Update README.md
Browse files
    	
        README.md
    CHANGED
    
    | 
         @@ -23,6 +23,7 @@ tags: 
     | 
|
| 23 | 
         | 
| 24 | 
         
             
            # SeaLLMs - Large Language Models for Southeast Asia
         
     | 
| 25 | 
         | 
| 
         | 
|
| 26 | 
         | 
| 27 | 
         
             
            <p align="center">
         
     | 
| 28 | 
         
             
            <a href="https://huggingface.co/SeaLLMs/SeaLLM-Chat-13b" target="_blank" rel="noopener"> 🤗 Tech Memo</a>
         
     | 
| 
         @@ -38,11 +39,11 @@ We introduce SeaLLMs - a family of language models optimized for Southeast Asian 
     | 
|
| 38 | 
         | 
| 39 | 
         
             
            SeaLLM-13b models exhibit superior performance across a wide spectrum of linguistic tasks and assistant-style instruction-following capabilities relative to comparable open-source models. Moreover, they outperform **ChatGPT-3.5** in non-Latin languages such as Thai, Khmer, Lao, and Burmese.
         
     | 
| 40 | 
         | 
| 41 | 
         
            -
            - DEMO: [SeaLLMs/SeaLLM- 
     | 
| 42 | 
         
             
            - Technical report: [Arxiv: SeaLLMs - Large Language Models for Southeast Asia](https://arxiv.org/pdf/2312.00738.pdf).
         
     | 
| 43 | 
         
             
            - Model weights:
         
     | 
| 44 | 
         
            -
              - [SeaLLM-7B- 
     | 
| 45 | 
         
            -
              - [SeaLLM-7B- 
     | 
| 46 | 
         | 
| 47 | 
         | 
| 48 | 
         
             
            <blockquote style="color:red">
         
     | 
| 
         | 
|
| 23 | 
         | 
| 24 | 
         
             
            # SeaLLMs - Large Language Models for Southeast Asia
         
     | 
| 25 | 
         | 
| 26 | 
         
            +
            # UPDATE: [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) is released with state-of-the-art performance.
         
     | 
| 27 | 
         | 
| 28 | 
         
             
            <p align="center">
         
     | 
| 29 | 
         
             
            <a href="https://huggingface.co/SeaLLMs/SeaLLM-Chat-13b" target="_blank" rel="noopener"> 🤗 Tech Memo</a>
         
     | 
| 
         | 
|
| 39 | 
         | 
| 40 | 
         
             
            SeaLLM-13b models exhibit superior performance across a wide spectrum of linguistic tasks and assistant-style instruction-following capabilities relative to comparable open-source models. Moreover, they outperform **ChatGPT-3.5** in non-Latin languages such as Thai, Khmer, Lao, and Burmese.
         
     | 
| 41 | 
         | 
| 42 | 
         
            +
            - DEMO: [SeaLLMs/SeaLLM-7B](https://huggingface.co/spaces/SeaLLMs/SeaLLM-7B).
         
     | 
| 43 | 
         
             
            - Technical report: [Arxiv: SeaLLMs - Large Language Models for Southeast Asia](https://arxiv.org/pdf/2312.00738.pdf).
         
     | 
| 44 | 
         
             
            - Model weights:
         
     | 
| 45 | 
         
            +
              - (New) [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2): A new model with state-of-the-art performance in reasoning capabilities across all tasks and languages, while half the size of SeaLLM-13B
         
     | 
| 46 | 
         
            +
              - [SeaLLM-7B-v1](https://huggingface.co/SeaLLMs/SeaLLM-7B-v1): Lower capability than [SeaLLM-13B-Chat](https://huggingface.co/spaces/SeaLLMs/SeaLLM-Chat-13b) but much faster and memory-efficient.
         
     | 
| 47 | 
         | 
| 48 | 
         | 
| 49 | 
         
             
            <blockquote style="color:red">
         
     |