Feature Extraction
Transformers
Safetensors
valen_qwen
valen
decision-making
shared-state
qwen3.5
custom-code
custom_code
Instructions to use Valen-Team/Valen-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Valen-Team/Valen-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Valen-Team/Valen-4B", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Valen-Team/Valen-4B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download data_types.py from Valen-Team/Valen-4B: direct link, hf CLI and curl.
- Browser
- Download file 258 Bytes
-
https://huggingface.co/Valen-Team/Valen-4B/resolve/main/data_types.py
- Command line
-
hf download hf://Valen-Team/Valen-4B/data_types.py
-
curl -L -o data_types.py https://huggingface.co/Valen-Team/Valen-4B/resolve/main/data_types.py
258 Bytes
| """Model-independent decision metadata; encoded tensors stay with each compiler.""" | |
| from dataclasses import dataclass | |
| class QuestionSpec: | |
| qid: str | |
| kind: str | |
| keys: list | |
| descriptions: list | |
| target: list | None | |
| is_text: bool | |