mradermacher/bitnet_b1_58-large-i1-GGUF
Full fine-tune vs 1bitLLM/bitnet_b1_58-large. mradermacher/bitnet_b1_58-large-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 0/73, MLP 72/72, Attention 96/120