Gryphe/Pantheon-RP-1.6.2-22b-Small
Full fine-tune vs mistralai/Mistral-Small-Instruct-2409. Fine-tune: 99% of the weights changed, across 56 of 56 layers.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 168/168, Attention 224/224, lm_head 1/1
4 derivatives checked
- bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF: Same weights, converted
- mradermacher/Pantheon-RP-1.6.2-22b-Small-i1-GGUF: Quantization
- mradermacher/Pantheon-RP-1.6.2-22b-Small-GGUF: Quantization
- Kaoeiri/Mistral-magnum-v4_X_Cydonia-VXXX_Mixture: Full fine-tune