Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,11 @@ inference: false
|
|
| 10 |
|
| 11 |
|
| 12 |
<p align="center">
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
</p>
|
| 15 |
|
| 16 |
We introduce SeaLLM - a family of language models optimized for Southeast Asian (SEA) languages. The SeaLLM-base models (to be released) were pre-trained from [Llama-2](https://huggingface.co/meta-llama/Llama-2-13b-hf), on a tailored publicly-available dataset, which comprises mainly Vietnamese 🇻🇳, Indonesian 🇮🇩 and Thai 🇹🇭 texts, along with those in English 🇬🇧 and Chinese 🇨🇳. The pre-training stage involves multiple stages with dynamic data control to preserve the original knowledge base of Llama-2 while gaining new abilities in SEA languages.
|
|
|
|
| 10 |
|
| 11 |
|
| 12 |
<p align="center">
|
| 13 |
+
<a href="https://huggingface.co/SeaLLMs/SeaLLM-Chat-13b-internal"> 🤗 Tech Memo</a>
|
| 14 |
+
|
| 15 |
+
<a href="https://huggingface.co/spaces/SeaLLMs/SeaLLM-Chat-13b"> 🤗 DEMO</a>
|
| 16 |
+
|
| 17 |
+
<a href="https://github.com/SeaLLMs/SeaLLMs">Github</a>
|
| 18 |
</p>
|
| 19 |
|
| 20 |
We introduce SeaLLM - a family of language models optimized for Southeast Asian (SEA) languages. The SeaLLM-base models (to be released) were pre-trained from [Llama-2](https://huggingface.co/meta-llama/Llama-2-13b-hf), on a tailored publicly-available dataset, which comprises mainly Vietnamese 🇻🇳, Indonesian 🇮🇩 and Thai 🇹🇭 texts, along with those in English 🇬🇧 and Chinese 🇨🇳. The pre-training stage involves multiple stages with dynamic data control to preserve the original knowledge base of Llama-2 while gaining new abilities in SEA languages.
|