ermiaazarkhalili/VibeThinker-3B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF
Full fine-tune vs WeiboAI/VibeThinker-3B. ermiaazarkhalili/VibeThinker-3B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 0/73, MLP 108/108, Attention 144/252