#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
#rstats#book
📕
Introducción a R: aprendiendo R sin morir en el intento.
Libro, en formato web y en español, ideal para aquellos interesados en iniciar el aprendizaje de #R a partir de los tipos de datos y la programación.
🌐ES
🔗Link
-----
Canal principal: @repo_science
Cupones: @freecoupons_reposcience
-----
#NYR2024#RStats
🖥
Excited to have Hadley Wickham, Chief Scientist at Posit, speaking at NY R Conference 2024! Dive into the evolution of data science and discover future trends with one of the pioneers in R programming.
rstats.ai/nyr.html
-----
Main channel: @repo_science
Coupons: @freecoupons_reposcience
-----
#DataScience#rstats#DataScientist#dataanalysis#r#programming#dataviz#statistics
In an era driven by data, harnessing the power of statistics is key to deriving meaningful insights from the vast sea of information around us.
pyoflife.com/statistics-wit
-----
Main channel: @repo_science
Coupons: @freecoupons_reposcience
-----
#ML#datascience#rstats#programming#dataviz#stats#analytics#machinelearning
6 formas de visualizar los resultados del análisis cluster jerárquico con R
-----
Main channel: @repo_science
Coupons: @freecoupons_reposcience
-----
#programming#GPT4#GPT3#dataviz#stats#analytics#ML#AI#IA
🚀
Cómo programar más rápidamente en #RStats con #ChatGPT
Escribir código es un proceso lento, especialmente cuando estás aprendiendo #datascience por primera vez. ¿Y si pudieras acelerarlo?
🔗Link
-----
Main channel: @repo_science
Coupons: @freecoupons_reposcience
-----