MYC081/Qwen2.5-3B-WPO-bf16-1

Full fine-tune vs Qwen/Qwen2.5-3B-Instruct. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 57/73, MLP 108/108, Attention 250/252

2 derivatives checked

• mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF: Quantization
• mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse