SynastriaNetworks/U1-0817
LoRA-style vs SynastriaNetworks/Uirapuru-U1-9B. 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 31 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, MLP 96/211, Attention 32/336, other 0/1, Norms 0/221
4 derivatives checked
- mradermacher/U1-0817-i1-GGUF: Quantization
- mradermacher/Uirapuru-U1.1-i1-GGUF: Quantization
- mradermacher/Uirapuru-U1.1-GGUF: Same weights, converted
- mradermacher/U1-0817-GGUF: Same weights, converted