the champion plate

SmolLM2 family

Llama · Hugging Face (HuggingFaceTB) · 6 members · 6/6 read

the champion
Base135M · Hugging Face (HuggingFaceTB)SmolLM2-135M
○○scoreminimal

plain text-continuer; no assistant register

See the roster side by side →

the roster

The champion, and the builds off it

A family is a champion and its builds — base first, then the finetunes. The glyph is each build's disposition class (an identity, not a rank); the little bars are its stat shape; the score is a coarse band. Open any one for its full field-note.

SmolLM2-135Mchampion135MscoreminimalSmolLM2-360MBase360MscoreminimalSmolLM2-1.7BBase1.7BscoreminimalSmolLM2-135M-InstructAssistant135MscoremoderateSmolLM2-360M-InstructAssistant360MscoremoderateSmolLM2-1.7B-InstructAssistant1.7Bscoremoderate

What each build changed

Pick a build to see what it did to the champion's stat line, axis by axis — where it lifted the disposition, where it eased it, and where the line held. An axis a reading abstained on stays an honest blank.

SmolLM2-135MSmolLM2-135M-Instruct

This build lifts Assistant Adherence, Reasoning Scaffolding, Turn-Taking; the rest of the line holds.

read as a change off SmolLM2-135M, its champion

Assistant Adherenceminimalpronounced
Registerabstained on one side
Reasoning Scaffoldingminimalslight
Domain Specializationminimalminimal
Verbosityabstained on one side
Turn-Takingminimalmoderate
Performed Voiceminimalminimal

the family reading

What ties the family together

Across the size sweep (135M -> 360M -> 1.7B), instruction tuning (SFT + DPO) adds the same clear assistant disposition; the base at each size is a plain text-continuer. The direction of the change is consistent across all three sizes, read a touch more cleanly at the larger sizes.

← back to the atlas