Mungert/Fathom-R1-14B-GGUF
Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-14B. Mungert/Fathom-R1-14B-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, Attention 336/336, MLP 144/144, Norms 97/97, lm_head 1/1