huseinzol05 commited on
Commit
7ac8402
β€’
1 Parent(s): 93c3529

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +4 -4
app.py CHANGED
@@ -9,14 +9,14 @@ INTRODUCTION_TEXT = """
9
 
10
  ## Dataset
11
 
12
- πŸ“ˆ We evaluate models based on 2 datasets,
13
 
14
  1. Research paper keyword `melayu` using Crossref, **this test set is about RAG**, https://huggingface.co/datasets/mesolitica/malaysian-ultrachat/resolve/main/ultrachat-crossref-melayu-malay.jsonl
15
  2. lom.agc.gov.my PDF files, **this test set is about RAG**, https://huggingface.co/datasets/mesolitica/malaysian-ultrachat/resolve/main/ultrachat-lom-agc.jsonl
16
  3. b.cari.com.my, **this test set is about semantic similarity**, https://huggingface.co/datasets/mesolitica/embedding-pair-mining/resolve/main/b.cari.com.my-dataset-bge-test.jsonl
17
- 3. c.cari.com.my, **this test set is about semantic similarity**, https://huggingface.co/datasets/mesolitica/embedding-pair-mining/resolve/main/c.cari.com.my-dataset-bge-test.jsonl
18
- 3. Malay news, **this test set is about semantic similarity**, https://huggingface.co/datasets/mesolitica/embedding-pair-mining/resolve/main/malay-news-dataset-bge-test.jsonl
19
- 3. Twitter, **this test set is about semantic similarity**, https://huggingface.co/datasets/mesolitica/embedding-pair-mining/resolve/main/twitter-dataset-bge-test.jsonl
20
  """
21
 
22
  close_source = [
 
9
 
10
  ## Dataset
11
 
12
+ πŸ“ˆ We evaluate models based on 6 datasets,
13
 
14
  1. Research paper keyword `melayu` using Crossref, **this test set is about RAG**, https://huggingface.co/datasets/mesolitica/malaysian-ultrachat/resolve/main/ultrachat-crossref-melayu-malay.jsonl
15
  2. lom.agc.gov.my PDF files, **this test set is about RAG**, https://huggingface.co/datasets/mesolitica/malaysian-ultrachat/resolve/main/ultrachat-lom-agc.jsonl
16
  3. b.cari.com.my, **this test set is about semantic similarity**, https://huggingface.co/datasets/mesolitica/embedding-pair-mining/resolve/main/b.cari.com.my-dataset-bge-test.jsonl
17
+ 4. c.cari.com.my, **this test set is about semantic similarity**, https://huggingface.co/datasets/mesolitica/embedding-pair-mining/resolve/main/c.cari.com.my-dataset-bge-test.jsonl
18
+ 5. Malay news, **this test set is about semantic similarity**, https://huggingface.co/datasets/mesolitica/embedding-pair-mining/resolve/main/malay-news-dataset-bge-test.jsonl
19
+ 6. Twitter, **this test set is about semantic similarity**, https://huggingface.co/datasets/mesolitica/embedding-pair-mining/resolve/main/twitter-dataset-bge-test.jsonl
20
  """
21
 
22
  close_source = [