Infermatic/14b-Qwen2.5-Infermatic-Crea-v1

Full fine-tune vs Qwen/Qwen2.5-14B-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Norms 0/97, MLP 144/144, Attention 220/336

2 derivatives checked

• mradermacher/14b-Qwen2.5-Infermatic-Crea-v1-i1-GGUF: Quantization
• mradermacher/14b-Qwen2.5-Infermatic-Crea-v1-GGUF: Quantization

On the Hub · Downloads on Model Pulse