Dylan Foster 🐢

djfoster.bsky.social

14 December 2024 16:59

Given a high-quality verifier, language model accuracy can be improved by scaling inference-time compute (e.g., w/ repeated sampling). When can we expect similar gains without an external verifier? New paper: Self-Improvement in Language Models: The Sharpening Mechanism arxiv.org/abs/2412.01951

Nathan Lambert

natolambert.bsky.social

26 November 2024 18:45

Tulu 3 SFT mix trending on HuggingFace :D , next step make preferences and RL datasets more accessible.

Andi

andimara.bsky.social

26 November 2024 16:30

Let's go! We are releasing SmolVLM, a smol 2B VLM built for on-device inference that outperforms all models at similar GPU RAM usage and tokens throughputs. SmolVLM can be fine-tuned on a Google collab and be run on a laptop! Or process millions of documents with a consumer GPU!

Philipp Schmid

philschmid.bsky.social

21 November 2024 15:11

🚀 Biggest open text dataset release of the year! SmolTalk: a 1M sample synthetic dataset used to train SmolLM v2 is here! Available under Apache 2.0, it combines newly generated datasets + publicly available ones. Here’s what you need to know 🧵👇

Kapalı içerik