yasserrmd/Human-Like-Qwen2.5-1.5B-Instruct-gguf
Full fine-tune vs yasserrmd/Human-Like-Qwen2.5-1.5B-Instruct. yasserrmd/Human-Like-Qwen2.5-1.5B-Instruct-gguf is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 1/57, MLP 84/84, Attention 113/196