yuxinlu1/Mellum2-12B-A2.5B-Claude-4.6-4.8-Opus-Thinking-GGUF

Full fine-tune vs JetBrains/Mellum2-12B-A2.5B-Thinking. yuxinlu1/Mellum2-12B-A2.5B-Claude-4.6-4.8-Opus-Thinking-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 0/113, MLP 0/28, Attention 112/112, lm_head 1/1

On the Hub · Downloads on Model Pulse