Alec Muffett

alecmuffett.bsky.social

31 January 2025 04:25

Run a 670 Billion parameter LLM at home for $6000 with no GPU required https://alecmuffett.com/article/111049 #DeepSeek #ai #homebrew #llm

Rhys Powell

rhyspowell.info

31 January 2025 04:24

It finally arrived!!! #homeassistant #diy #selfhosted #homelab #hass #voice #llm

Alyssa Pradhan

alyssapradhan.bsky.social

31 January 2025 04:24

I really like the detail in this paper! Exploring the bias in #LLM responses through counterfactuals, SHAP, embeddings (oh my) and looking at intersections of gender x ethnicity 😍 TLDR: #Algorithmicbias runs deep #MedSky #MLSky #digitalhealth #healthequity arxiv.org/abs/2410.16574

Daniel van Strien

danielvanstrien.bsky.social

31 January 2025 04:24

Why choose between strong #LLM reasoning and efficient models? Use DeepSeek to generate high-quality training data, then distil that knowledge into ModernBERT for fast, efficient classification. New blog post: danielvanstrien.xyz/posts/2025/d...

🍉paraver🟩🟡🟥

paraver.bsky.social

31 January 2025 04:23

A #IA assemelha-se a esquema piramidal. Há poucas semanas a #OpenAI dizia que o dinheiro investido não era nada e que iriam precisar de muito mais. E aparece uma empresa, sujeita a sanções dos EUA, e apresenta produto notoriamente melhor e muito mais barato.