mradermacher/OpenThinker2-Off-policy-GRPO-7B-GGUF
Full fine-tune vs KRAFTON/OpenThinker2-Offline-GRPO-7B. mradermacher/OpenThinker2-Off-policy-GRPO-7B-GGUF is a GGUF (F16) of different weights. Fine-tune: 93% 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 0/1