DreadPoor/Spei_Meridiem-8B-model_stock
Adapter vs Blackroot/Llama-3-8B-Abomination-LORA. Blackroot/Llama-3-8B-Abomination-LORA is a LoRA adapter, not full weights: rank 64, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 32 layers (224 adapted matrices). It modifies DreadPoor/Spei_Meridiem-8B-model_stock at load time.
4 derivatives checked
- mradermacher/Spei_Meridiem-8B-model_stock-i1-GGUF: Quantization
- mradermacher/Spei_Meridiem-8B-model_stock-GGUF: Same weights, converted
- djuna/L3.1-Promissum_Mane-8B-Della-1.5-calc: Full fine-tune
- djuna/L3.1-Promissum_Mane-8B-Della-calc: Full fine-tune