Surpem/Supertron2.1-8B-A1B

Full fine-tune vs LiquidAI/LFM2.5-8B-A1B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: MLP 2140/2162, Embeddings 2/2, other 54/54, Norms 20/60, Attention 24/24

3 derivatives checked

• mradermacher/Supertron-2.1-8B-A1B-i1-GGUF: Quantization
• Surpem/Supertron-2.1-8B-A1B-GGUF: Same weights, converted
• mradermacher/Supertron-2.1-8B-A1B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse