Nelathan/Qwen2-7B-FocusMix

Full fine-tune vs MaziyarPanahi/calme-2.8-qwen2-7b. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Norms 57/57, MLP 84/84, Attention 196/196

2 derivatives checked

• mradermacher/Qwen2-7B-FocusMix-i1-GGUF: Quantization
• mradermacher/Qwen2-7B-FocusMix-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse