How to use from
llama.cpp
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf iamlyth/gemma4-e4b-ha:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf iamlyth/gemma4-e4b-ha:Q4_K_S
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf iamlyth/gemma4-e4b-ha:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf iamlyth/gemma4-e4b-ha:Q4_K_S
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf iamlyth/gemma4-e4b-ha:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama cli -hf iamlyth/gemma4-e4b-ha:Q4_K_S
Use Docker
docker model run hf.co/iamlyth/gemma4-e4b-ha:Q4_K_S
Quick Links

Model Card for gemma4-e4b-ha

This model is a fine-tuned version of unsloth/gemma-4-E4B-it. It has been trained using TRL and trained on the acon96 Home Assistant V2 Training Set. Optimized to make home assistant tool calls targeted for the nVidia Jetson Nano devices.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

  • PEFT 0.19.1
  • TRL: 0.24.0
  • Transformers: 5.5.0
  • Pytorch: 2.10.0
  • Datasets: 4.3.0
  • Tokenizers: 0.22.2

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}
Downloads last month
21
GGUF
Model size
8B params
Architecture
gemma4
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for iamlyth/gemma4-e4b-ha

Adapter
(86)
this model