jsfs11/WONMSeverusDevilv2-TIES
Full fine-tune vs PetroGPT/WestSeverus-7B-DPO-v2. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 63/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/WONMSeverusDevilv2-TIES-GGUF: Same weights, converted
- mradermacher/WONMSeverusDevilv2-TIES-i1-GGUF: Quantization
- jsfs11/WONMSeverusDevilv3-LORAMERGED: Full fine-tune