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

ssdataanalysis
/
gemma-4-E2B-hebrew-first

Transformers
Safetensors
Generated from Trainer
hf_jobs
trl
sft
Model card Files Files and versions
xet
Community

Instructions to use ssdataanalysis/gemma-4-E2B-hebrew-first with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use ssdataanalysis/gemma-4-E2B-hebrew-first with Transformers:

    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("ssdataanalysis/gemma-4-E2B-hebrew-first", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
gemma-4-E2B-hebrew-first
336 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 13 commits
ssdataanalysis's picture
ssdataanalysis
Model save
16e4b07 verified 4 months ago
  • .gitattributes
    1.57 kB
    Training in progress, step 500 4 months ago
  • README.md
    1.45 kB
    Model save 4 months ago
  • adapter_config.json
    8.76 kB
    Training in progress, step 500 4 months ago
  • adapter_model.safetensors
    304 MB
    xet
    Training in progress, step 500 4 months ago
  • chat_template.jinja
    16.8 kB
    Training in progress, step 500 4 months ago
  • run_e2b.sh
    306 Bytes
    Add entrypoint script with fixed args 4 months ago
  • tokenizer.json
    32.2 MB
    xet
    Training in progress, step 500 4 months ago
  • tokenizer_config.json
    2.74 kB
    Training in progress, step 500 4 months ago
  • train.py
    6.04 kB
    Fix: add assistant_only_loss=False to prevent all labels being masked to -100 4 months ago
  • training_args.bin
    5.78 kB
    xet
    Training in progress, step 500 4 months ago