shisa-ai/029-shisa-gamma-7b-v1-v2new-dpo405b
Full fine-tune vs augmxnt/shisa-gamma-7b-v1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 37/65, MLP 96/96, Attention 128/128, lm_head 1/1
2 derivatives checked
- mradermacher/029-shisa-gamma-7b-v1-v2new-dpo405b-i1-GGUF: Quantization
- mradermacher/029-shisa-gamma-7b-v1-v2new-dpo405b-GGUF: Same weights, converted