CultriX/Qwen2.5-14B-Verged

Full fine-tune vs CultriX/Qwen2.5-14B-ReasoningMerge. Fine-tune: 98% of the weights changed, across 48 of 48 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 97/97, MLP 141/144, Attention 329/336

2 derivatives checked

• mradermacher/Qwen2.5-14B-Verged-i1-GGUF: Quantization
• mradermacher/Qwen2.5-14B-Verged-GGUF: Quantization

On the Hub · Downloads on Model Pulse