Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • 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

Raymond1122
/
metask-jev-4b-policy-mix

Text Classification
Transformers
Safetensors
English
qwen3_5
image-text-to-text
typed-decisions
calibrated-classification
system-one
classification
structured-prediction
candidate-logit
jev
single-forward-pass
commercial-use
Model card Files Files and versions
xet
Community

Instructions to use Raymond1122/metask-jev-4b-policy-mix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use Raymond1122/metask-jev-4b-policy-mix with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-classification", model="Raymond1122/metask-jev-4b-policy-mix")
    # Load model directly
    from transformers import AutoProcessor, AutoModelForMultimodalLM
    
    processor = AutoProcessor.from_pretrained("Raymond1122/metask-jev-4b-policy-mix")
    model = AutoModelForMultimodalLM.from_pretrained("Raymond1122/metask-jev-4b-policy-mix", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
metask-jev-4b-policy-mix
9.1 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 4 commits
Raymond1122's picture
Raymond1122
Laya-style model card: benchmark figures, 13-subset table w/ CI, honest limits
7775e0b verified 10 days ago
  • eval
    Laya-style model card: benchmark figures, 13-subset table w/ CI, honest limits 10 days ago
  • .gitattributes
    1.7 kB
    Laya-style model card: benchmark figures, 13-subset table w/ CI, honest limits 10 days ago
  • README.md
    7.05 kB
    Laya-style model card: benchmark figures, 13-subset table w/ CI, honest limits 10 days ago
  • chat_template.jinja
    7.76 kB
    metask-jev-4b: Qwen3.5-4B LoRA for typed decisions (13-subset 79.6%, JevBench 80.1% @4096) 10 days ago
  • config.json
    2.99 kB
    metask-jev-4b: Qwen3.5-4B LoRA for typed decisions (13-subset 79.6%, JevBench 80.1% @4096) 10 days ago
  • generation_config.json
    164 Bytes
    metask-jev-4b: Qwen3.5-4B LoRA for typed decisions (13-subset 79.6%, JevBench 80.1% @4096) 10 days ago
  • model.safetensors
    9.08 GB
    xet
    metask-jev-4b: Qwen3.5-4B LoRA for typed decisions (13-subset 79.6%, JevBench 80.1% @4096) 10 days ago
  • tokenizer.json
    20 MB
    xet
    metask-jev-4b: Qwen3.5-4B LoRA for typed decisions (13-subset 79.6%, JevBench 80.1% @4096) 10 days ago
  • tokenizer_config.json
    1.12 kB
    metask-jev-4b: Qwen3.5-4B LoRA for typed decisions (13-subset 79.6%, JevBench 80.1% @4096) 10 days ago