Stars
A module to find available network ports for testing.
A framework for few-shot evaluation of language models.
Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets
Efficiently computes derivatives of NumPy code.
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
QLoRA: Efficient Finetuning of Quantized LLMs
Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型
Ongoing research training transformer models at scale
Toolkit for creating, sharing and using natural language prompts.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
视频播放器(IJKplayer、ExoPlayer、MediaPlayer),HTTPS,16k page size,支持弹幕,外挂字幕,支持滤镜、水印、gif截图,片头广告、中间广告,多个同时播放,支持基本的拖动,声音、亮度调节,支持边播边缓存,支持视频自带rotation的旋转(90,270之类),重力旋转与手动旋转的同步支持,支持列表播放 ,列表全屏动画,视频加载速度,列表小窗口支持拖…
Code for the paper Fine-Tuning Language Models from Human Preferences
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
A modular RL library to fine-tune language models to human preferences
Train transformer language models with reinforcement learning.
Regular expressions that match the mobile phone number in mainland China. / 一组匹配中国大陆手机号码的正则表达式。
Can receive any HTTP request, extract any values from JSON or XML and trigger a job with those values available as variables. Works with GitHub, GitLab, Bitbucket, Jira and many more.
CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition
Java wrapper around the FFmpeg command line tool
🔥持续更新。Android广告聚合:帮助 Android 开发者快速、便捷、灵活的接入国内多家主流安卓广告 SDK。广点通(优量汇)、穿山甲、快手联盟、百青藤(百度Mob)。开屏广告、Banner横幅广告、插屏广告、激励广告、原生信息流、全屏广告。
Awesome Knowledge Distillation