prithivMLmods/Elita-1
Full fine-tune vs prithivMLmods/Megatron-Corpus-14B-Exp. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 14/97, MLP 144/144, Attention 283/336, lm_head 1/1
4 derivatives checked
- mradermacher/Elita-1-i1-GGUF: Quantization
- mradermacher/Elita-1-GGUF: Quantization
- prithivMLmods/Evac-Opus-14B-Exp: Full fine-tune
- prithivMLmods/Jolt-v0.1: Full fine-tune