bunnycore/Qwen2.5-7B-RRP-1M-Thinker

Full fine-tune vs bunnycore/QandoraExp-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

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

1 derivatives checked

• mradermacher/Qwen2.5-7B-RRP-1M-Thinker-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse