Kaoeiri/Qwenwify2.5-32B-v3.98

Full fine-tune vs Dans-DiscountModels/Qwen2.5-32B-ChatML. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 128/129, MLP 192/192, Attention 448/448

2 derivatives checked

• mradermacher/Qwenwify2.5-32B-v3.98-i1-GGUF: Quantization
• mradermacher/Qwenwify2.5-32B-v3.98-GGUF: Quantization

On the Hub · Downloads on Model Pulse