Загрузка видео...
Не удалось загрузить видео
🚀 Today, we are introducing SmolTools! 🚀 Last week, at Hugging Face we made a significant leap forward with the release of SmolLM2, a compact 1.7B language model that sets a new benchmark for performance among models of its size. But beyond the impressive stats, SmolLM2 truly shines in... show more
100,813 просмотров • 1 год назад •via X (Twitter)
Комментарии: 11

@andi_marafioti great stuff! i've been finetuning SmolLM2-135M recently and really liking the results and speed of iteration it allows for

@andi_marafioti @simonw check out SmolAgent for local tool calling

@andi_marafioti Great Job, congrats to @LoubnaBenAllal1 Team.

@andi_marafioti @Thom_Wolf @Thom_Wolf, what are your thoughts on SmolTools' efficiency? Do you foresee widespread adoption in the AI community?

@andi_marafioti 🔥🔥y este temazo!! 🎶🇦🇷

Subliminal 😂

@andi_marafioti Looking forward to trying it! Thanks for sharing

@andi_marafioti Nice

@andi_marafioti @LoubnaBenAllal1 Very interesting and great work to be honest, can't wait to try it.

@andi_marafioti What is the doc for the max output tokens? Is it limited to 8.192 like the other models or is it longer? I ask because my task is to punctuate longer texts and it’s cumbersome to chunk apriori

This is using the same smollm2 instruct 1.7B model that was released last week, so the context size is still 8k. Honestly, I find the performance for rewriting is best for shorter texts.


