Mungert/DiffuCoder-7B-cpGRPO-GGUF
Full fine-tune vs apple/DiffuCoder-7B-Instruct. Mungert/DiffuCoder-7B-cpGRPO-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 93% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 46/57, MLP 84/84, Attention 196/196, lm_head 1/1