Feature Extraction
Transformers
Safetensors
decision2
decision-model
classification
system-one
custom_code
Instructions to use vllm-sr/Decision-2.0-Sol-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vllm-sr/Decision-2.0-Sol-2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="vllm-sr/Decision-2.0-Sol-2B", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("vllm-sr/Decision-2.0-Sol-2B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download configuration_decision2.py from vllm-sr/Decision-2.0-Sol-2B: direct link, hf CLI and curl.
- Browser
- Download file 692 Bytes
-
https://huggingface.co/vllm-sr/Decision-2.0-Sol-2B/resolve/73bb148b08891047c5ae96656548a9fbc387f2c8/configuration_decision2.py
- Command line
-
hf download hf://vllm-sr/Decision-2.0-Sol-2B@73bb148b08891047c5ae96656548a9fbc387f2c8/configuration_decision2.py
-
curl -L -o configuration_decision2.py https://huggingface.co/vllm-sr/Decision-2.0-Sol-2B/resolve/73bb148b08891047c5ae96656548a9fbc387f2c8/configuration_decision2.py
692 Bytes
| """Decision 2.0 configuration for 🤗 Transformers (``trust_remote_code=True``). | |
| The repository's root ``config.json`` is the package pointer the native runtime reads first (model name, | |
| model files by role, input limit) plus ``model_type``, ``auto_map`` and ``custom_pipelines``. This class | |
| only exposes those fields: the model is described by ``decision_config.json`` and every file is checked | |
| against ``MODEL_MANIFEST.json`` when ``Decision2Model`` loads. | |
| """ | |
| try: | |
| from transformers import PreTrainedConfig | |
| except ImportError: # Transformers 4 | |
| from transformers import PretrainedConfig as PreTrainedConfig | |
| class Decision2Config(PreTrainedConfig): | |
| model_type = "decision2" | |