Synapticode/bitnet-b1.58-2B-4T-tq2_0-gguf
LoRA-style vs microsoft/bitnet-b1.58-2B-4T-bf16. Synapticode/bitnet-b1.58-2B-4T-tq2_0-gguf is a GGUF (F16/TQ2_0) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 30 of 30 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 90/90, Attention 120/120