ClaudioItaly/Pulzar-DPO-7
Full fine-tune vs ClaudioItaly/Evolutionstory-7B-v2.2. Fine-tune: 90% of the weights changed, across 30 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 22/65, MLP 90/96, Attention 120/128
2 derivatives checked
- mradermacher/Pulzar-DPO-7-GGUF: Quantization
- mradermacher/Pulzar-DPO-7-i1-GGUF: Quantization