SURESHBEEKHANI/Deep-seek-R1-Medical-reasoning-SFT
Full fine-tune vs unsloth/DeepSeek-R1-Distill-Llama-8B. SURESHBEEKHANI/Deep-seek-R1-Medical-reasoning-SFT is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1