Text Classification
Transformers
Safetensors
English
tiny_jev
feature-extraction
jev
system-one
open-jev
decision-model
calibrated
routing
classification
guardrails
non-autoregressive
custom_code
Instructions to use lostargon/Tiny-Jev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lostargon/Tiny-Jev with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="lostargon/Tiny-Jev", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("lostargon/Tiny-Jev", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
model card: remove video
Browse files
README.md
CHANGED
|
@@ -23,10 +23,6 @@ tags:
|
|
| 23 |
|
| 24 |
> **Not affiliated with TypeSafe AI.** Tiny-Jev is an independent, open-weights model *inspired by* the System One idea and the Jev decision API published by TypeSafe AI. It is not built, endorsed, or supported by them, shares no code or weights with their models, and "Jev" in the name refers only to the interface style it reproduces (Choice / Score / Noul with calibrated probabilities).
|
| 25 |
|
| 26 |
-
[](https://www.youtube.com/watch?v=MXLHolGxhAI)
|
| 27 |
-
|
| 28 |
-
*▶ Video (third-party, Smoke Test AI): what System One decision models are and why they are so fast.*
|
| 29 |
-
|
| 30 |
A larger, more accurate sibling is available as [Tiny-Jev-1.7B](https://huggingface.co/lostargon/Tiny-Jev-1.7B).
|
| 31 |
|
| 32 |
Tiny-Jev does not generate text. It reads a *state* (a message, a ticket, a JSON record, a transcript, a log, a diff), a *question* written the way a developer would write it in code, and a fixed set of *options* — and returns a probability distribution over those options in a single forward pass. Every answer comes with a calibrated confidence, so your code can act on the confident ones and route the rest.
|
|
|
|
| 23 |
|
| 24 |
> **Not affiliated with TypeSafe AI.** Tiny-Jev is an independent, open-weights model *inspired by* the System One idea and the Jev decision API published by TypeSafe AI. It is not built, endorsed, or supported by them, shares no code or weights with their models, and "Jev" in the name refers only to the interface style it reproduces (Choice / Score / Noul with calibrated probabilities).
|
| 25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
A larger, more accurate sibling is available as [Tiny-Jev-1.7B](https://huggingface.co/lostargon/Tiny-Jev-1.7B).
|
| 27 |
|
| 28 |
Tiny-Jev does not generate text. It reads a *state* (a message, a ticket, a JSON record, a transcript, a log, a diff), a *question* written the way a developer would write it in code, and a fixed set of *options* — and returns a probability distribution over those options in a single forward pass. Every answer comes with a calibrated confidence, so your code can act on the confident ones and route the rest.
|