mradermacher/RoLlama2-7b-Instruct-DPO-GGUF
Full fine-tune vs OpenLLM-Ro/RoLlama2-7b-Instruct-DPO. mradermacher/RoLlama2-7b-Instruct-DPO-GGUF is a GGUF (F16) of different weights. 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