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

JohnP1
/
d1a-e4b

Text Classification
PEFT
Safetensors
English
Japanese
d1a
decision-model
calibration
lora
gemma4
typesafe
system-one
pull-requests
Model card Files Files and versions
xet
Community

Instructions to use JohnP1/d1a-e4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use JohnP1/d1a-e4b with PEFT:

    from peft import PeftModel
    from transformers import AutoModel
    
    base_model = AutoModel.from_pretrained("google/gemma-4-E4B")
    model = PeftModel.from_pretrained(base_model, "JohnP1/d1a-e4b")
  • Notebooks
  • Google Colab
  • Kaggle
d1a-e4b
183 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 18 commits
JohnP1's picture
JohnP1
Model card: wording
93ee47b verified 21 days ago
  • .gitattributes
    1.62 kB
    Card: add the D1A avatar about 1 month ago
  • README.md
    18.7 kB
    Model card: wording 21 days ago
  • adapter_config.json
    1.17 kB
    D1A-E4B v0.6 about 1 month ago
  • adapter_model.safetensors
    140 MB
    xet
    D1A-E4B v0.6 about 1 month ago
  • d1a-avatar.png
    423 kB
    xet
    Card: the chosen D1A avatar about 1 month ago
  • d1a_config.json
    6.48 kB
    v0.6.1: routing temperature (use_case_temperatures.routing), same weights as v0.6 (jonpol01/d1a#264) about 1 month ago
  • head.pt
    5.25 MB
    xet
    D1A-E4B v0.6 about 1 month ago
  • head.safetensors
    5.25 MB
    xet
    D1A-E4B v0.6 about 1 month ago
  • provenance.json
    2.56 kB
    Model card: wording 21 days ago
  • result.json
    9.85 kB
    D1A-E4B v0.6 about 1 month ago
  • tokenizer.json
    32.2 MB
    xet
    D1A-E4B v0.1: two epochs at lr 5e-5 (dev acc 0.853 trained / 0.680 new sources) about 2 months ago
  • tokenizer_config.json
    1.53 kB
    D1A-E4B v0.1: two epochs at lr 5e-5 (dev acc 0.853 trained / 0.680 new sources) about 2 months ago
  • training_config.json
    1.55 kB
    D1A-E4B v0.6 about 1 month ago
  • training_metrics.json
    11.8 kB
    D1A-E4B v0.6 about 1 month ago