BenevolenceMessiah/Qwen2.5-72B-2x-Instruct-TIES-v1.0

Full fine-tune vs Qwen/Qwen2.5-72B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: MLP 240/240, Attention 560/560, Norms 147/161

1 derivatives checked

• mradermacher/Qwen2.5-72B-2x-Instruct-TIES-v1.0-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse