multilingual
sea
nxphi47 commited on
Commit
00560d7
·
1 Parent(s): e70d390

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -18
README.md CHANGED
@@ -109,13 +109,10 @@ 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
  <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,
@@ -123,13 +120,10 @@ despite the fact that Llama-2 was already trained on a decent data amount of Vi,
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.
@@ -137,12 +131,8 @@ For important aspects such as Safety and Task-Solving, our model nearly on par w
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
 
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
+
113
  <div class="row" style="display: flex; clear: both;">
114
+ <img src="seallm_vs_polylm_by_lang.png" alt="Snow" style="float: left; width: 48%">
115
+ <img src="seallm_vs_polylm_by_cat_sea.png" alt="Forest" style="float: left; width: 48%">
 
 
 
 
116
  </div>
117
 
118
  Compared with Llama-2-13b-chat, our SeaLLM-13b performs significantly better in all SEA languages,
 
120
  In english, our model is 46% as good as Llama-2-13b-chat, even though it did not undergo complex human-labor intensive RLHF.
121
 
122
 
123
+
124
  <div class="row" style="display: flex; clear: both;">
125
+ <img src="seallm_vs_llama2_by_lang.png" alt="Snow" style="float: left; width: 48%">
126
+ <img src="seallm_vs_llama2_by_cat_sea.png" alt="Forest" style="float: left; width: 48%">
 
 
 
 
127
  </div>
128
 
129
  Compared with ChatGPT-3.5, our SeaLLM-13b model is performing 45% as good as ChatGPT for Thai.
 
131
 
132
 
133
  <div class="row" style="display: flex; clear: both;">
134
+ <img src="seallm_vs_chatgpt_by_lang.png" alt="Snow" style="float: left; width: 48%">
135
+ <img src="seallm_vs_chatgpt_by_cat_sea.png" alt="Forest" style="float: left; width: 48%">
 
 
 
 
136
  </div>
137
 
138
  ### M3Exam - World Knowledge in Regional Languages