attn-signs/Watari-7b-v1
Full fine-tune vs t-tech/T-lite-it-1.0. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 57/57, MLP 84/84, Attention 196/196
2 derivatives checked
- mradermacher/Watari-7b-v1-GGUF: Same weights, converted
- attn-signs/Zariman-R-7b-v0: LoRA-style