Cas-Warehouse/UltraHermes-Merge
Full fine-tune vs argilla/CapybaraHermes-2.5-Mistral-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/UltraHermes-Merge-GGUF: Same weights, converted
- mradermacher/UltraHermes-Merge-i1-GGUF: Quantization
- Casual-Autopsy/WorldGen-v2-TEST002: Full fine-tune