mradermacher/MetaMath-Qwen2.5-0.5b-GGUF
Partial fine-tune vs rawsh/MetaMath-Qwen2.5-0.5b. mradermacher/MetaMath-Qwen2.5-0.5b-GGUF is a GGUF (F16) of different weights. Partial change: 78% of the weights changed (attention, lm_head, mlp), in 24 of 24 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 0/49, MLP 72/72, Attention 96/168