prithivMLmods/MegaScience-Qwen-GGUF
Partial fine-tune vs MegaScience/Qwen2.5-1.5B-MegaScience. prithivMLmods/MegaScience-Qwen-GGUF is a GGUF (F16) of different weights. Partial change: 0% of the weights changed (attention), in 3 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 3/196