mradermacher/unbound-e2b-GGUF
LoRA-style (fewer layers) vs evalengine/unbound-e2b. mradermacher/unbound-e2b-GGUF matches part of evalengine/unbound-e2b (505 of its 1951 tensors; the rest of evalengine/unbound-e2b has no counterpart). On the shared part: mradermacher/unbound-e2b-GGUF is a GGUF (F16) 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 35 of 35 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/227, MLP 105/105, other 0/71, Attention 100/100