mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF
Full fine-tune vs nvidia/Nemotron-Research-Reasoning-Qwen-1.5B. mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1