mradermacher/DeepSeek-R1-Distill-Qwen-7B-GSPO-Basic-GGUF
Full fine-tune vs leonMW/DeepSeek-R1-Distill-Qwen-7B-GSPO-Basic. mradermacher/DeepSeek-R1-Distill-Qwen-7B-GSPO-Basic-GGUF is a GGUF (F16) of different weights. Fine-tune: 93% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 45/57, MLP 84/84, Attention 196/196, lm_head 1/1