lostargon commited on
Commit
937374e
·
verified ·
1 Parent(s): c9b1d27

model card: remove video

Browse files
Files changed (1) hide show
  1. README.md +0 -4
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
- [![Watch: Jev | This AI Can't Talk. That's Why It's So Fast.](assets/video.jpg)](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.