AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16
LoRA-style vs ornith-ai/Ornith-1.0-35B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of conv1d, down_proj, gate, o_proj, out_proj changed, in 37 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/241, Attention 37/388, MLP 68/2366
4 derivatives checked
- AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-NVFP4: Quantization
- vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF: Quantization
- mrexodia/Ornith-1.0-35B-AEON-Ultimate-Uncensored-MTP-GGUF: Same weights, converted
- AninoDevel/Ornith-1.0-35B-AEON-Ultimate-Uncensored-MTP-GGUF: Same weights, converted
2 other repos hold byte-for-byte identical weight files.