saishf/Long-Neural-SOVLish-Devil-8B-L3-262K
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/Long-Neural-SOVLish-Devil-8B-L3-262K at load time.
3 derivatives checked
- mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-i1-GGUF: Quantization
- mradermacher/Long-Neural-SOVLish-Devil-8B-L3-262K-GGUF: Same weights, converted
- saishf/Extended-Mega-Mash-262K-8B-L3: Full fine-tune