ArRENCEAI/Qwen2.5-1.5B-OBLITERATED

Partial fine-tune vs Qwen/Qwen2.5-1.5B. Partial change: 30% of the weights changed (attention, embeddings, mlp), in 5 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 0/57, MLP 15/84, Attention 25/196

2 derivatives checked

• mradermacher/Qwen2.5-1.5B-OBLITERATED-i1-GGUF: Quantization
• mradermacher/Qwen2.5-1.5B-OBLITERATED-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse