搜索、推荐、广告、用增等工业界实践文章收集（来源：知乎、Datafuntalk、技术公众号）

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

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

Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)

Train transformer language models with reinforcement learning.

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现包括二次预训练、有监督微调、奖励建模、强化学习训练。

Llama中文社区，最好的中文Llama大模型，完全开源可商用

A 13B large language model developed by Baichuan Intelligent Technology

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

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

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

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

Example models using DeepSpeed

中文LLaMA&Alpaca大语言模型+本地CPU/GPU部署 (Chinese LLaMA & Alpaca LLMs)

[NeurIPS 2020] "Graph Contrastive Learning with Augmentations" by Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang Shen

Code and documentation to train Stanford's Alpaca models, and generate the data.

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

Awesome-LLM: a curated list of Large Language Model

基于ChatGLM-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning等

Instruct-tune LLaMA on consumer hardware

Inference code for LLaMA models

ChatGLM-6B：开源双语对话语言模型 | An Open Bilingual Dialogue Language Model

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Official Pytorch Implementation of: "Asymmetric Loss For Multi-Label Classification"(ICCV, 2021) paper

Easy-to-use NLP library with Awesome pre-trained model zoo, supporting wide-range of NLP tasks from research to industrial applications.

Code for ALBEF: a new vision-language pre-training method

Contrastive Language-Image Pretraining

Baidu's open-source Sentiment Analysis System.

[CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks.