YOYO-AI/YOYO-O1-14B

Full fine-tune vs Gen-Verse/ReasonFlux-F1-14B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Norms 96/97, MLP 144/144, Attention 336/336

2 derivatives checked

• mradermacher/YOYO-O1-14B-i1-GGUF: Quantization
• mradermacher/YOYO-O1-14B-GGUF: Quantization

On the Hub · Downloads on Model Pulse