prithivMLmods/Gamma-Corvi-Qwen-14B

Full fine-tune vs prithivMLmods/Lacerta-Opus-14B-Elite8. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336

1 derivatives checked