Yukendiran/Liceron-SecOps-Model
Full fine-tune vs DeepHat/DeepHat-V1-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1
1 derivatives checked
- mradermacher/Liceron-SecOps-Model-GGUF: Same weights, converted