louisgrc/Montebello_7B_SLERP

Full fine-tune vs louisgrc/Marengoli_7B_SLERP. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

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

1 derivatives checked

• mradermacher/Montebello_7B_SLERP-GGUF: Quantization

On the Hub · Downloads on Model Pulse