Instructions to use FritzStack/HiTOP-QWEN4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FritzStack/HiTOP-QWEN4B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("FritzStack/HiTOP-QWEN4B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use FritzStack/HiTOP-QWEN4B 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 FritzStack/HiTOP-QWEN4B 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 FritzStack/HiTOP-QWEN4B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for FritzStack/HiTOP-QWEN4B to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="FritzStack/HiTOP-QWEN4B", max_seq_length=2048, )
!pip install git+https://github.com/Fede-stack/TONYpy.git
from TONY.HiTOP import HiTOP_Predictor
text = 'Some days I keep living, even though I feel completely alone in the world'
hitop = HiTOP_Predictor(model_name='FritzStack/HiTOP-QWEN4B')
hitop.predict_HiTOP(text)
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("FritzStack/HiTOP-QWEN4B", dtype="auto")