TheDrummer/Anubis-Mini-8B-v1
LoRA-style vs shb777/Llama-3.3-8B-Instruct-128K. 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: Norms 0/65, MLP 96/96, Attention 128/128
5 derivatives checked
- bartowski/TheDrummer_Anubis-Mini-8B-v1-GGUF: Same weights, converted
- mradermacher/Anubis-Mini-8B-v1-i1-GGUF: Quantization
- mradermacher/Anubis-Mini-8B-v1-GGUF: Same weights, converted
- EnlistedGhost/Anubis-Mini-11B-v1-Vision: Different architecture
- coder3101/Anubis-Mini-8B-v1-heretic: Abliterated