prithivMLmods/Tadpole-Opus-14B-Exp
Full fine-tune vs prithivMLmods/Sombrero-Opus-14B-Elite5. 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
4 derivatives checked
- mradermacher/Tadpole-Opus-14B-Exp-i1-GGUF: Quantization
- csabakecskemeti/prithivMLmods.Tadpole-Opus-14B-Exp-GGUF: Same weights, converted
- mradermacher/Tadpole-Opus-14B-Exp-GGUF: Quantization
- tensorblock/Tadpole-Opus-14B-Exp-GGUF: Quantization