Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B
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 Cas-Warehouse/Llama-3-MopeyMule-Blackroot-8B at load time.
16 derivatives checked
- mradermacher/MopeyMule-Blackroot-8B-i1-GGUF: Quantization
- QuantFactory/L3-Umbral-Mind-RP-v3.0-8B-GGUF: Full fine-tune
- mradermacher/MopeyMule-Blackroot-8B-GGUF: Same weights, converted
- Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B: Full fine-tune
- mradermacher/Llama-3-MopeyMule-Blackroot-8B-i1-GGUF: Quantization
- mradermacher/Llama-3-MopeyMule-Blackroot-8B-GGUF: Same weights, converted
- Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B: Full fine-tune
- Casual-Autopsy/L3-Umbral-Mind-RP-v0.3-8B: Full fine-tune
- Cas-Warehouse/Llama-3-Mopeyfied-Psychology-8B: Full fine-tune
- Cas-Warehouse/Llama-3-SOVL-MopeyMule-Blackroot-8B: LoRA-style
- Skarmorie/L3-Lunaris-Mopey-Psy-Med: Full fine-tune
- mergekit-community/Umbral-v0.4-1: Full fine-tune
- mergekit-community/Umbral-v0.4-2: Full fine-tune
- Cas-Archive/L3-Umbral-Mind-RP-v1.0.1-8B: Full fine-tune
- DopeyGay/L3-Reapers-Coast-8B: Full fine-tune
- mergekit-community/Umbral-v0.4-3: Full fine-tune