mradermacher/malaysian-Llama-3.2-1B-Instruct-GGUF
Partial fine-tune vs mesolitica/Malaysian-Llama-3.2-1B-Instruct-v0.1. mradermacher/malaysian-Llama-3.2-1B-Instruct-GGUF is a GGUF (F16) of different weights. Partial change: 82% of the weights changed (attention, lm_head, mlp), in 16 of 16 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 0/33, MLP 48/48, Attention 64/64