opencerebral/Boris-125M-Instruct

Full fine-tune vs opencerebral/Boris-125M. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: Attention 48/48, Norms 50/50, MLP 48/48, Embeddings 2/2

2 derivatives checked

• opencerebral/Boris-125M-Instruct-GGUF: Same weights, converted
• mradermacher/Boris-125M-Instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse