smollm2:360m

Upstream reference: SmolLM2-360M base

Publisher: Hugging Face Smol Models Research

Hugging Face documents this 360M base checkpoint within its compact SmolLM2 language-model family. Base and instruction-tuned releases are distinct.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Published size
360 million parameters Source
Architecture
Transformer decoder Source
Pretraining tokens
4 trillion Source
Published training precision
bfloat16 Source
Upstream license label
Apache-2.0 Source

Publisher-described uses

  • Text continuation and further adaptation of the base checkpoint. Source

Reference limitations

  • The card describes English as the primary language and notes possible factual, consistency and bias errors. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

Links

Recorded references do not establish downloadable weights, licensing or current availability.

360M
parameters
F16
quantization
llama
architecture
8192
context
apache-2.0
license
2024-10-31
released

Where smollm2:360m comes from

Company / lab

Hugging Face

See every model and family from this maker.

Model family

smollm2

Other versions and sizes in this line.

completion

Named in 6 observation pages

Browse the Observatory

AI-generated & AI-scored. Every observation on this site is produced and judged by AI, and AI makes mistakes. Treat each result as a recorded observation under a declared protocol, as of its date. Method and marker legend