mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF

Full fine-tune vs ChuGyouk/Qwen3-4B-DeepWriting-SFT. mradermacher/Qwen3-4B-DeepWriting-SFT-GGUF is a GGUF (F16) of different weights. Fine-tune: 90% of the weights changed, across 36 of 36 layers.

Tensors changed: Norms 145/145, Embeddings 0/1, MLP 108/108, Attention 144/144

On the Hub · Downloads on Model Pulse