Update README.md

README.md

@@ -4,26 +4,48 @@ tags:
 - merge
 - mergekit
 - vilm/vinallama-7b-chat
-- vilm/vinallama-7b-chat
-- vilm/vinallama-7b-chat
-- vilm/vinallama-7b-chat
-- vilm/vinallama-7b-chat
-- vilm/vinallama-7b-chat
-- vilm/vinallama-7b-chat
-- vilm/vinallama-7b-chat
 ---
 
-# vinallama-chat-merge-3
+# VinaLLaMA - State-of-the-art Vietnamese LLMs
+
+![image](https://i.ibb.co/W0dq12n/vinallama.png)
+
+Read our [Paper](https://huggingface.co/papers/2312.11011)
+
+Prompt Format (ChatML):
+
+```
+<|im_start|>system
+Bạn là một trợ lí AI hữu ích. Hãy trả lời người dùng một cách chính xác.
+<|im_end|>
+<|im_start|>user
+Hello world!<|im_end|>
+<|im_start|>assistant
+```
+
+## Evaluation
+
+We evaluated our model via peer comparison on multiple publicly available dataset using 
+<a href="https://github.com/hieunguyen1053/lm-evaluation-harness"> @hieunguyen1053 fork of lm-evaluation-harness </a>
+, and combine the results with that provided by the authors of VinaLLaMA. The results are bellow:
+| Model                    | Model size | arc_vi (acc) | hellaswag_vi (acc) | mmlu_vi (acc) | truthfulqa_vi (acc) | Average |
+| ------------------------ | ---------- | ------------ | ------------------ | ------------- | ------------------- | ------- |
+| URA-LLaMA-13B            |            | 0,3752       | 0,4830             | 0,3973        | 0,4574              | 0,4282  |
+| BLOOMZ-7B                |            | 0,3205       | 0,4930             | 0,3975        | 0,4523              | 0,4158  |
+| PhoGPT-7B5-Instruct      |            | 0,2470       | 0,2578             | 0,2413        | 0,4759              | 0,3055  |
+| SeaLLM-7B-chat           |            | 0,3607       | 0,5112             | 0,3339        | 0,4948              | 0,4252  |
+| Vietcuna-7b-v3           |            | 0,3419       | 0,4939             | 0,3354        | 0,4807              | 0,4130  |
+| VinaLLaMA-2.7B-chat      |            | 0,3273       | 0,4814             | 0,3051        | 0,4972              | 0,4028  |
+| VinaLLaMA-7B-chat        |            | 0,4239       | 0,5407             | 0,3932        | 0,5251              | 0,4707  |
+| VBD-LLaMA2-7B-50b        |            | 0,3222       | 0,5195             | 0,2964        | 0,4614              | 0,3999  |
+| VBD-LLaMA2-7B-50b-Chat   |            | 0,3585       | 0,5207             | 0,3444        | 0,5179              | 0,4354  |
+| VinaLLaMA-12.5B-chat-DUS |            | 0,4325       | 0,5816             | 0,3875        | 0,5850              | 0,4967  |
+
+# Merging Methods
 
 This model is a merge of the following models made with [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
  * [vilm/vinallama-7b-chat](https://huggingface.co/vilm/vinallama-7b-chat)
- * [vilm/vinallama-7b-chat](https://huggingface.co/vilm/vinallama-7b-chat)
- * [vilm/vinallama-7b-chat](https://huggingface.co/vilm/vinallama-7b-chat)
- * [vilm/vinallama-7b-chat](https://huggingface.co/vilm/vinallama-7b-chat)
- * [vilm/vinallama-7b-chat](https://huggingface.co/vilm/vinallama-7b-chat)
- * [vilm/vinallama-7b-chat](https://huggingface.co/vilm/vinallama-7b-chat)
- * [vilm/vinallama-7b-chat](https://huggingface.co/vilm/vinallama-7b-chat)
- * [vilm/vinallama-7b-chat](https://huggingface.co/vilm/vinallama-7b-chat)
+
 
 ## 🧩 Configuration