Update README.md

README.md

@@ -1,46 +1,55 @@
----
-tags:
-- generated_from_keras_callback
-model-index:
-- name: tf version
-  results: []
----
+# tweet-topic-21-multi
 
-<!-- This model card has been generated automatically according to the information Keras had access to. You should
-probably proofread and complete it, then remove this comment. -->
+This is a roBERTa-base model trained on ~124M tweets from January 2018 to December 2021 (see [here](https://huggingface.co/cardiffnlp/twitter-roberta-base-2021-124m)), and finetuned for single-label topic classification on a corpus of 11,267 tweets.
+The original roBERTa-base model can be found [here](https://huggingface.co/cardiffnlp/twitter-roberta-base-2021-124m) and the original reference paper is [TweetEval](https://github.com/cardiffnlp/tweeteval). This model is suitable for English. 
 
-# tf version
+- Reference Paper: [TimeLMs paper](https://arxiv.org/abs/2202.03829). 
+- Git Repo: [TimeLMs official repository](https://github.com/cardiffnlp/timelms).
 
-This model is a fine-tuned version of [antypasd/tweet-topic-21-multi](https://huggingface.co/antypasd/tweet-topic-21-multi) on an unknown dataset.
-It achieves the following results on the evaluation set:
+<b>Labels</b>: 
 
 
-## Model description
+| <span style="font-weight:normal">0: arts_&_culture</span>           | <span style="font-weight:normal">5: fashion_&_style</span>   | <span style="font-weight:normal">10: learning_&_educational</span>  | <span style="font-weight:normal">15: science_&_technology</span>  |
+|-----------------------------|---------------------|----------------------------|--------------------------|
+| 1: business_&_entrepreneurs | 6: film_tv_&_video  | 11: music                  | 16: sports               |
+| 2: celebrity_&_pop_culture  | 7: fitness_&_health | 12: news_&_social_concern  | 17: travel_&_adventure   |
+| 3: diaries_&_daily_life     | 8: food_&_dining    | 13: other_hobbies          | 18: youth_&_student_life |
+| 4: family                   | 9: gaming           | 14: relationships          |                          |
 
-More information needed
 
-## Intended uses & limitations
+## Full classification example
 
-More information needed
+```python
+from transformers import AutoModelForSequenceClassification
+from transformers import AutoTokenizer
+import numpy as np
+from scipy.special import expit
 
-## Training and evaluation data
+    
+MODEL = f"antypasd/tweet-topic-21-single"
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
 
-More information needed
+# PT
+model = AutoModelForSequenceClassification.from_pretrained(MODEL)
+class_mapping = model.config.id2label
 
-## Training procedure
+text = "It is great to see athletes promoting awareness for climate change."
+tokens = tokenizer(text, return_tensors='pt')
+output = model(**tokens)
 
-### Training hyperparameters
+scores = output[0][0].detach().numpy()
+scores = expit(scores)
+predictions = (scores >= 0.5) * 1
 
-The following hyperparameters were used during training:
-- optimizer: None
-- training_precision: float32
+# Map to classes
+for i in range(len(predictions)):
+  if predictions[i]:
+    print(class_mapping[i])
 
-### Training results
+```
+Output: 
 
-
-
-### Framework versions
-
-- Transformers 4.19.2
-- TensorFlow 2.8.2
-- Tokenizers 0.12.1
+```
+news_&_social_concern
+sports
+```