mradermacher/AceReason-Nemotron-1.1-Off-policy-GRPO-7B-GGUF
Partial fine-tune vs KRAFTON/AceReason-Nemotron-1.1-Offline-GRPO-7B. mradermacher/AceReason-Nemotron-1.1-Off-policy-GRPO-7B-GGUF is a GGUF (F16) of different weights. Partial change: 83% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 57/57, MLP 81/84, Attention 196/196, lm_head 0/1