gianni-cor/bitnet_b1_58-large-TQ2_0
Full fine-tune vs 1bitLLM/bitnet_b1_58-large. gianni-cor/bitnet_b1_58-large-TQ2_0 is a GGUF (TQ2_0/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