prithivMLmods/Jolt-v0.1
Full fine-tune vs prithivMLmods/Elita-1. Fine-tune: 99% of the weights changed, across 48 of 48 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 14/97, MLP 143/144, Attention 282/336
5 derivatives checked
- mradermacher/Jolt-v0.1-i1-GGUF: Quantization
- mradermacher/Jolt-v0.1-GGUF: Quantization
- prithivMLmods/Dinobot-Opus-14B-Exp: Full fine-tune
- prithivMLmods/Viper-Coder-v0.1: Full fine-tune
- prithivMLmods/Equuleus-Opus-14B-Exp: Full fine-tune