Instructions to use prayasabhinav/aadha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prayasabhinav/aadha with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="prayasabhinav/aadha")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("prayasabhinav/aadha") model = AutoModelForSequenceClassification.from_pretrained("prayasabhinav/aadha", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Say NSMnum and how to say it (release 0.8.1)
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ A small reader that gives each sentence one mark:
|
|
| 21 |
|
| 22 |
aadha only marks. It writes nothing. Code, not the model, decides what the marks mean for a piece of writing. In *teetar aadhi bater*, the tool built on it, the page shows how the marks are spread across the piece. Its name is from the Hindi idiom *aadha teetar aadha bater*, half partridge, half quail: a thing that is neither one thing nor the other.
|
| 23 |
|
| 24 |
-
It is an NSMnum (Narrow Small Model; written NSM until 15 November 2026, when the short form was changed to avoid a collision with the Natural Semantic Metalanguage in linguistics). What is narrow is its answer, which is always one of four marks; the model's own size does not decide it. It is an exemplar in [ungli](https://ungli.syntax.prayasabhinav.net), the builder for
|
| 25 |
|
| 26 |
## Use it
|
| 27 |
|
|
|
|
| 21 |
|
| 22 |
aadha only marks. It writes nothing. Code, not the model, decides what the marks mean for a piece of writing. In *teetar aadhi bater*, the tool built on it, the page shows how the marks are spread across the piece. Its name is from the Hindi idiom *aadha teetar aadha bater*, half partridge, half quail: a thing that is neither one thing nor the other.
|
| 23 |
|
| 24 |
+
It is an NSMnum (Narrow Small Model, said en-ess-em-num, एन-एस-एम-नम; written NSM until 15 November 2026, when the short form was changed to avoid a collision with the Natural Semantic Metalanguage in linguistics). What is narrow is its answer, which is always one of four marks; the model's own size does not decide it. It is an exemplar in [ungli](https://ungli.syntax.prayasabhinav.net), the builder for NSMnum, and part of [SYNTAX](https://syntax.prayasabhinav.net).
|
| 25 |
|
| 26 |
## Use it
|
| 27 |
|