nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
Partial fine-tune vs flammenai/Mahou-1.5-mistral-nemo-12B. Partial change: 53% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 50/81, MLP 55/120, Attention 69/160, lm_head 1/1
18 derivatives checked
- mradermacher/Mahou-1.5-mistral-nemo-12B-lorablated-i1-GGUF: Quantization
- QuantFactory/Mistral-Nemo-Prism-12B-v7-GGUF: Quantization
- featherless-ai-quants/nbeerbower-Mahou-1.5-mistral-nemo-12B-lorablated-GGUF: Quantization
- mradermacher/Mahou-1.5-mistral-nemo-12B-lorablated-GGUF: Same weights, converted
- nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated-GGUF: Same weights, converted
- nbeerbower/Mistral-Nemo-Prism-12B: LoRA-style
- nbeerbower/mistral-nemo-kartoffel-12B: LoRA-style
- nbeerbower/mistral-nemo-narwhal-12B: LoRA-style
- nbeerbower/SmolNemo-12B-FFT-experimental: Full fine-tune
- nbeerbower/Mistral-Nemo-Moderne-12B-FFT-experimental: Full fine-tune
- nbeerbower/mistral-nemo-bophades3-12B: LoRA-style
- nbeerbower/Mistral-Nemo-Prism-12B-v7: LoRA-style
- nbeerbower/Mistral-Nemo-Prism-12B-v2: LoRA-style
- nbeerbower/mistral-nemo-gutenberg3-12B: LoRA-style
- nbeerbower/Mistral-Nemo-Prism-12B-v5: LoRA-style
- nbeerbower/Mistral-Nemo-Prism-12B-v4: LoRA-style
- nbeerbower/Mistral-Nemo-Prism-12B-v6: LoRA-style
- nbeerbower/Mistral-Nemo-Prism-12B-v3: LoRA-style