Zero-Shot Classification
Transformers
Safetensors
English
qwen3
text-generation
assay
decision-model
calibrated
conformal-prediction
text-classification
structured-output
text-generation-inference
Instructions to use Berk/assay-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Berk/assay-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="Berk/assay-4b")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Berk/assay-4b") model = AutoModelForCausalLM.from_pretrained("Berk/assay-4b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -137,10 +137,10 @@ options, `noul` booleans) load unchanged.
|
|
| 137 |
## Usage
|
| 138 |
|
| 139 |
```python
|
| 140 |
-
from assay
|
| 141 |
from assay.schema import Question
|
| 142 |
|
| 143 |
-
model =
|
| 144 |
answers = model.answer(
|
| 145 |
state="My card was charged twice for order A-104.",
|
| 146 |
questions={
|
|
|
|
| 137 |
## Usage
|
| 138 |
|
| 139 |
```python
|
| 140 |
+
from assay import load_model
|
| 141 |
from assay.schema import Question
|
| 142 |
|
| 143 |
+
model = load_model("Berk/assay-4b")
|
| 144 |
answers = model.answer(
|
| 145 |
state="My card was charged twice for order A-104.",
|
| 146 |
questions={
|