amadeusai/Amadeus-Verbo-BI-Qwen-2.5-3B-PT-BR-Instruct-Experimental
Full fine-tune vs Qwen/Qwen2.5-3B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 54/73, MLP 108/108, Attention 241/252
2 derivatives checked
- mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-i1-GGUF: Quantization
- mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF: Same weights, converted