2.02220 20 39

ctransformers

Python bindings for the Transformer models implemented in C/C++ using GGML library.

Language:CMIT1767 19 198

rag-from-scratch

Language:Jupyter Notebook1766 21 16

LLMs_interview_notes

该仓库主要记录大模型（LLMs）算法工程师相关的面试题

Apache-2.01206 10 1

XuanYuan

轩辕：度小满中文金融对话大模型

Language:Python970 12 33

Med-ChatGLM

Repo for Chinese Medical ChatGLM 基于中文医学知识的ChatGLM指令微调

Language:PythonApache-2.0935 11 59

uniem

unified embedding model

Language:PythonApache-2.0794 7 101

LLaMA-Pro

[ACL 2024] Progressive LLaMA with Block Expansion.

Language:PythonApache-2.0448 20 31

LLMPruner

Language:Python281 5 5

Python-Package-Template

A easy, reliable, fluid template for python packages complete with docs, testing suites, readme's, github workflows, linting and much much more

Language:ShellMIT116 30

GraphXInAction

Book <Spark GraphX In Action> code and resources.

Language:Scala24 40