SmolLM-1.7B is a series of small language models trained by Hugging Face on a high-quality dataset. The 1.7 billion parameter version is designed to be efficient for on-device or low-resource inference while achieving competitive results on benchmarks such as MMLU. It supports standard text-generation tasks and is available through the Transformers library.
SmolLM 1.7B is a Foundation models & chat project. It focuses on providing a small, efficient language model that can run with limited compute resources while maintaining strong performance on reasoning tasks. SmolLM 1.7B is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the web, the command line, and API.
It is developed by Hugging Face, and it first shipped in 2023. The project is developed in the open on GitHub with 2.8k stars. Among its 3 catalogued features are Text Generation, Small Language Model, and Benchmark Evaluation. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do