Text Classification
Transformers
PyTorch
Safetensors
Polish
bert
twitter
emotion
polish
herbert
Eval Results (legacy)
text-embeddings-inference
Instructions to use bardsai/twitter-emotion-pl-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bardsai/twitter-emotion-pl-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="bardsai/twitter-emotion-pl-base")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("bardsai/twitter-emotion-pl-base") model = AutoModelForSequenceClassification.from_pretrained("bardsai/twitter-emotion-pl-base") - Notebooks
- Google Colab
- Kaggle
docs: add CC BY 4.0 license (inherited from HerBERT), base_model + metadata per HF guidelines
Browse files
README.md
CHANGED
|
@@ -1,10 +1,18 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- text-classification
|
| 5 |
- twitter
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
datasets:
|
| 7 |
-
-
|
| 8 |
metrics:
|
| 9 |
- f1
|
| 10 |
- accuracy
|
|
@@ -15,6 +23,28 @@ widget:
|
|
| 15 |
example_title: "Example 1"
|
| 16 |
- text: "Osoby z Ukrainy zapłacą za życie w centrach pomocy? Sprzeczne prawem UE, niehumanitarne, okrutne."
|
| 17 |
example_title: "Example 2"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
---
|
| 19 |
|
| 20 |
|
|
@@ -52,6 +82,12 @@ nlp("Nigdy przegrana nie sprawiła mi takiej radości. Szczęście i Opatrznoś
|
|
| 52 |
## Changelog
|
| 53 |
- 2023-07-19: Initial release
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
## About bards.ai
|
| 56 |
|
| 57 |
At bards.ai, we focus on providing machine learning expertise and skills to our partners, particularly in the areas of nlp, machine vision and time series analysis. Our team is located in Wroclaw, Poland. Please visit our website for more information: [bards.ai](https://bards.ai/)
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- pl
|
| 4 |
+
license: cc-by-4.0
|
| 5 |
+
library_name: transformers
|
| 6 |
+
pipeline_tag: text-classification
|
| 7 |
tags:
|
| 8 |
- text-classification
|
| 9 |
- twitter
|
| 10 |
+
- emotion
|
| 11 |
+
- polish
|
| 12 |
+
- herbert
|
| 13 |
+
base_model: allegro/herbert-base-cased
|
| 14 |
datasets:
|
| 15 |
+
- tweet_eval
|
| 16 |
metrics:
|
| 17 |
- f1
|
| 18 |
- accuracy
|
|
|
|
| 23 |
example_title: "Example 1"
|
| 24 |
- text: "Osoby z Ukrainy zapłacą za życie w centrach pomocy? Sprzeczne prawem UE, niehumanitarne, okrutne."
|
| 25 |
example_title: "Example 2"
|
| 26 |
+
model-index:
|
| 27 |
+
- name: twitter-emotion-pl-base
|
| 28 |
+
results:
|
| 29 |
+
- task:
|
| 30 |
+
type: text-classification
|
| 31 |
+
name: Emotion Classification
|
| 32 |
+
dataset:
|
| 33 |
+
name: TweetEval (translated to Polish)
|
| 34 |
+
type: tweet_eval
|
| 35 |
+
metrics:
|
| 36 |
+
- type: f1
|
| 37 |
+
value: 0.756
|
| 38 |
+
name: F1 (macro)
|
| 39 |
+
- type: precision
|
| 40 |
+
value: 0.767
|
| 41 |
+
name: Precision (macro)
|
| 42 |
+
- type: recall
|
| 43 |
+
value: 0.750
|
| 44 |
+
name: Recall (macro)
|
| 45 |
+
- type: accuracy
|
| 46 |
+
value: 0.789
|
| 47 |
+
name: Accuracy
|
| 48 |
---
|
| 49 |
|
| 50 |
|
|
|
|
| 82 |
## Changelog
|
| 83 |
- 2023-07-19: Initial release
|
| 84 |
|
| 85 |
+
## License
|
| 86 |
+
|
| 87 |
+
This model is released under the **[Creative Commons Attribution 4.0 International (CC BY 4.0)](https://creativecommons.org/licenses/by/4.0/)** license, inherited from the base model [allegro/herbert-base-cased](https://huggingface.co/allegro/herbert-base-cased) (also CC BY 4.0).
|
| 88 |
+
|
| 89 |
+
Attribution: HerBERT — Allegro ML Research and the Linguistic Engineering Group at the Institute of Computer Science, Polish Academy of Sciences; Twitter emotion PL (base) — bards.ai.
|
| 90 |
+
|
| 91 |
## About bards.ai
|
| 92 |
|
| 93 |
At bards.ai, we focus on providing machine learning expertise and skills to our partners, particularly in the areas of nlp, machine vision and time series analysis. Our team is located in Wroclaw, Poland. Please visit our website for more information: [bards.ai](https://bards.ai/)
|