mradermacher/Gemma-Rhino-27B-RAG-GGUF

Full fine-tune vs QomSSLab/Gemma-Rhino-27B-RAG. mradermacher/Gemma-Rhino-27B-RAG-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 46 of 46 layers.

Tensors changed: Embeddings 1/1, Norms 0/185, MLP 138/138, Attention 184/184

On the Hub · Downloads on Model Pulse