nbeerbower/mistral-nemo-kartoffel-12B
LoRA-style vs nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 120/120, Attention 160/160
14 derivatives checked
- mradermacher/mistral-nemo-kartoffel-12B-i1-GGUF: Quantization
- featherless-ai-quants/nbeerbower-mistral-nemo-kartoffel-12B-GGUF: Quantization
- nbeerbower/mistral-nemo-kartoffel-PRUNE3: Partial fine-tune (fewer layers)
- nbeerbower/DoublePotato-Mistral-Nemo-13B: Partial fine-tune
- DevQuasar-7/nbeerbower.mistral-nemo-kartoffel-12B-GGUF: Same weights, converted
- mradermacher/mistral-nemo-kartoffel-12B-GGUF: Quantization
- nbeerbower/Kartoffel-Deepfry-12B: LoRA-style
- nbeerbower/Schreiber-mistral-nemo-12B: LoRA-style
- nbeerbower/Denker-mistral-nemo-12B: LoRA-style
- nbeerbower/GigaPotato-Mistral-Nemo-23B: Partial fine-tune (fewer layers)
- nbeerbower/BigKartoffel-mistral-nemo-20B: Partial fine-tune (fewer layers)
- nbeerbower/TriplePotato-Mistral-Nemo-15B: Partial fine-tune
- nbeerbower/mistral-nemo-kartoffel-PRUNE: Partial fine-tune
- nbeerbower/mistral-nemo-kartoffel-PRUNE2: Partial fine-tune