Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

olaverse
/
PurpleMIST-Mini-2.0

Text Classification
Transformers
Safetensors
qwen3_5
feature-extraction
multilingual
system-one
typed-decisions
decision-model
calibration
probabilistic-classification
vision
multimodal
long-context
african-languages
nigerian-languages
qwen3.5
Eval Results
Model card Files Files and versions
xet
Community

Instructions to use olaverse/PurpleMIST-Mini-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use olaverse/PurpleMIST-Mini-2.0 with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-classification", model="olaverse/PurpleMIST-Mini-2.0")
    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoProcessor, AutoModel
    
    processor = AutoProcessor.from_pretrained("olaverse/PurpleMIST-Mini-2.0")
    model = AutoModel.from_pretrained("olaverse/PurpleMIST-Mini-2.0", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
PurpleMIST-Mini-2.0 / eval
6.74 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
olumideola's picture
olumideola
mini 2.0: full fine-tune of Qwen/Qwen3.5-4B-Base, two-block attention, no truncation (98,304 tokens), vision
1611606 verified 6 days ago
  • metrics.csv
    790 Bytes
    mini 2.0: full fine-tune of Qwen/Qwen3.5-4B-Base, two-block attention, no truncation (98,304 tokens), vision 6 days ago
  • metrics_african_by_lang.csv
    870 Bytes
    mini 2.0: full fine-tune of Qwen/Qwen3.5-4B-Base, two-block attention, no truncation (98,304 tokens), vision 6 days ago
  • metrics_by_kind.csv
    2.3 kB
    mini 2.0: full fine-tune of Qwen/Qwen3.5-4B-Base, two-block attention, no truncation (98,304 tokens), vision 6 days ago
  • predictions.parquet
    6.73 MB
    xet
    mini 2.0: full fine-tune of Qwen/Qwen3.5-4B-Base, two-block attention, no truncation (98,304 tokens), vision 6 days ago