sapienzanlp/Minerva-7B-instruct-v1.0

Full fine-tune vs sapienzanlp/Minerva-7B-base-v1.0. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 51/65, MLP 96/96, Attention 128/128

2 derivatives checked

• sapienzanlp/Minerva-7B-instruct-v1.0-GGUF: Same weights, converted
• DevQuasar-5/sapienzanlp.Minerva-7B-instruct-v1.0-GGUF: Quantization

On the Hub · Downloads on Model Pulse