Сводка 19.03.2023 — 26.03.2023
А теперь о том, что происходило в последнее время на других ресурсах.
Мероприятия
Обсуждения
StackOverflow на русском
Популярное на GitHub
| tatsu-lab/stanford_alpaca — Code and documentation to train Stanford's Alpaca models, and generate the data. |
| THUDM/ChatGLM-6B — ChatGLM-6B：开源双语对话语言模型 An Open Bilingual Dialogue Language Model |
| kaixindelele/ChatPaper — Use ChatGPT to summarize the arXiv papers. |
| yizhongw/self-instruct — Aligning pretrained language models with instruction data generated by themselves. |
| BlinkDL/RWKV-LM — RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding. |
| TheR1D/shell_gpt — A command-line productivity tool powered by ChatGPT, will help you accomplish your tasks faster and more efficiently. |
| modelscope/modelscope — ModelScope: bring the notion of Model-as-a-Service to life. |
| mpoon/gpt-repository-loader — Convert code repos into an LLM prompt-friendly format. Mostly built by GPT-4. |
| huggingface/peft — 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. |
| Zero6992/chatGPT-discord-bot — Integrate ChatGPT into your own discord bot |
| mingrammer/diagrams — 🎨 Diagram as Code for prototyping cloud system architectures |
| hwchase17/chat-langchain |
| acheong08/EdgeGPT — Reverse engineered API of Microsoft's Bing Chat AI |
| WassimTenachi/PhySO — Physical Symbolic Optimization |
| unifyai/ivy — The Unified Machine Learning Framework |
| Azure-Samples/azure-search-openai-demo — A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. |
На заметку
У нас есть новостная группа в Telegram. Там же можно обсудить интересующие вопросы. Ссылка в самом низу страницы.