Instructions to use Archit-01/decisions-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Archit-01/decisions-tiny with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Archit-01/decisions-tiny", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Archit-01/decisions-tiny: direct link, hf CLI and curl.
- Browser
- Download file 1.67 kB
-
https://huggingface.co/Archit-01/decisions-tiny/resolve/main/README.md
- Command line
-
hf download hf://Archit-01/decisions-tiny/README.md
-
curl -L -o README.md https://huggingface.co/Archit-01/decisions-tiny/resolve/main/README.md
1.67 kB
| language: | |
| - en | |
| license: other | |
| library_name: transformers | |
| tags: | |
| - decision-model | |
| - classification | |
| - qwen | |
| # decisions-tiny | |
| A small fine-tuned decision model inspired by the System 1 / typed-decision approach used by models such as JEV. It performs structured decisions from natural-language inputs, including categorical classification and yes/no-style decisions. | |
| ## Model Details | |
| - **Base model:** `Qwen3.5-0.8B` | |
| - **Fine-tuning:** LoRA with 4-bit base-model loading | |
| ## Dataset | |
| - **Dataset:** [LocalLLaMA/typed-decisions](https://huggingface.co/datasets/LocalLLaMA/typed-decisions) | |
| ## Evaluation | |
| | Metric | Score | | |
| |---|---:| | |
| | Accuracy | 0.7035 | | |
| | Record accuracy | 0.2375 | | |
| | Loss | 1.0787 | | |
| ## Inference | |
| ```python | |
| from unsloth import FastDecisionModel | |
| model, tokenizer = FastDecisionModel.from_pretrained( | |
| model_name="Archit-01/decisions-tiny", | |
| max_seq_length=2048, | |
| load_in_4bit=True, | |
| ) | |
| FastDecisionModel.for_inference(model) | |
| text = ( | |
| "Hi, I was charged twice for invoice #4411. " | |
| "Please refund the duplicate today." | |
| ) | |
| schema = { | |
| "team": { | |
| "type": "choice", | |
| "instructions": "Which team should handle this?", | |
| "criteria": { | |
| "billing": "invoices, payments, refunds", | |
| "technical": "bugs, outages, errors", | |
| "sales": "pricing, new plans", | |
| }, | |
| }, | |
| "refund": { | |
| "type": "noul", | |
| "instructions": "Does the customer ask for a refund?", | |
| }, | |
| } | |
| answers = FastDecisionModel.predict( | |
| model, tokenizer, text, schema | |
| ) | |
| print(answers["team"]["answer"]) | |
| print(answers["team"]["probabilities"]) | |
| print(answers["refund"]["answer"]) | |