fix examples

Signed-off-by: Zhiyuan Chen <[email protected]>
DLS5-Omics · Jan 22, 2025 · 0f86c56 · 0f86c56
1 parent ac5c429
commit 0f86c56
Show file tree

Hide file tree

Showing 12 changed files with 129 additions and 123 deletions.
diff --git a/multimolecule/models/ernierna/README.ernierna-ss.md b/multimolecule/models/ernierna/README.ernierna-ss.md
@@ -25,18 +25,18 @@ widget:
       - label: "."
         score: 0.10200861096382141
   - example_title: "microRNA-21"
-    text: "UAGC<mask>UAUCAGACUGAUGUUGA"
+    text: "UAGC<mask>UAUCAGACUGAUGUUG"
     output:
       - label: "U"
-        score: 0.20929744839668274
-      - label: "C"
-        score: 0.1741773933172226
-      - label: "G"
-        score: 0.16430608928203583
+        score: 0.23881851136684418
       - label: "A"
-        score: 0.1348584145307541
-      - label: "."
-        score: 0.11933524906635284
+        score: 0.2219424843788147
+      - label: "G"
+        score: 0.133585587143898
+      - label: "C"
+        score: 0.11793075501918793
+      - label: "-"
+        score: 0.10667591542005539
 ---
 
 # ERNIE-RNA
@@ -131,7 +131,7 @@ from multimolecule import RnaTokenizer, ErnieRnaModel
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna-ss")
 model = ErnieRnaModel.from_pretrained("multimolecule/ernierna-ss")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 
 output = model(**input)
@@ -151,7 +151,7 @@ from multimolecule import RnaTokenizer, ErnieRnaForSequencePrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna-ss")
 model = ErnieRnaForSequencePrediction.from_pretrained("multimolecule/ernierna-ss")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.tensor([1])
 
@@ -172,7 +172,7 @@ from multimolecule import RnaTokenizer, ErnieRnaForTokenPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna-ss")
 model = ErnieRnaForTokenPrediction.from_pretrained("multimolecule/ernierna-ss")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), ))
 
@@ -193,7 +193,7 @@ from multimolecule import RnaTokenizer, ErnieRnaForContactPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna-ss")
 model = ErnieRnaForContactPrediction.from_pretrained("multimolecule/ernierna-ss")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), len(text)))
 

diff --git a/multimolecule/models/ernierna/README.md b/multimolecule/models/ernierna/README.md
@@ -24,18 +24,18 @@ widget:
       - label: "."
         score: 0.06993662565946579
   - example_title: "microRNA-21"
-    text: "UAGC<mask>UAUCAGACUGAUGUUGA"
+    text: "UAGC<mask>UAUCAGACUGAUGUUG"
     output:
-      - label: "U"
-        score: 0.22777850925922394
       - label: "A"
-        score: 0.21105751395225525
-      - label: "C"
-        score: 0.18962091207504272
+        score: 0.28607121109962463
+      - label: "U"
+        score: 0.24161304533481598
       - label: "G"
-        score: 0.11191495507955551
-      - label: "."
-        score: 0.09583593904972076
+        score: 0.12279549986124039
+      - label: "C"
+        score: 0.10425350069999695
+      - label: "-"
+        score: 0.09150994569063187
 ---
 
 # ERNIE-RNA
@@ -130,7 +130,7 @@ from multimolecule import RnaTokenizer, ErnieRnaModel
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna")
 model = ErnieRnaModel.from_pretrained("multimolecule/ernierna")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 
 output = model(**input)
@@ -150,7 +150,7 @@ from multimolecule import RnaTokenizer, ErnieRnaForSequencePrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna")
 model = ErnieRnaForSequencePrediction.from_pretrained("multimolecule/ernierna")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.tensor([1])
 
@@ -171,7 +171,7 @@ from multimolecule import RnaTokenizer, ErnieRnaForTokenPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna")
 model = ErnieRnaForTokenPrediction.from_pretrained("multimolecule/ernierna")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), ))
 
