ClaudioItaly/Evolutionstory-7B-v2.2
Full fine-tune vs BarraHome/Mistroll-7B-v2.2. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 53/65, MLP 96/96, Attention 128/128, lm_head 1/1
7 derivatives checked
- QuantFactory/Evolutions-Reflex-GGUF: Full fine-tune
- mradermacher/Evolutionstory-7B-v2.2-i1-GGUF: Quantization
- mradermacher/Evolutionstory-7B-v2.2-GGUF: Same weights, converted
- ClaudioItaly/Albacus: Partial fine-tune
- ClaudioItaly/Evolutionstory-7B-v3.0: Same weights, converted
- ClaudioItaly/Evolutions-Reflex: Full fine-tune
- ClaudioItaly/Pulzar-DPO-7: Full fine-tune