codegood/DistHermYam-7B-ties
Full fine-tune vs eren23/DistilHermes-2.5-Mistral-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 8/65, MLP 96/96, Attention 128/128
1 derivatives checked
- mradermacher/DistHermYam-7B-ties-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.