@@ -192,7 +192,7 @@ from multimolecule import RnaTokenizer, ErnieRnaForContactPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna")
 model = ErnieRnaForContactPrediction.from_pretrained("multimolecule/ernierna")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), len(text)))
 

diff --git a/multimolecule/models/rinalmo/README.md b/multimolecule/models/rinalmo/README.md
@@ -27,18 +27,18 @@ widget:
       - label: "G"
         score: 0.0408296100795269
   - example_title: "microRNA-21"
-    text: "UAGC<mask>UAUCAGACUGAUGUUGA"
+    text: "UAGC<mask>UAUCAGACUGAUGUUG"
     output:
       - label: "A"
-        score: 0.2931748032569885
+        score: 0.27524828910827637
       - label: "U"
-        score: 0.2710167169570923
+        score: 0.27015420794487
       - label: "X"
-        score: 0.18341825902462006
+        score: 0.1874540150165558
       - label: "C"
-        score: 0.16714636981487274
+        score: 0.16866911947727203
       - label: "G"
-        score: 0.08522326499223709
+        score: 0.09844783693552017
 ---
 
 # RiNALMo
@@ -129,7 +129,7 @@ from multimolecule import RnaTokenizer, RiNALMoModel
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rinalmo")
 model = RiNALMoModel.from_pretrained("multimolecule/rinalmo")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 
 output = model(**input)
@@ -149,7 +149,7 @@ from multimolecule import RnaTokenizer, RiNALMoForSequencePrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rinalmo")
 model = RiNALMoForSequencePrediction.from_pretrained("multimolecule/rinalmo")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.tensor([1])
 
@@ -170,7 +170,7 @@ from multimolecule import RnaTokenizer, RiNALMoForTokenPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rinalmo")
 model = RiNALMoForTokenPrediction.from_pretrained("multimolecule/rinalmo")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), ))
 
@@ -191,7 +191,7 @@ from multimolecule import RnaTokenizer, RiNALMoForContactPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rinalmo")
 model = RiNALMoForContactPrediction.from_pretrained("multimolecule/rinalmo")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), len(text)))
 

diff --git a/multimolecule/models/rnabert/README.md b/multimolecule/models/rnabert/README.md
@@ -24,18 +24,18 @@ widget:
       - label: "<null>"
         score: 0.038484156131744385
   - example_title: "microRNA-21"
-    text: "UAGC<mask>UAUCAGACUGAUGUUGA"
+    text: "UAGC<mask>UAUCAGACUGAUGUUG"
     output:
       - label: "N"
-        score: 0.0385337695479393
+        score: 0.03855736553668976
       - label: "I"
-        score: 0.03851701319217682
+        score: 0.03851182386279106
       - label: "<unk>"
-        score: 0.03850541263818741
+        score: 0.038497816771268845
       - label: "<null>"
-        score: 0.03850402310490608
-      - label: "<cls>"
-        score: 0.03848475590348244
+        score: 0.03848177567124367
+      - label: "-"
+        score: 0.038468137383461
 ---
 
 # RNABERT
@@ -134,7 +134,7 @@ from multimolecule import RnaTokenizer, RnaBertModel
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnabert")
 model = RnaBertModel.from_pretrained("multimolecule/rnabert")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 
 output = model(**input)
@@ -154,7 +154,7 @@ from multimolecule import RnaTokenizer, RnaBertForSequencePrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnabert")
 model = RnaBertForSequencePrediction.from_pretrained("multimolecule/rnabert")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.tensor([1])
 
@@ -175,7 +175,7 @@ from multimolecule import RnaTokenizer, RnaBertForTokenPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnabert")
 model = RnaBertForTokenPrediction.from_pretrained("multimolecule/rnabert")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), ))
 
