prithivMLmods/Sombrero-Opus-14B-Elite5
Partial fine-tune vs prithivMLmods/Calcium-Opus-14B-Elite2. Partial change: 89% of the weights changed (attention, mlp, norms), in 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 4/97, MLP 144/144, Attention 195/336, lm_head 0/1
6 derivatives checked
- mradermacher/Sombrero-Opus-14B-Elite5-i1-GGUF: Quantization
- csabakecskemeti/prithivMLmods.Sombrero-Opus-14B-Elite5-GGUF: Same weights, converted
- mradermacher/Sombrero-Opus-14B-Elite5-GGUF: Quantization
- prithivMLmods/Sombrero-Opus-14B-Elite6: Partial fine-tune
- prithivMLmods/Porpoise-Opus-14B-Exp: Full fine-tune
- prithivMLmods/Tadpole-Opus-14B-Exp: Full fine-tune
1 other repos hold byte-for-byte identical weight files.