multilingual
sea
nxphi47 commited on
Commit
503bd28
·
1 Parent(s): f4a7da1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -9
README.md CHANGED
@@ -109,26 +109,41 @@ We use GPT-4 as an evaluator to rate the comparison between our models versus Ch
109
 
110
  Compared with [PolyLM-13b-chat](https://arxiv.org/pdf/2307.06018.pdf), a recent multilingual model, our model significantly outperforms across all languages and categories.
111
 
112
- <img src="seallm_vs_polylm_by_lang.png" width="500" />
113
-
114
- <img src="seallm_vs_polylm_by_cat_sea.png" width="500" />
 
 
 
 
 
115
 
116
  Compared with Llama-2-13b-chat, our SeaLLM-13b performs significantly better in all SEA languages,
117
  despite the fact that Llama-2 was already trained on a decent data amount of Vi, Id, and Th.
118
  In english, our model is 46% as good as Llama-2-13b-chat, even though it did not undergo complex human-labor intensive RLHF.
119
 
120
- <img src="seallm_vs_llama2_by_lang.png" width="500" />
121
 
122
- <img src="seallm_vs_llama2_by_cat_sea.png" width="500" />
 
 
 
 
 
 
 
123
 
124
  Compared with ChatGPT-3.5, our SeaLLM-13b model is performing 45% as good as ChatGPT for Thai.
125
  For important aspects such as Safety and Task-Solving, our model nearly on par with ChatGPT across the languages.
126
 
127
- <img src="seallm_vs_chatgpt_by_lang.png" width="500" />
128
-
129
- <img src="seallm_vs_chatgpt_by_cat_sea.png" width="500" />
130
-
131
 
 
 
 
 
 
 
 
 
132
 
133
  ### M3Exam - World Knowledge in Regional Languages
134
 
 
109
 
110
  Compared with [PolyLM-13b-chat](https://arxiv.org/pdf/2307.06018.pdf), a recent multilingual model, our model significantly outperforms across all languages and categories.
111
 
112
+ <div class="row" style="display: flex; clear: both;">
113
+ <div class="column" style="float: left; width: 49%">
114
+ <img src="seallm_vs_polylm_by_lang.png" alt="Snow" style="width:100%">
115
+ </div>
116
+ <div class="column" style="float: left; width: 49%">
117
+ <img src="seallm_vs_polylm_by_cat_sea.png" alt="Forest" style="width:100%">
118
+ </div>
119
+ </div>
120
 
121
  Compared with Llama-2-13b-chat, our SeaLLM-13b performs significantly better in all SEA languages,
122
  despite the fact that Llama-2 was already trained on a decent data amount of Vi, Id, and Th.
123
  In english, our model is 46% as good as Llama-2-13b-chat, even though it did not undergo complex human-labor intensive RLHF.
124
 
 
125
 
126
+ <div class="row" style="display: flex; clear: both;">
127
+ <div class="column" style="float: left; width: 49%">
128
+ <img src="seallm_vs_llama2_by_lang.png" alt="Snow" style="width:100%">
129
+ </div>
130
+ <div class="column" style="float: left; width: 49%">
131
+ <img src="seallm_vs_llama2_by_cat_sea.png" alt="Forest" style="width:100%">
132
+ </div>
133
+ </div>
134
 
135
  Compared with ChatGPT-3.5, our SeaLLM-13b model is performing 45% as good as ChatGPT for Thai.
136
  For important aspects such as Safety and Task-Solving, our model nearly on par with ChatGPT across the languages.
137
 
 
 
 
 
138
 
139
+ <div class="row" style="display: flex; clear: both;">
140
+ <div class="column" style="float: left; width: 49%">
141
+ <img src="seallm_vs_chatgpt_by_lang.png" alt="Snow" style="width:100%">
142
+ </div>
143
+ <div class="column" style="float: left; width: 49%">
144
+ <img src="seallm_vs_chatgpt_by_cat_sea.png" alt="Forest" style="width:100%">
145
+ </div>
146
+ </div>
147
 
148
  ### M3Exam - World Knowledge in Regional Languages
149