MarsupialAI/Lusca-33B_iMat_GGUF
Full fine-tune (fewer layers) vs mistralai/Mistral-Small-Instruct-2409. mistralai/Mistral-Small-Instruct-2409 matches part of MarsupialAI/Lusca-33B_iMat_GGUF (507 of its 759 tensors; the rest of MarsupialAI/Lusca-33B_iMat_GGUF has no counterpart). On the shared part: MarsupialAI/Lusca-33B_iMat_GGUF is a GGUF (F16/F32) of different weights. Fine-tune: 100% of the weights changed, across 56 of 56 layers.
Tensors changed: Embeddings 1/1, Norms 82/113, MLP 168/168, Attention 224/224, lm_head 1/1