#jupyter_notebook#chinese_llm#chinese_nlp#finetune#generative_ai#instruct_gpt#instruction_set#llama#llm#lora#open_models#open_source#open_source_models#qlora
AirLLM is a tool that lets you run very large AI models on computers with limited memory by using a smart layer-by-layer loading technique instead of traditional compression methods. You can run a 70-billion-parameter model on just 4GB of GPU memory, or even a 405-billion-parameter model on 8GB, without losing model quality. The benefit is that you can use powerful AI models on affordable hardware without expensive upgrades, and the tool also offers optional compression features that can speed up performance by up to 3 times while maintaining accuracy.
https://github.com/lyogavin/airllm
📰@Botfather Officially Launches as a Mini App
The well-known bot @BotFather—the central tool for creating and managing Telegram bots—has now been made available as a Mini App.
This new feature allows users to access all of BotFather’s functionalities through an updated, interactive interface, no need to manually enter text commands.
#botfather
👉The TG Times
@nashrabot
Qué puede hacer este bot?
Impresionante bot para canales y propietarios de listas de publicidad te ayuda a crear publicaciones enriquecidas, podcasting en muchos canales
Idioma: Inglés
(visto en @BotsGram_cu)
#botfather, #token, #create, #development, #dev, #botbuilding