rhaymison/Qwen-portuguese-luana-7b

Full fine-tune vs Qwen/Qwen1.5-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 63/65, MLP 96/96, Attention 224/224, lm_head 1/1

2 derivatives checked

• mradermacher/Qwen-portuguese-luana-7b-i1-GGUF: Quantization
• mradermacher/Qwen-portuguese-luana-7b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse