Update README.md

README.md

@@ -35,7 +35,14 @@ tags:
 
 - **Target**: Racism, homophobia, sexism, transphobia and other forms of discrimination.
 
-## 2. Key Enhancements in v2:
+## 2. Try it out:
+
+You can interact with the model directly through the [Inference Endpoint](https://huggingface.co/spaces/delarosajav95/HateSpeech-BETO-cased-v2):
+
+[![Open Inference Endpoint](https://img.shields.io/badge/Open_Inference_Endpoint-blue)](https://huggingface.co/spaces/delarosajav95/HateSpeech-BETO-cased-v2)
+
+
+## 3. Key Enhancements in v2:
 
 - **Previous Version (v1)**: Fine-tuned on the [**Paul/hatecheck-spanish**](https://huggingface.co/datasets/Paul/hatecheck-spanish) dataset, but real-world testing revealed performance issues, limiting its effectiveness.
 
@@ -46,7 +53,7 @@ tags:
 - **Incorporation of Paul Samples**: After evaluating the results, it was clear that including key samples from the **Paul dataset** would help the model capture additional nuanced forms of hate speech, such as **transphobia** and **multiple types of racism**.
   - A significant amount of effort went into carefully selecting and processing these samples from the Paul dataset and integrating them with the **manueltonneau** dataset. This careful curation created a more comprehensive dataset, **enhancing the model's ability to differentiate between hate and non-hate speech**.
 
-## 3. Preprocessing and Postprocessing:
+## 4. Preprocessing and Postprocessing:
 
 To prepare the datasets for fine-tuning and ensure optimal model performance, the following steps were undertaken:
 
@@ -89,13 +96,13 @@ label_mapping = {0.0: 0, 1.0: 1}
   - Applied dynamic padding using the Hugging Face DataCollator to handle varying text lengths efficiently.
   - Batch settings: batch_size=8, shuffle=True.
 
-## 4. Performance Improvements:
+## 5. Performance Improvements:
 
 - **Greater Accuracy**: The inclusion of diverse samples led to a more balanced model that can better handle different forms of discrimination.
 - **Precision in Detecting Non-Hate Speech**: The model is now more reliable at detecting non-hateful content, minimizing false positives.
 - **Robustness**: The updated model performs better in real-world scenarios, offering stronger results for content moderation tasks.
 
-## 5. Use Case:
+## 6. Use Case:
 
 - This model is optimized for content moderation on online platforms, where it can detect harmful speech and help foster safer online environments.
 - **Classification Task**: The model categorizes text into two labels:
@@ -103,15 +110,15 @@ label_mapping = {0.0: 0, 1.0: 1}
   - **Non-Hateful (LABEL_0)**: Content that does not contain hate speech and is neutral or constructive.
   - **Hateful (LABEL_1)**: Content that promotes hate speech or harmful rhetoric.
 
-## 6. Goal:
+## 7. Goal:
 
 The **goal** of the model is to identify content that promotes **harmful rhetoric** or **behavior**, while distinguishing it from **neutral** or **constructive speech**. This makes it highly applicable for **moderating online content**, ensuring that **harmful speech** and **behavior** are flagged while maintaining the integrity of **non-hateful communication**. By accurately identifying and differentiating between **harmful** and **non-harmful** content, this model supports the creation of a **safer** and more **inclusive digital environment**.
 
-## 7. Future Work:
+## 8. Future Work:
 
 While the model demonstrates significant improvements over the previous version, **content moderation** is an ongoing challenge. Further refinements are always possible to improve its accuracy and effectiveness in diverse contexts and improved versions are expected in the near future.
 
-## 8. Full classification example in Pyhton:
+## 9. Full classification example in Pyhton:
 
 To assess the model’s performance, I selected 23 examples representing various types of hate speech and non-hate speech, covering categories such as homophobia, racism, sexism, and transphobia. These examples were carefully chosen from outside the datasets the model was trained or evaluated on, providing a comprehensive test of the model’s ability to generalize and handle real-world data.
 
@@ -286,7 +293,7 @@ Hate Speech: 0.02%
 ```
 </details>
 
-## 9. Metrics and results:
+## 10. Metrics and results:
 
 It achieves the following results on the *evaluation set* (last epoch):
 - 'eval_loss': 0.3601696193218231
@@ -302,7 +309,7 @@ It achieves the following results on the *evaluation set* (last epoch):
 - 'eval_steps_per_second': 30.681
 - 'epoch': 6.0
 
-## 10. Training Details and Procedure:
+## 11. Training Details and Procedure:
 
 ### Main Hyperparameters:
 
@@ -323,14 +330,14 @@ The following hyperparameters were used during training:
 - metric_for_best_model: "eval_loss"
 - greater_is_better: False
 
-## 11. Framework versions:
+## 12. Framework versions:
 
 - Transformers 4.47.1
 - PyTorch version 2.5.1+cu121
 - Datasets version 3.2.0
 - Tokenizers version 0.21.0
 
-## 12. CITATION:
+## 13. CITATION:
 
 - **manueltonneau/spanish-hate-speech-superset**:
 
@@ -386,7 +393,7 @@ For additional information about the dataset, refer to the original [repository]
 ```
 Please, if you use this model, do not forget to include my citation. Thank you!
 
-## 13. Authorship and Contact Information:
+## 14. Authorship and Contact Information:
 
 This model was fine-tuned and optimized by **Javier de la Rosa Sánchez**, applying state-of-the-art techniques to enhance its performance for hate speech detection in Spanish.