mergekit-community/L3-Boshima-a
Full fine-tune vs Casual-Autopsy/L3-Deluxe-Scrambled-Eggs-On-Toast-8B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128
2 derivatives checked
- mradermacher/L3-Boshima-a-i1-GGUF: Quantization
- mradermacher/L3-Boshima-a-GGUF: Same weights, converted