nbeerbower/BigKartoffel-mistral-nemo-20B
Partial fine-tune (fewer layers) vs nbeerbower/mistral-nemo-kartoffel-12B. nbeerbower/mistral-nemo-kartoffel-12B matches part of nbeerbower/BigKartoffel-mistral-nemo-20B (363 of its 633 tensors; the rest of nbeerbower/BigKartoffel-mistral-nemo-20B has no counterpart). On the shared part: Partial change: 67% of the weights changed (attention, mlp, norms), in 30 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 60/81, MLP 90/120, Attention 120/160, lm_head 0/1
4 derivatives checked
- mradermacher/BigKartoffel-mistral-nemo-i1-GGUF: Quantization
- mradermacher/BigKartoffel-mistral-nemo-20B-i1-GGUF: Quantization
- mradermacher/BigKartoffel-mistral-nemo-GGUF: Quantization
- mradermacher/BigKartoffel-mistral-nemo-20B-GGUF: Quantization