ArRENCEAI/Qwen2.5-14B-OBLITERATED

Full fine-tune vs Qwen/Qwen2.5-14B. Fine-tune: 91% of the weights changed, across 46 of 48 layers.

Tensors changed: Embeddings 0/1, Norms 0/97, MLP 138/144, Attention 230/336, lm_head 1/1

2 derivatives checked

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

On the Hub · Downloads on Model Pulse