Gryphe/Pantheon-RP-Pure-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
8 derivatives checked
- bartowski/Pantheon-RP-Pure-1.6.2-22b-Small-GGUF: Same weights, converted
- mradermacher/Pantheon-RP-Pure-1.6.2-22b-Small-i1-GGUF: Quantization
- DevQuasar-11/Gryphe.Pantheon-RP-Pure-1.6.2-22b-Small-GGUF: Same weights, converted
- mradermacher/Pantheon-RP-Pure-1.6.2-22b-Small-GGUF: Quantization
- Aleteian/Pantheon-of-Cydonia-Realm-MN-22B-RP: Full fine-tune
- Kaoeiri/Magpantheon-v4x1.6.2-Cydonia-vXXX-22B: Full fine-tune
- Kaoeiri/Magpantheon-lark-v4x1.6.2-Cydonia-vXXX-22B: Full fine-tune
- Edens-Gate/Chunky-Merge-22B: Full fine-tune (fewer layers)