vanta-research/mox-small-1
LoRA-style vs allenai/Olmo-3.1-32B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, MLP 0/192, Norms 0/257, Attention 256/256, lm_head 0/1
2 derivatives checked
- mradermacher/mox-small-1-i1-GGUF: Quantization
- mradermacher/mox-small-1-GGUF: Quantization