jaspionjader/Auro-Kosmos-EVAA-v2.3-8B

Full fine-tune vs jaspionjader/Auro-Kosmos-EVAA-v2.2-8B. Fine-tune: 94% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 62/65, MLP 90/96, Attention 119/128

2 derivatives checked

• mradermacher/Auro-Kosmos-EVAA-v2.3-8B-i1-GGUF: Quantization
• mradermacher/Auro-Kosmos-EVAA-v2.3-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse