prithivMLmods/Lacerta-Opus-14B-Elite8
Full fine-tune vs prithivMLmods/Messier-Opus-14B-Elite7. Fine-tune: 98% of the weights changed, across 48 of 48 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 97/97, MLP 141/144, Attention 329/336
5 derivatives checked
- mradermacher/Lacerta-Opus-14B-Elite8-i1-GGUF: Quantization
- mradermacher/Lacerta-Opus-14B-Elite8-GGUF: Quantization
- MaziyarPanahi/Lacerta-Opus-14B-Elite8-GGUF: Same weights, converted
- prithivMLmods/Galactic-Qwen-14B-Exp2: Full fine-tune
- prithivMLmods/Gamma-Corvi-Qwen-14B: Full fine-tune