bunnycore/S1K-Maestro-7B-Sce

Full fine-tune vs arcee-ai/Arcee-Maestro-7B-Preview. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1, Embeddings 1/1

2 derivatives checked

• mradermacher/S1K-Maestro-7B-Sce-i1-GGUF: Quantization
• mradermacher/S1K-Maestro-7B-Sce-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse