Dataset for the Emerging & Novel Entity NER task (WNUT '17)

MiniRBT (中ちゅう文ぶん小型こがた预训练模型がた系列けいれつ)

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.

Tesseract Open Source OCR Engine (main repository)

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近せっきんGPT-4o表おもて现的开源多た模も态对话模型がた

An application for running LLMs locally on your device, with your documents, facilitating detailed citations in generated responses.

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

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

算法さんぽう工程こうてい师-机つくえ器き学がく习面试题总结

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多た语言多た模も态对话模型がた

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)

Firefly: 大だい模型もけい训练工具こうぐ，支持しじ训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等とう大だい模型もけい

主要しゅよう记录大だい语言大だい模型もけい（LLMs） 算法さんぽう（应用）工程こうてい师相关的知ち识及面めん试题

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

A Docker image for PyTorch

Ongoing research training transformer language models at scale, including: BERT & GPT-2

The official Meta Llama 3 GitHub site

[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct

Home of StarCoder2!

大だい模型もけい基もと础: 一文了解大模型基础知识

An incremental parsing system for programming tools

Reliable project licenses detector.

MNBVC(Massive Never-ending BT Vast Chinese corpus)超ちょう大だい规模中ちゅう文ぶん语料集しゅう。对标chatGPT训练的てき40T数かず据すえ。MNBVC数すう据すえ集しゅう不ふ但ただし包括ほうかつ主流しゅりゅう文化ぶんか，也包括ほうかつ各かく个小众文化ぶんか甚至火星かせい文ぶん的てき数すう据すえ。MNBVC数すう据すえ集しゅう包括ほうかつ新しん闻、作文さくぶん、小しょう说、书籍、杂志、论文、台たい词、帖じょう子こ、wiki、古こ诗、歌うた词、商品しょうひん介かい绍、笑わらい话、糗事、聊天记录等とう一切形式的纯文本中文数据。