jaspionjader/Kosmos-EVAA-gamma-8B

Full fine-tune vs jaspionjader/Kosmos-EVAA-v12-8B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128

2 derivatives checked

• mradermacher/Kosmos-EVAA-gamma-8B-GGUF: Same weights, converted
• jaspionjader/Kosmos-EVAA-gamma-light-8B: Full fine-tune

On the Hub · Downloads on Model Pulse