McGill-NLP/AfriqueQwen3.5-0.8B-50Langs

Partial fine-tune vs Qwen/Qwen3.5-0.8B-Base. Partial change: 88% of the weights changed (attention, embeddings, mlp, norms), in 24 of 24 layers.

Tensors changed: Attention 166/216, Norms 79/129, Embeddings 1/4, MLP 72/124

2 derivatives checked

• mradermacher/AfriqueQwen3.5-0.8B-50Langs-i1-GGUF: Quantization
• mradermacher/AfriqueQwen3.5-0.8B-50Langs-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse