Text Classification
Transformers
Safetensors
English
llama
safety
content-moderation
tiny-language-model
from-scratch
text-embeddings-inference
Instructions to use KucLab/Censer.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Censer.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Censer.1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Censer.1") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Censer.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload Censer.1
Browse files
README.md
CHANGED
|
@@ -85,6 +85,22 @@ Per-source F1 reflects label noise in the scraped sources:
|
|
| 85 |
| civil_comments | 0.77 |
|
| 86 |
| toxic_chat | 0.48 |
|
| 87 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
## Usage
|
| 89 |
|
| 90 |
```python
|
|
|
|
| 85 |
| civil_comments | 0.77 |
|
| 86 |
| toxic_chat | 0.48 |
|
| 87 |
|
| 88 |
+
## Benchmark
|
| 89 |
+
|
| 90 |
+
Measured on an AMD Radeon RX 9060 XT (ROCm 7.1, torch 2.13.0):
|
| 91 |
+
|
| 92 |
+
| Metric | Value |
|
| 93 |
+
| --- | --- |
|
| 94 |
+
| Parameters | 1,115,264 |
|
| 95 |
+
| Checkpoint size | 4.26 MB |
|
| 96 |
+
| Single text latency | 1.67 ms |
|
| 97 |
+
| Single text throughput | 599 texts/s |
|
| 98 |
+
| Batched latency (batch of 8) | 1.94 ms |
|
| 99 |
+
| Batched throughput | 4,119 texts/s |
|
| 100 |
+
| Peak VRAM (inference) | 85.7 MB |
|
| 101 |
+
|
| 102 |
+
Training the whole model from scratch takes about 3.5 minutes on the same GPU.
|
| 103 |
+
|
| 104 |
## Usage
|
| 105 |
|
| 106 |
```python
|