QuantFactory/Biggie-SmoLlm-0.4B-GGUF
Full fine-tune vs HuggingFaceTB/SmolLM-360M-Instruct. QuantFactory/Biggie-SmoLlm-0.4B-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128