saishf/Merge-Mayhem-L3-V2.1
Adapter vs ResplendentAI/Aura_Llama3. ResplendentAI/Aura_Llama3 is a LoRA adapter, not full weights: rank 128, on q_proj, v_proj in 32 layers (64 adapted matrices). It modifies saishf/Merge-Mayhem-L3-V2.1 at load time.
3 derivatives checked
- mradermacher/Merge-Mayhem-L3-V2.1-i1-GGUF: Quantization
- featherless-ai-quants/saishf-Merge-Mayhem-L3-V2.1-GGUF: Quantization
- mradermacher/Merge-Mayhem-L3-V2.1-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.