whatmodel.sh / Tk-Instruct 11B (def-pos-neg-expl)
Tk-Instruct 11B (def-pos-neg-expl)
↗ share
+ contribute
Tk-Instruct 11B (def-pos-neg-expl) is an open-weights language model from AllenAI / UW, released May 2022. Its published size is 11B parameters. Licence: apache-2.0.
Catalogue identity notes
Tk-Instruct 11B trained with definition, positive and negative examples plus explanations; repo allenai/tk-instruct-11b-def-pos-neg-expl created 2022-05-05.
Model information sources
Score within the LMArena (text) comparison set only.
$ how it compares
The LLMs ranked either side of Tk-Instruct 11B (def-pos-neg-expl), out of 1182 with a score, then more from AllenAI / UW.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 888 |  North Micro Vision Instruct (2.4B) | 42±2 | local | ||
| 889 |  Deita 7B v1.0 | 42±2 | local | ||
| 890 | Tk-Instruct 11B (def-pos-neg-expl) | 42±10 | comparison only | ||
| 891 |  Vicuna 13B v1.1 | 42±2 | comparison only | ||
| 892 |  OpenHermes 2.5 Mistral 7B | 42±1 | local | ||
| more from AllenAI / UW | |||||
| 866 | Tk-Instruct 11B (def-pos) | 43±6 | comparison only | ||
| 1109 | Tk-Instruct 11B (def) | 26±4 | comparison only | ||
$ what it's good at
other tests1 not in a task · 60% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMentry accuracy (zero-shot) | 53.0% ✎ | ▂▆·▄▄█▃·▂··▂ beats 12/14 | 60% |
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: huggingface.co/allenai ↗
$ how the score was worked out · LMentry: A Language Model Ben… 60%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMentry: A Language Model Benchmark of Elementary Language Tasks — authors' own runs | 1 | 60% |
| prior · pull toward the middle | 40% | |
| weighted average | = 41.9 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json