ewald1976/Red-Rosie-12B

Partial fine-tune vs TheDrummer/Rocinante-X-12B-v1. Partial change: 36% of the weights changed (attention, mlp, norms), in 16 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 10/81, MLP 48/120, Attention 64/160, lm_head 0/1

2 derivatives checked

• mradermacher/Red-Rosie-12B-GGUF: Quantization
• mradermacher/Red-Rosie-12B-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse