Instructions to use wizardoftrap/functiongemma-270m-it-mobile-actions with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wizardoftrap/functiongemma-270m-it-mobile-actions with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("wizardoftrap/functiongemma-270m-it-mobile-actions", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use wizardoftrap/functiongemma-270m-it-mobile-actions 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 wizardoftrap/functiongemma-270m-it-mobile-actions 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 wizardoftrap/functiongemma-270m-it-mobile-actions to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for wizardoftrap/functiongemma-270m-it-mobile-actions to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="wizardoftrap/functiongemma-270m-it-mobile-actions", max_seq_length=2048, )
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,11 +14,16 @@ datasets:
|
|
| 14 |
|
| 15 |
# Uploaded finetuned model
|
| 16 |
|
| 17 |
-
- **Developed by:** wizardoftrap
|
| 18 |
- **License:** apache-2.0
|
| 19 |
-
- **Finetuned from model :** unsloth/functiongemma-270m-it-unsloth-bnb-4bit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
-
This gemma3_text model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 22 |
-
Also this model was converted into a Litertlm format and used in Google's Edge Gallery App on android.
|
| 23 |
|
| 24 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 14 |
|
| 15 |
# Uploaded finetuned model
|
| 16 |
|
| 17 |
+
- **Developed by:** Shiv Prakash(wizardoftrap)
|
| 18 |
- **License:** apache-2.0
|
| 19 |
+
- **Finetuned from model :** [unsloth/functiongemma-270m-it-unsloth-bnb-4bit](https://huggingface.co/unsloth/functiongemma-270m-it-unsloth-bnb-4bit)
|
| 20 |
+
- **Dataset Used :** [google/mobile-actions](https://huggingface.co/datasets/google/mobile-actions)
|
| 21 |
+
|
| 22 |
+
# Overview
|
| 23 |
+
- This gemma3_text model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 24 |
+
- FunctionGemma is a lightweight, open model from Google, built as a foundation for creating your own specialized function calling models.
|
| 25 |
+
- Also this model was converted into a Litertlm format and used in Google's Edge Gallery App on android.
|
| 26 |
+
- This model was trained on Google Colab with T4 GPU
|
| 27 |
|
|
|
|
|
|
|
| 28 |
|
| 29 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|