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

roshangrewal
/
gemma4-e4b-toolcall-v02

Text Generation
Safetensors
English
gemma4
function-calling
tool-use
agentic
fine-tuned
unsloth
conversational
Model card Files Files and versions
xet
Community
1

Instructions to use roshangrewal/gemma4-e4b-toolcall-v02 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Local Apps Settings
  • Unsloth Studio

    How to use roshangrewal/gemma4-e4b-toolcall-v02 with Unsloth Studio:

    Install Unsloth Studio (macOS, Linux, WSL)
    curl -fsSL https://unsloth.ai/install.sh | sh
    # Run unsloth studio
    unsloth studio -H 0.0.0.0 -p 8888
    # Then open http://localhost:8888 in your browser
    # Search for roshangrewal/gemma4-e4b-toolcall-v02 to start chatting
    Install Unsloth Studio (Windows)
    irm https://unsloth.ai/install.ps1 | iex
    # Run unsloth studio
    unsloth studio -H 0.0.0.0 -p 8888
    # Then open http://localhost:8888 in your browser
    # Search for roshangrewal/gemma4-e4b-toolcall-v02 to start chatting
    Using HuggingFace Spaces for Unsloth
    # No setup required
    # Open https://huggingface.co/spaces/unsloth/studio in your browser
    # Search for roshangrewal/gemma4-e4b-toolcall-v02 to start chatting
    Load model with FastModel
    pip install unsloth
    from unsloth import FastModel
    model, tokenizer = FastModel.from_pretrained(
        model_name="roshangrewal/gemma4-e4b-toolcall-v02",
        max_seq_length=2048,
    )
gemma4-e4b-toolcall-v02
15.9 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 23 commits
roshangrewal's picture
roshangrewal
Upload README.md with huggingface_hub
dceef61 verified 15 days ago
  • assets
    Add chart: bfcl_breakdown.png 21 days ago
  • eval
    Add 1000-query evaluation dataset 22 days ago
  • .gitattributes
    1.57 kB
    Gemma 4 E4B tool-calling v02 (SFT merged, 94.4% accuracy on 1000 queries) 22 days ago
  • README.md
    6.85 kB
    Upload README.md with huggingface_hub 15 days ago
  • chat_template.jinja
    16.8 kB
    Gemma 4 E4B tool-calling v02 (SFT merged, 94.4% accuracy on 1000 queries) 22 days ago
  • config.json
    5.28 kB
    Fix: re-merge with all weights (k_norm) for vLLM compatibility 22 days ago
  • example_inference.py
    2.16 kB
    Add example inference script 22 days ago
  • generation_config.json
    204 Bytes
    Fix: re-merge with all weights (k_norm) for vLLM compatibility 22 days ago
  • model.safetensors
    15.9 GB
    xet
    Gemma 4 E4B tool-calling v02 (SFT merged, 94.4% accuracy on 1000 queries) 22 days ago
  • processor_config.json
    1.69 kB
    Gemma 4 E4B tool-calling v02 (SFT merged, 94.4% accuracy on 1000 queries) 22 days ago
  • run_evaluation.py
    2.18 kB
    Add evaluation script 22 days ago
  • tokenizer.json
    32.2 MB
    xet
    Gemma 4 E4B tool-calling v02 (SFT merged, 94.4% accuracy on 1000 queries) 22 days ago
  • tokenizer_config.json
    6.89 kB
    Gemma 4 E4B tool-calling v02 (SFT merged, 94.4% accuracy on 1000 queries) 22 days ago