mradermacher/DeepSeek-R1-Distill-Qwen-14B-GSPO-Basic-GGUF
Full fine-tune vs leonMW/DeepSeek-R1-Distill-Qwen-14B-GSPO-Basic. mradermacher/DeepSeek-R1-Distill-Qwen-14B-GSPO-Basic-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 92/97, MLP 144/144, Attention 336/336, lm_head 1/1