mradermacher/Qwen2.5-Coder-7B-Instruct-OBLITERATED-GGUF
Partial fine-tune vs OBLITERATUS/Qwen2.5-Coder-7B-Instruct-OBLITERATED. mradermacher/Qwen2.5-Coder-7B-Instruct-OBLITERATED-GGUF is a GGUF (F16) of different weights. Partial change: 87% of the weights changed (attention, lm_head, mlp), in 26 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 78/84, Attention 130/196, lm_head 1/1