mergekit-community/mergekit-sce-sudfgqi

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

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

2 derivatives checked

• mradermacher/mergekit-sce-sudfgqi-i1-GGUF: Quantization
• mradermacher/mergekit-sce-sudfgqi-GGUF: Quantization

On the Hub · Downloads on Model Pulse