nbeerbower/bruphin-theta

Full fine-tune vs Weyaxi/Einstein-v4-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/bruphin-theta-GGUF: Same weights, converted
• nbeerbower/StrangeBru-7B: Full fine-tune

On the Hub · Downloads on Model Pulse