dicta-il/dictalm2.0-instruct

Full fine-tune vs dicta-il/dictalm2.0. Fine-tune: 98% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 12/65, MLP 96/96, Attention 128/128, lm_head 1/1

2 derivatives checked

• mradermacher/dictalm2.0-instruct-GGUF: Same weights, converted
• 618AI/dictalm2-it-qa-fine-tune: LoRA-style

On the Hub · Downloads on Model Pulse