JetBrains/Mellum2.1-12B-A2.5B-Thinking
Full fine-tune vs JetBrains/Mellum2-12B-A2.5B-Base. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 113/113, MLP 2773/2773, Attention 112/112, lm_head 1/1
5 derivatives checked
- JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF: Same weights, converted
- bartowski/Mellum2.1-12B-A2.5B-Thinking-GGUF: Same weights, converted
- prithivMLmods/JetBrains-Mellum2.1-12B-A2.5B-Thinking-GGUF: Same weights, converted
- randmaru/Mellum2.1-12B-A2.5B-Thinking-mlx-mxfp4: Quantization
- alexwkleung/Mellum2.1-12B-A2.5B-Thinking-Abliterated-GGUF: Quantization