eren23/ogno-monarch-jaskier-merge-7b

Full fine-tune vs bardsai/jaskier-7b-dpo-v5.6. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/ogno-monarch-jaskier-merge-7b-GGUF: Same weights, converted
• mayacinka/ramonda-monarch-7b: Full fine-tune

On the Hub · Downloads on Model Pulse