Vasanth/Beast-Soul-new
Full fine-tune vs flemmingmiguel/MBX-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1
2 derivatives checked
- mradermacher/Beast-Soul-new-i1-GGUF: Quantization
- mradermacher/Beast-Soul-new-GGUF: Same weights, converted