saishf/Fett-uccine-11B-Experiment
Partial fine-tune (fewer layers) vs Epiculous/Fett-uccine-7B. Epiculous/Fett-uccine-7B matches part of saishf/Fett-uccine-11B-Experiment (291 of its 435 tensors; the rest of saishf/Fett-uccine-11B-Experiment has no counterpart). On the shared part: Partial change: 24% of the weights changed (attention, mlp, norms), in 8 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 16/65, MLP 24/96, Attention 32/128, lm_head 0/1
1 derivatives checked
- mradermacher/Fett-uccine-11B-Experiment-i1-GGUF: Quantization