Downloads · 30 days
4
1% of all-time downloads
emrahemrez/mira-e4b-it
mira-e4b-it is a machine learning model from emrahemrez. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as gemma.
MIRA is a fine-tuned version of Gemma 4 E4B-it, trained as a personal AI assistant with tool-calling capabilities.
Downloads · 30 days
4
1% of all-time downloads
All-time downloads
360
Public
Repo size
—
Likes
0
Public
Click a slice to open those files.
.pt163 MB · 83%
From the Hugging Face model README
MIRA is a fine-tuned version of Gemma 4 E4B-it, trained as a personal AI assistant with tool-calling capabilities.
| Property | Value |
|---|---|
| Base Model | google/gemma-4-e4b-it |
| Fine-tuning | QLoRA (4-bit NF4 + LoRA rank=32) |
| Dataset | 322 custom examples (messages[] format) |
| Training | 150 steps, lr=3e-5, batch=16 |
| Languages | Turkish, English, Russian |
!git clone https://github.com/emrahemrez/mira_model /content/mira
import os; os.chdir('/content/mira')
!pip install gradio transformers bitsandbytes accelerate sentencepiece huggingface_hub -q
exec(open('app.py').read())
# Gradio link → share with anyone for 72h
<tool_call> <tool_name>write_file</tool_name> {"path": "test.py", "content": "print('Hello World')"} </tool_call>