mradermacher/EVisRAG-7B-i1-GGUF

Full fine-tune (fewer layers) vs Boggy666/EVisRAG-7B. mradermacher/EVisRAG-7B-i1-GGUF matches part of Boggy666/EVisRAG-7B (339 of its 729 tensors; the rest of Boggy666/EVisRAG-7B has no counterpart). On the shared part: mradermacher/EVisRAG-7B-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: lm_head 1/1, Norms 54/57, Attention 196/196, MLP 84/84, Embeddings 1/1

On the Hub · Downloads on Model Pulse