jaspionjader/Auro-Kosmos-EVAA-v2.2-8B
Full fine-tune vs jaspionjader/Auro-Kosmos-EVAA-v2.1-8B. Fine-tune: 95% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 90/96, Attention 120/128
4 derivatives checked
- mradermacher/Auro-Kosmos-EVAA-v2.2-8B-i1-GGUF: Quantization
- mradermacher/Auro-Kosmos-EVAA-v2.2-8B-GGUF: Same weights, converted
- jaspionjader/Kosmos-EVAA-v11-8B: Full fine-tune
- jaspionjader/Auro-Kosmos-EVAA-v2.3-8B: Full fine-tune