Transformers
Safetensors
decision-model
commerce
system-one
structured-output
calibration
custom-code
qwen3.8
offline
Instructions to use infercrane/Commerce-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use infercrane/Commerce-1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("infercrane/Commerce-1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download source/autojev/types.py from infercrane/Commerce-1: direct link, hf CLI and curl.
- Browser
- Download file 1.8 kB
-
https://huggingface.co/infercrane/Commerce-1/resolve/main/source/autojev/types.py
- Command line
-
hf download hf://infercrane/Commerce-1/source/autojev/types.py
-
curl -L -o types.py https://huggingface.co/infercrane/Commerce-1/resolve/main/source/autojev/types.py
1.8 kB
| from pathlib import Path | |
| from typing import Literal, NotRequired, TypedDict | |
| from PIL import Image | |
| type JSONValue = str | int | float | bool | None | list[JSONValue] | dict[str, JSONValue] | |
| type Content = str | dict[str, JSONValue] | list[JSONValue] | |
| type ImageInput = str | Path | Image.Image | |
| type Label = str | int | bool | |
| type Target = Label | float | list[float] | |
| class QuestionBase(TypedDict): | |
| instructions: NotRequired[Content | None] | |
| class ChoiceQuestion(QuestionBase): | |
| type: Literal["choice"] | |
| criteria: dict[str, Content | None] | |
| class NoulQuestion(QuestionBase): | |
| type: Literal["noul"] | |
| criteria: NotRequired[dict[Literal["true", "false"], Content | None] | None] | |
| class ScoreQuestion(QuestionBase): | |
| type: Literal["score"] | |
| criteria: list[Content] | |
| type Question = ChoiceQuestion | NoulQuestion | ScoreQuestion | |
| class DecisionInput(TypedDict): | |
| state: Content | |
| question: Question | |
| images: NotRequired[list[ImageInput]] | |
| class Example(DecisionInput): | |
| id: str | |
| suite: str | |
| family: str | |
| label: Label | |
| target: Target | |
| source: dict[str, JSONValue] | |
| class ChoiceAnswer(TypedDict): | |
| type: Literal["choice"] | |
| choice: str | |
| probabilities: dict[str, float] | |
| confidence: float | |
| class NoulAnswer(TypedDict): | |
| type: Literal["noul"] | |
| noul: float | |
| class ScoreAnswer(TypedDict): | |
| type: Literal["score"] | |
| score: float | |
| legend: dict[str, Content | None] | |
| probabilities: dict[str, float] | |
| confidence: float | |
| type Answer = ChoiceAnswer | NoulAnswer | ScoreAnswer | |
| class Usage(TypedDict, total=False): | |
| input_tokens: int | |
| output_tokens: int | |
| class DecisionResponse(TypedDict): | |
| answers: dict[str, Answer] | |
| usage: Usage | |
| model: NotRequired[str] | |
| id: NotRequired[str] | |
| provider: NotRequired[str] | |