Text Classification
Transformers
PyTorch
English
modernbert
encoder
decision-model
tool-routing
agentic
Instructions to use open-zzrl/kyo-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use open-zzrl/kyo-instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="open-zzrl/kyo-instruct")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("open-zzrl/kyo-instruct", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -45,7 +45,7 @@ Evaluated across 2,000 holdout agent policy scenarios and multi-class NLP benchm
|
|
| 45 |
|
| 46 |

|
| 47 |
|
| 48 |
-
| Benchmark / Capability | Kyo-
|
| 49 |
| :--- | :--- | :--- | :--- |
|
| 50 |
| **DAIR Emotion** (6 classes, 2000 holdout) | **71.55%** | 59.50% | 48.00% |
|
| 51 |
| **Banking77** (Full 77 classes, 3076 test) | **47.56%** *(77 options)* | 42.50% *(72 options)* | **87.00%** *(72 options)* |
|
|
|
|
| 45 |
|
| 46 |

|
| 47 |
|
| 48 |
+
| Benchmark / Capability | Kyo-Instruct (140M) | Laya Base (421M) | TypeSafe Jev (~490M) |
|
| 49 |
| :--- | :--- | :--- | :--- |
|
| 50 |
| **DAIR Emotion** (6 classes, 2000 holdout) | **71.55%** | 59.50% | 48.00% |
|
| 51 |
| **Banking77** (Full 77 classes, 3076 test) | **47.56%** *(77 options)* | 42.50% *(72 options)* | **87.00%** *(72 options)* |
|