@@ -196,7 +196,7 @@ from multimolecule import RnaTokenizer, RnaBertForContactPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnabert")
 model = RnaBertForContactPrediction.from_pretrained("multimolecule/rnabert")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), len(text)))
 

diff --git a/multimolecule/models/rnaernie/README.md b/multimolecule/models/rnaernie/README.md
@@ -24,18 +24,18 @@ widget:
       - label: "S"
         score: 0.07325706630945206
   - example_title: "microRNA-21"
-    text: "UAGC<mask>UAUCAGACUGAUGUUGA"
+    text: "UAGC<mask>UAUCAGACUGAUGUUG"
     output:
-      - label: "G"
-        score: 0.09372635930776596
-      - label: "R"
-        score: 0.08816102892160416
       - label: "A"
-        score: 0.08292599022388458
-      - label: "<eos>"
-        score: 0.07841548323631287
+        score: 0.08444530516862869
+      - label: "R"
+        score: 0.07878861576318741
+      - label: "G"
+        score: 0.07351073622703552
       - label: "V"
-        score: 0.073448047041893
+        score: 0.07145819813013077
+      - label: "M"
+        score: 0.07045349478721619
 ---
 
 # RNAErnie
@@ -146,7 +146,7 @@ from multimolecule import RnaTokenizer, RnaErnieModel
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnaernie")
 model = RnaErnieModel.from_pretrained("multimolecule/rnaernie")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 
 output = model(**input)
@@ -166,7 +166,7 @@ from multimolecule import RnaTokenizer, RnaErnieForSequencePrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnaernie")
 model = RnaErnieForSequencePrediction.from_pretrained("multimolecule/rnaernie")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.tensor([1])
 
@@ -187,7 +187,7 @@ from multimolecule import RnaTokenizer, RnaErnieForTokenPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnaernie")
 model = RnaErnieForTokenPrediction.from_pretrained("multimolecule/rnaernie")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), ))
 
@@ -208,7 +208,7 @@ from multimolecule import RnaTokenizer, RnaErnieForContactPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnaernie")
 model = RnaErnieForContactPrediction.from_pretrained("multimolecule/rnaernie")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), len(text)))
 

diff --git a/multimolecule/models/rnafm/README.md b/multimolecule/models/rnafm/README.md
@@ -24,18 +24,18 @@ widget:
       - label: "A"
         score: 0.08898332715034485
   - example_title: "microRNA-21"
-    text: "UAGC<mask>UAUCAGACUGAUGUUGA"
+    text: "UAGC<mask>UAUCAGACUGAUGUUG"
     output:
       - label: "."
-        score: 0.23545819520950317
+        score: 0.2275155633687973
       - label: "*"
-        score: 0.1889132708311081
+        score: 0.18255384266376495
       - label: "I"
-        score: 0.15300516784191132
+        score: 0.14644214510917664
       - label: "A"
-        score: 0.12081773579120636
+        score: 0.1262909322977066
       - label: "U"
-        score: 0.10451140254735947
+        score: 0.12270607799291611
 ---
 
 # RNA-FM
@@ -162,7 +162,7 @@ from multimolecule import RnaTokenizer, RnaFmModel
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnafm")
 model = RnaFmModel.from_pretrained("multimolecule/rnafm")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 
 output = model(**input)
@@ -182,7 +182,7 @@ from multimolecule import RnaTokenizer, RnaFmForSequencePrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnafm")
 model = RnaFmForSequencePrediction.from_pretrained("multimolecule/rnafm")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.tensor([1])
 
@@ -203,7 +203,7 @@ from multimolecule import RnaTokenizer, RnaFmForTokenPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnafm")
 model = RnaFmForTokenPrediction.from_pretrained("multimolecule/rnafm")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), ))
 
@@ -224,7 +224,7 @@ from multimolecule import RnaTokenizer, RnaFmForContactPrediction
 tokenizer = RnaTokenizer.from_pretrained("multimolecule/rnafm")
 model = RnaFmForContactPrediction.from_pretrained("multimolecule/rnafm")
 
-text = "UAGCUUAUCAGACUGAUGUUGA"
+text = "UAGCUUAUCAGACUGAUGUUG"
 input = tokenizer(text, return_tensors="pt")
 label = torch.randint(2, (len(text), len(text)))