Pass IndexThe State of AISign in

stablelm-tuned-alpha-7b

StableLM-Tuned-Alpha is a suite of 3B and 7B parameter decoder-only language models built on top of the StableLM-Base-Alpha models and further fine-tuned on various chat and instruction-following datasets.

text → text · made by Stability AI

Sold by

Nobody in the catalogue publishes a price for this yet.

Measured 6 standings

PlaceBoardMetricScore
63rdof 70Open book qa — Epoch AIAccuracy32.4
112thof 113Hella swag — Epoch AIOverall accuracy0.407
113thof 113Piqa — Epoch AIScore65.8
131stof 134Arc ai2 — Epoch AIChallenge score0.27
131stof 136Bool q — Epoch AIScore59
137thof 137Wino grande — Epoch AIAccuracy51.5

About

stablelm-tuned-alpha-7b — a text model from Stability AI, placed 63rd of 70 on Open book qa — Epoch AI.

It takes text and returns text. It was published in April 2023. The catalogue files it under chat. Its weights are published, but the licence forbids selling what it produces. It has been measured on 6 boards, and stands best at 63rd of 70 on Open book qa — Epoch AI.

Every current figure

Maker
Stability AI
Register
model
Takes
text
Returns
text
Published
April 2023
Parameters
7 billion · read from its own name
Licence
cc-by-nc-sa-4.0
Boards
6
Best place
63rd of 70 — Open book qa — Epoch AI

Known as 1 name

stabilityai/stablelm-tuned-alpha-7b