mradermacher/Marco-LLM-AR-i1-GGUF
Full fine-tune vs ATH-MaaS/Marco-LLM-AR-V2. mradermacher/Marco-LLM-AR-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, Attention 196/196, MLP 84/84, lm_head 1/1