Nitral-Archive/CaptainErisNebula-12B-AOE-v1
Full fine-tune vs Nitral-Archive/CaptainErisNebula-12B-AOE-v0.69. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 44/81, MLP 117/120, Attention 156/160
4 derivatives checked
- mradermacher/CaptainErisNebula-12B-AOE-v1-i1-GGUF: Quantization
- Lewdiculous/CaptainErisNebula-12B-AOE-v1-GGUF-IQ-Imatrix: Same weights, converted
- mradermacher/CaptainErisNebula-12B-AOE-v1-GGUF: Quantization
- Nitral-Archive/CaptainErisNebula-12B-AOE-v1R: Full fine-tune