Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

LOMO: LOw-Memory Optimization

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

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

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts…

An easy/swift-to-adapt PyTorch-Lighting template. 套壳模板，简单易用，稍改原来Pytorch代码，即可适配Lightning。You can translate your previous Pytorch code much easier using this template, and keep your freedom to edit a…

A WeChat medical automatic reply robot based on tensorflow2.5

An implementation of "Incorporating copying mechanism in sequence-to-sequence learning"

An Open-source Neural Hierarchical Multi-label Text Classification Toolkit

Tensorflow2.3的文本分类项目，支持各种分类模型，支持相关tricks。

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

The source code of NeurIPS 2020 paper "CogLTX: Applying BERT to Long Texts"

Deep learning LSTM + BERT based approach for labelling a corpus with keywords, then training a model to extract keywords.

基于Tensorflow2.3开发的NER模型，都是CRF范式，包含Bilstm(IDCNN)-CRF、Bert-Bilstm(IDCNN)-CRF、Bert-CRF，可微调预训练模型，可对抗学习，用于命名实体识别，配置后可直接运行。

TensorFlow code and pre-trained models for BERT

Papers for image caption and text to image GANs

Image Caption using GAN.

Tensorflow implementation of Image Caption model based on SeqGAN

Generative Models for Image Captioning

A res_3D based detection system for micro expression recognition