mengmeong/meng-programming-skill-finetune
Full fine-tune vs nisten/Biggie-SmoLlm-0.15B-Base. nisten/Biggie-SmoLlm-0.15B-Base is a GGUF (BF16) of different weights. Fine-tune: 100% of the weights changed, across 35 of 35 layers.
Tensors changed: Embeddings 1/1, Attention 140/140, MLP 105/105, Norms 71/71