amadeusai/Amadeus-Verbo-BI-Qwen-2.5-32B-PT-BR-Instruct-Experimental
Full fine-tune vs Qwen/Qwen2.5-32B. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 122/129, MLP 192/192, Attention 447/448, lm_head 1/1
3 derivatives checked
- mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF: Quantization
- mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF: Quantization
- mradermacher/qwen2.5-32B-PT-BR-Instruct-GGUF: Quantization