PygmalionAI/Eleusis-12B
Full fine-tune vs mistralai/Mistral-Nemo-Base-2407. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 45/81, MLP 120/120, Attention 160/160, lm_head 1/1
5 derivatives checked
- bartowski/PygmalionAI_Eleusis-12B-GGUF: Same weights, converted
- mradermacher/Eleusis-12B-GGUF: Quantization
- mradermacher/Eleusis-12B-i1-GGUF: Quantization
- DevQuasar-8/PygmalionAI.Eleusis-12B-GGUF: Same weights, converted
- PygmalionAI/Eleusis-12B-GGUF: Same weights, converted