Update README.md

README.md

@@ -101,13 +101,17 @@ pipeline_tag: text-classification
 metrics:
 - accuracy
 - f1
+- bertscore
 tags:
 - sentiment-analysis
 - thai
 - classification
 - fine-tuned
 - multilingual
-new_version: ZombitX64/Thai-sentiment-e5
+new_version: ZombitX64/MultiSent-E5-Pro
+datasets:
+- ZombitX64/SEACrowdWongnaiReviews
+- ZombitX64/Sentiment-Benchmark
 ---
 
 # MultiSent-E5
@@ -141,7 +145,7 @@ The model is particularly effective at:
 
 ### Model Sources
 
-* **Repository:** [https://huggingface.co/ZombitX64/Thai-sentiment-e5](https://huggingface.co/ZombitX64/Thai-sentiment-e5)
+* **Repository:** [https://huggingface.co/ZombitX64/Thai-sentiment-e5](https://huggingface.co/ZombitX64/ZombitX64/MultiSent-E5-Pro)
 * **Base Model:** [https://huggingface.co/intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large)
 
 ## Uses
@@ -359,29 +363,6 @@ The model showed excellent convergence with minimal overfitting:
 - Accuracy plateaued at 99.63% from epoch 3 onwards
 - Early convergence suggests effective transfer learning from the base model
 
-## Evaluation
-
-### Model Comparison Metrics
-![image.png](https://cdn-uploads.huggingface.co/production/uploads/673eef9c4edfc6d3b58ba3aa/uJQ3RLo9P82ZTAsZUnNdL.png)
-
-### Model Comparison Metrics (Scatter)
-![image.png](https://cdn-uploads.huggingface.co/production/uploads/673eef9c4edfc6d3b58ba3aa/Yk1Odi_-4dVJVOn2wIwoM.png)
-
-| 🥇อันดับ | ชื่อโมเดล                          | Accuracy (%) | หมายเหตุ                       |
-| -------- | ---------------------------------- | ------------ | ------------------------------ |
-| 1        | **MultiSent-E5**                   | **84.88**    | ★ โมเดลที่แม่นยำที่สุด         |
-| 2        | ZombitX64/sentiment-103            | 68.60        | รองชนะเลิศ                     |
-| 3        | Thai-sentiment-e5                  | 67.44        | ดีเด่นด้านความเข้าใจภาษาไทย    |
-| 4        | xlm-roberta                        | 34.30        | multilingual baseline          |
-| 5        | mMiniLM                            | 28.49        | ขนาดเล็ก ใช้ทรัพยากรน้อย       |
-| 6        | wangchan-sentiment-thai-text-model | 25.58        | ภาษาไทยโดยเฉพาะ                |
-| 7        | WangchanBERTa-finetuned-sentiment  | 25.00        | fine-tuned Thai BERT           |
-| 8        | wangchanberta                      | 22.67        | Thai BERT base                 |
-| 9        | Thaweewat/hyperopt-sentiment       | 21.51        | ปรับจูนด้วย hyperopt           |
-| 10       | sentiment-thai-text-model          | 17.44        | baseline keyword model         |
-| 11       | e5-base                            | 16.86        | multilingual encoder           |
-| 12       | twitter-xlm-roberta-base-sentiment | 7.56         | fine-tuned บน Twitter (อังกฤษ) |
-
 ============================================================
 Evaluating Model: MultiSent-E5
 ============================================================
@@ -936,16 +917,6 @@ ZombitX64, K. Janutsaha, and C. Saengwichain, "MultiSent-E5: A Fine-tuned Multil
 
 If you use this model in your research or applications, please cite both this model and the base model:
 
-```bibtex
-@misc{wang2022text,
-  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training}, 
-  author={Liang Wang and Nan Yang and Xiaolong Huang and Binxing Jiao and Linjun Yang and Daxin Jiang and Rangan Majumder and Furu Wei},
-  year={2022},
-  eprint={2212.03533},
-  archivePrefix={arXiv},
-  primaryClass={cs.CL}
-}
-```
 ```bibtex
 @article{wang2024multilingual,
   title={Multilingual E5 Text Embeddings: A Technical Report},
@@ -990,5 +961,5 @@ Your feedback helps improve this model. Please report:
 ---
  
 *Last updated: 2024*
-*Model version: 1.0*
+*Model version: 1.1*
 *Documentation version: 2.0*