ciel-zhang Goto Github PK

bert4keras

light reimplement of bert for keras

blog

个人博客

cantontrans

JavaScript utility for translating between mandarin and cantonese 工具爲雙向翻譯繁體中文至粵語

chinese-vicuna

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

chinesestopwords

常用的中文停用词表

colossalai

Making large AI models cheaper, faster and more accessible

concrete-ml

Concrete ML: Privacy Preserving ML framework built on top of Concrete, with bindings to traditional ML frameworks.

dromedary

Dromedary: towards helpful, ethical and reliable LLMs.

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

food-pics

googlecommonspider

谷歌图片通用爬虫

hgb

Revisiting, benchmarking, and refining Heterogeneous Graph Neural Networks.

keras-ocr

A packaged and flexible version of the CRAFT text detector and Keras CRNN recognition model.

mobileagent

Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception

nemo-guardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

openchatkit

os-urlpattern

Unsupervised URLs clustering, generate and match URL pattern.

pyrit

The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in their generative AI systems.

rasa

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

retinaface_pytorch

Reimplement RetinaFace with Pytorch

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

sparrowrecsys

A Deep Learning Recommender System

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

uer-py

wizardlm

Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder