[ICCV 2023]ToonTalker: Cross-Domain Face Reenactment

Bring portraits to life!

[CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"

Unofficial Implementation of Animate Anyone

本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。

Code for Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

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

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

对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF

Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT.

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

基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

chatglm 6b finetuning and alpaca finetuning

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

ACE 2005 corpus preprocessing for Event Extraction task

ACE 2005 Corpus Preprocessing (tips for how to run mgormley/ace-data-prep)

ICTAI 2019: Multi-Task Learning for Relation Extraction

An Open Source Machine Learning Framework for Everyone

This is a general purpose Ripple client in Java(JavaSE/Android) And have their own Ripple-Blockchain Systems, and provides Ripple-Blockchain special scripting language(The script also supports Base…