prithivMLmods/Equuleus-Opus-14B-Exp
Full fine-tune vs prithivMLmods/Jolt-v0.1. 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
3 derivatives checked
- mradermacher/Equuleus-Opus-14B-Exp-i1-GGUF: Quantization
- mradermacher/Equuleus-Opus-14B-Exp-GGUF: Quantization
- prithivMLmods/Messier-Opus-14B-Elite7: Partial fine-tune