israel/AfriGuard-AfriqueQwen3.5-4B-50Langs

VISIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:4.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 18, 2026License:otherArchitecture:Transformer Featherless Exclusive Cold

AfriGuard-AfriqueQwen3.5-4B-50Langs is a 4.5 billion parameter language model developed by israel, fine-tuned from McGill-NLP/AfriqueQwen3.5-4B-50Langs. This model is specifically adapted using the afriguard dataset, making it suitable for applications requiring specialized knowledge from that domain. With a 32768 token context length, it is designed for tasks benefiting from extensive contextual understanding.

Loading preview...

Model Overview

AfriGuard-AfriqueQwen3.5-4B-50Langs is a 4.5 billion parameter language model, fine-tuned by israel from the base model McGill-NLP/AfriqueQwen3.5-4B-50Langs. This adaptation specifically leverages the afriguard dataset, indicating a specialization for tasks and applications within that domain. The model was trained with a learning rate of 1e-05 over 1 epoch, utilizing a multi-GPU setup and AdamW optimizer.

Key Training Details

  • Base Model: McGill-NLP/AfriqueQwen3.5-4B-50Langs
  • Fine-tuning Dataset: afriguard dataset
  • Learning Rate: 1e-05
  • Epochs: 1.0
  • Optimizer: AdamW_TORCH_FUSED
  • Framework Versions: Transformers 5.8.0, Pytorch 2.14.0+cu130, Datasets 4.0.0, Tokenizers 0.22.2

Intended Use Cases

Given its fine-tuning on the afriguard dataset, this model is likely best suited for:

  • Applications requiring understanding or generation of content related to the afriguard domain.
  • Tasks where specialized knowledge from the fine-tuning data is beneficial.

Further details on specific intended uses and limitations would require more information about the afriguard dataset and the fine-tuning objectives.