Instructions to use Machlovi/GGuard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Machlovi/GGuard with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Machlovi/GGuard", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use Machlovi/GGuard 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 Machlovi/GGuard 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 Machlovi/GGuard to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Machlovi/GGuard to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Machlovi/GGuard", max_seq_length=2048, )
Update README.md
Browse files
README.md
CHANGED
|
@@ -33,7 +33,7 @@ from unsloth import FastModel
|
|
| 33 |
|
| 34 |
|
| 35 |
# Load the base model
|
| 36 |
-
base_model_name = "unsloth/gemma-3-
|
| 37 |
model, tokenizer = FastModel.from_pretrained(
|
| 38 |
model_name=base_model_name,
|
| 39 |
max_seq_length=2048, # Must match fine-tuning
|
|
@@ -41,7 +41,7 @@ model, tokenizer = FastModel.from_pretrained(
|
|
| 41 |
)
|
| 42 |
|
| 43 |
# Load the fine-tuned LoRA adapter
|
| 44 |
-
lora_model_name = "Machlovi/
|
| 45 |
model = PeftModel.from_pretrained(model, lora_model_name)
|
| 46 |
|
| 47 |
model.eval()
|
|
|
|
| 33 |
|
| 34 |
|
| 35 |
# Load the base model
|
| 36 |
+
base_model_name = "unsloth/gemma-3-12b-it-unsloth-bnb-4bit",",
|
| 37 |
model, tokenizer = FastModel.from_pretrained(
|
| 38 |
model_name=base_model_name,
|
| 39 |
max_seq_length=2048, # Must match fine-tuning
|
|
|
|
| 41 |
)
|
| 42 |
|
| 43 |
# Load the fine-tuned LoRA adapter
|
| 44 |
+
lora_model_name = "Machlovi/GGuard"
|
| 45 |
model = PeftModel.from_pretrained(model, lora_model_name)
|
| 46 |
|
| 47 |
model.eval()
|