LilRg/PRYMMAL-slerp-Merge

Full fine-tune vs jpacifico/Chocolatine-3B-Instruct-DPO-Revised. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 62/64, Attention 62/64, lm_head 1/1

1 derivatives checked

• mradermacher/PRYMMAL-slerp-Merge-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse