mergekit-community/YorkShire11
Full fine-tune (fewer layers) vs Sao10K/Fimbulvetr-11B-v2. mergekit-community/YorkShire11 matches part of Sao10K/Fimbulvetr-11B-v2 (291 of its 435 tensors; the rest of Sao10K/Fimbulvetr-11B-v2 has no counterpart). On the shared part: Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1
1 derivatives checked
- MaziyarPanahi/YorkShire11-GGUF: Quantization