Instructions to use cngchis/phi4-mini-intent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cngchis/phi4-mini-intent with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="cngchis/phi4-mini-intent")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cngchis/phi4-mini-intent") model = AutoModelForCausalLM.from_pretrained("cngchis/phi4-mini-intent") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -87,17 +87,20 @@ The model outputs a class index, which can be mapped to intent labels:
|
|
| 87 |
|
| 88 |
### Model Details
|
| 89 |
|
| 90 |
-
Architecture: Transformer-based classification model
|
| 91 |
-
Task: Intent classification
|
| 92 |
-
Format: PyTorch (safetensors)
|
| 93 |
-
Library: Hugging Face Transformers
|
| 94 |
-
Input: Natural language text
|
| 95 |
-
Output: Single intent class
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
|
|
|
|
|
|
|
|
|
| 101 |
|
| 102 |
---
|
| 103 |
|
|
|
|
| 87 |
|
| 88 |
### Model Details
|
| 89 |
|
| 90 |
+
- Architecture: Transformer-based classification model
|
| 91 |
+
- Task: Intent classification
|
| 92 |
+
- Format: PyTorch (safetensors)
|
| 93 |
+
- Library: Hugging Face Transformers
|
| 94 |
+
- Input: Natural language text
|
| 95 |
+
- Output: Single intent class
|
| 96 |
+
|
| 97 |
+
---
|
| 98 |
+
|
| 99 |
+
### Notes
|
| 100 |
+
- Best performance when input format matches training data
|
| 101 |
+
- Requires label mapping for interpretation
|
| 102 |
+
- Works with GPU
|
| 103 |
+
- Supports batch inference via Transformers
|
| 104 |
|
| 105 |
---
|
| 106 |
|