Instructions to use twn39/bert-base-chinese-finetune-dianping with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use twn39/bert-base-chinese-finetune-dianping with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="twn39/bert-base-chinese-finetune-dianping")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("twn39/bert-base-chinese-finetune-dianping") model = AutoModelForSequenceClassification.from_pretrained("twn39/bert-base-chinese-finetune-dianping", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,9 @@ pipeline_tag: text-classification
|
|
| 10 |
library_name: transformers
|
| 11 |
---
|
| 12 |
|
|
|
|
|
|
|
|
|
|
| 13 |
最终评估结果:
|
| 14 |
======================================================================
|
| 15 |
eval_loss............................... 0.9778
|
|
@@ -27,6 +30,10 @@ library_name: transformers
|
|
| 27 |
eval_steps_per_second................... 4.2790
|
| 28 |
epoch................................... 6.0000
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
详细分类报告:
|
| 31 |
======================================================================
|
| 32 |
precision recall f1-score support
|
|
@@ -39,4 +46,6 @@ library_name: transformers
|
|
| 39 |
|
| 40 |
accuracy 0.7857 8997
|
| 41 |
macro avg 0.7701 0.7821 0.7752 8997
|
| 42 |
-
weighted avg 0.7908 0.7857 0.7875 8997
|
|
|
|
|
|
|
|
|
| 10 |
library_name: transformers
|
| 11 |
---
|
| 12 |
|
| 13 |
+
|
| 14 |
+
```
|
| 15 |
+
|
| 16 |
最终评估结果:
|
| 17 |
======================================================================
|
| 18 |
eval_loss............................... 0.9778
|
|
|
|
| 30 |
eval_steps_per_second................... 4.2790
|
| 31 |
epoch................................... 6.0000
|
| 32 |
|
| 33 |
+
```
|
| 34 |
+
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
详细分类报告:
|
| 38 |
======================================================================
|
| 39 |
precision recall f1-score support
|
|
|
|
| 46 |
|
| 47 |
accuracy 0.7857 8997
|
| 48 |
macro avg 0.7701 0.7821 0.7752 8997
|
| 49 |
+
weighted avg 0.7908 0.7857 0.7875 8997
|
| 50 |
+
|
| 51 |
+
```
|