Fireworks AI · featureQwen, Llama, DeepSeek SFT support

Valid from

2025-06-13

Valid until

still holds

Published

2025-06-13

Recorded by AsOf

2026-10-29

Checked

2026-10-31 · its source page states the value and the date

Confidence

0.70

Sources

“This now encompasses the Qwen 2/2.5/3 series, Phi 4, Gemma 3, the Llama family, as well as leading open-source MoE models like Deepseek R1 and V3, including, of course, any fine-tuned variants of those models!”— what the page says, read 2026-10-31

• Supervised Fine Tuning V2: Faster SFT on More Modelsprimary · fireworks.ai · 2025-06-13

/claim/clm_8B6641F51FC4.md/v1/claims/clm_8B6641F51FC4timelinesubmit a correction