Update README.md
Browse files
README.md
CHANGED
@@ -126,6 +126,10 @@ Cross-Encoder (Reranker)
|
|
126 |
| gte-multilingual-reranker-base | 0.7281 | 0.7281 | 0.7281 |
|
127 |
| jina-reranker-v2-base-multilingual | 0.8070 | 0.8070 | 0.8070 |
|
128 |
| bge-reranker-v2-m3 | 0.8772 | 0.8772 | 0.8772 |
|
|
|
|
|
|
|
|
|
129 |
| **bge-reranker-v2-m3-ko** | **0.9123** | **0.9123** | **0.9123** |
|
130 |
|
131 |
|
@@ -161,42 +165,10 @@ Cross-Encoder (Reranker)
|
|
161 |
| gte-multilingual-reranker-base | 0.4605 | 0.9211 | 0.3070 |
|
162 |
| jina-reranker-v2-base-multilingual | 0.4649 | 0.9298 | 0.3099 |
|
163 |
| bge-reranker-v2-m3 | 0.4781 | 0.9561 | 0.3187 |
|
|
|
|
|
|
|
|
|
164 |
| **bge-reranker-v2-m3-ko** | **0.4825** | **0.9649** | **0.3216** |
|
165 |
|
166 |
|
167 |
-
**Top-k 5**
|
168 |
-
|
169 |
-
Bi-Encoder (Sentence Transformer)
|
170 |
-
|
171 |
-
| Model name | F1 | Recall | Precision |
|
172 |
-
|---------------------------------------|------------|------------|------------|
|
173 |
-
| paraphrase-multilingual-mpnet-base-v2 | 0.1813 | 0.5439 | 0.1088 |
|
174 |
-
| KoSimCSE-roberta | 0.2164 | 0.6491 | 0.1298 |
|
175 |
-
| Cohere embed-multilingual-v3.0 | 0.2076 | 0.6228 | 0.1246 |
|
176 |
-
| openai ada 002 | 0.2602 | 0.7807 | 0.1561 |
|
177 |
-
| multilingual-e5-large-instruct | 0.2544 | 0.7632 | 0.1526 |
|
178 |
-
| Upstage Embedding | 0.2982 | 0.8947 | 0.1789 |
|
179 |
-
| paraphrase-multilingual-MiniLM-L12-v2 | 0.1637 | 0.4912 | 0.0982 |
|
180 |
-
| openai_embed_3_small | 0.2690 | 0.8070 | 0.1614 |
|
181 |
-
| ko-sroberta-multitask | 0.2164 | 0.6491 | 0.1298 |
|
182 |
-
| openai_embed_3_large | 0.2807 | 0.8421 | 0.1684 |
|
183 |
-
| KU-HIAI-ONTHEIT-large-v1 | 0.3041 | 0.9123 | 0.1825 |
|
184 |
-
| KU-HIAI-ONTHEIT-large-v1.1 | **0.3099** | **0.9298** | **0.1860** |
|
185 |
-
| kf-deberta-multitask | 0.2281 | 0.6842 | 0.1368 |
|
186 |
-
| gte-multilingual-base | 0.2865 | 0.8596 | 0.1719 |
|
187 |
-
| KoE5 | 0.2982 | 0.8947 | 0.1789 |
|
188 |
-
| BGE-m3 | 0.3041 | 0.9123 | 0.1825 |
|
189 |
-
| bge-m3-korean | 0.2661 | 0.7982 | 0.1596 |
|
190 |
-
| **BGE-m3-ko** | **0.3099** | **0.9298** | **0.1860** |
|
191 |
-
|
192 |
-
Cross-Encoder (Reranker)
|
193 |
-
|
194 |
-
| Model name | F1 | Recall | Precision |
|
195 |
-
|---------------------------------------|------------|------------|------------|
|
196 |
-
| gte-multilingual-reranker-base | 0.3158 | 0.9474 | 0.1895 |
|
197 |
-
| jina-reranker-v2-base-multilingual | 0.3129 | 0.9386 | 0.1877 |
|
198 |
-
| bge-reranker-v2-m3 | **0.3216** | **0.9649** | **0.1930** |
|
199 |
-
| **bge-reranker-v2-m3-ko** | **0.3216** | **0.9649** | **0.1930** |
|
200 |
-
|
201 |
-
|
202 |
-
|
|
|
126 |
| gte-multilingual-reranker-base | 0.7281 | 0.7281 | 0.7281 |
|
127 |
| jina-reranker-v2-base-multilingual | 0.8070 | 0.8070 | 0.8070 |
|
128 |
| bge-reranker-v2-m3 | 0.8772 | 0.8772 | 0.8772 |
|
129 |
+
| upskyy/ko-reranker-8k | 0.8684| 0.8684 | 0.8684 |
|
130 |
+
| upskyy/ko-reranker | 0.8333| 0.8333 | 0.8333 |
|
131 |
+
| mncai/bge-ko-reranker-560M | 0.0088| 0.0088 | 0.0088 |
|
132 |
+
| Dongjin-kr/ko-reranker | 0.8509| 0.8509 | 0.8509 |
|
133 |
| **bge-reranker-v2-m3-ko** | **0.9123** | **0.9123** | **0.9123** |
|
134 |
|
135 |
|
|
|
165 |
| gte-multilingual-reranker-base | 0.4605 | 0.9211 | 0.3070 |
|
166 |
| jina-reranker-v2-base-multilingual | 0.4649 | 0.9298 | 0.3099 |
|
167 |
| bge-reranker-v2-m3 | 0.4781 | 0.9561 | 0.3187 |
|
168 |
+
| upskyy/ko-reranker-8k | 0.4781| 0.9561 | 0.3187 |
|
169 |
+
| upskyy/ko-reranker | 0.4649| 0.9298 | 0.3099 |
|
170 |
+
| mncai/bge-ko-reranker-560M | 0.0044| 0.0088 | 0.0029 |
|
171 |
+
| Dongjin-kr/ko-reranker | 0.4737| 0.9474 | 0.3158 |
|
172 |
| **bge-reranker-v2-m3-ko** | **0.4825** | **0.9649** | **0.3216** |
|
173 |
|
174 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|