| --- |
| license: apache-2.0 |
| base_model: vllm-sr/d3-nano |
| pipeline_tag: zero-shot-classification |
| library_name: transformers |
| tags: [decision-model, system-one] |
| --- |
| |
| # d3-nano for 🤗 Transformers |
|
|
| The 255-way answer-code readout of [vllm-sr/d3-nano](https://huggingface.co/vllm-sr/d3-nano) as a JEV decision head, for the `decision` |
| pipeline. This repo holds the readout, the tokenizer and the prompt; the backbone loads from the original repo, |
| with bidirectional full attention as it was trained. |
|
|
| ## Questions |
|
|
| Each question is answered with a probability for every option: `noul` (yes/no), `choice` and `score`. |
|
|
| ```python |
| from transformers import pipeline |
| |
| decide = pipeline("decision", model="ArthurZ/d3-nano") |
| answers = decide( |
| { |
| "state": {"customer": "Lena", "message": "I was charged twice for my order and I want my money back today."}, |
| "questions": { |
| "refund": {"type": "noul", "instructions": "Does the customer ask for a refund?"}, |
| "tone": {"type": "choice", "instructions": "What is the tone?", "criteria": {"calm": "Polite", "angry": None}}, |
| "urgency": {"type": "score", "instructions": "How urgent is it?", "criteria": ["Can wait", "This week", "Today", "Now"]}, |
| }, |
| } |
| ) |
| answers["refund"]["noul"] # probability of true |
| answers["tone"]["choice"], answers["tone"]["probabilities"] |
| answers["urgency"]["score"] # expected level, 0 to 3 |
| ``` |
|
|
| ## Same questions, new states |
|
|
| A bare state is asked the questions of the last request, or the ones given up front: |
|
|
| ```python |
| decide = pipeline( |
| "decision", |
| model="ArthurZ/d3-nano", |
| questions={"spam": {"type": "noul", "instructions": "Is this spam?"}}, |
| ) |
| decide("WIN A FREE IPHONE!!! click here to claim your prize") |
| decide("Hi! The parcel arrived, thanks a lot.") |
| ``` |
|
|
| ## Images |
|
|
| Images are `assets`, as in the System One API: a placeholder in the state is replaced with its image. An asset is a |
| PIL image, a path, a URL or `{"type": "image", "format": "png", "data_base64": ...}`. |
|
|
| ```python |
| decide( |
| { |
| "state": "The customer sent photo-1 and asks if the product is damaged.", |
| "assets": {"photo-1": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/coco_sample.png"}, |
| "questions": {"damaged": {"type": "noul", "instructions": "Is the product in the photo damaged?"}}, |
| } |
| ) |
| ``` |
|
|
| Converted with |
| [`convert_decider_to_hf.py`](https://github.com/huggingface/transformers/blob/main/src/transformers/models/jev/convert_decider_to_hf.py). |
| Its prompts are token-for-token those of the original code (`decision_test.json`), except that control tokens written |
| in a request are escaped instead of read as such. |
|
|
