McGill-NLP/AfriqueQwen3.5-9B-50Langs
Full fine-tune vs Qwen/Qwen3.5-9B-Base. Fine-tune: 95% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/4, MLP 96/208, Attention 218/332, Norms 105/215
3 derivatives checked
- McGill-NLP/AfriqueQwen3.5-9B-50Langs-Instruct-v1: Full fine-tune (fewer layers)
- mradermacher/AfriqueQwen3.5-9B-50Langs-i1-GGUF: Quantization
- mradermacher/AfriqueQwen3.5-9B-50Langs-GGUF: Same weights, converted