DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED
LoRA-style (fewer layers) vs OBLITERATUS/Ornith-1.5-9B-OBLITERATED. DuoNeural/Cyber-Ornith-1.5-9B-OBLITERATED matches part of OBLITERATUS/Ornith-1.5-9B-OBLITERATED (427 of its 775 tensors; the rest of OBLITERATUS/Ornith-1.5-9B-OBLITERATED has no counterpart). On the shared part: 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/105, Attention 32/224, MLP 96/96, lm_head 0/1
3 derivatives checked
- mradermacher/Cyber-Ornith-1.5-9B-OBLITERATED-i1-GGUF: Quantization
- mradermacher/Cyber-Ornith-1.5-9B-OBLITERATED-GGUF: Same weights, converted
- Atomic-Germ/Cyber-Ornith-1.5-9B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.