Gryphe/Pantheon-Reasoning-27B

Full fine-tune vs llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: lm_head 1/1, Embeddings 3/5, Norms 0/325, Attention 410/560, MLP 251/307, other 1/1

3 derivatives checked