Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +2 -0
- classifierDL-bert-lang-detect/metadata/_SUCCESS +0 -0
- classifierDL-bert-lang-detect/metadata/_committed_6593034593231839734 +1 -0
- classifierDL-bert-lang-detect/metadata/_started_6593034593231839734 +0 -0
- classifierDL-bert-lang-detect/metadata/part-00000-tid-6593034593231839734-2eaa5d67-5ef0-4066-9f3b-ecc65cf0d06f-302-1-c000.txt +1 -0
- classifierDL-bert-lang-detect/stages/0_DocumentAssembler_a85d70e054b5/metadata/_SUCCESS +0 -0
- classifierDL-bert-lang-detect/stages/0_DocumentAssembler_a85d70e054b5/metadata/_committed_4249049908337889056 +1 -0
- classifierDL-bert-lang-detect/stages/0_DocumentAssembler_a85d70e054b5/metadata/_started_4249049908337889056 +0 -0
- classifierDL-bert-lang-detect/stages/0_DocumentAssembler_a85d70e054b5/metadata/part-00000-tid-4249049908337889056-a4a31c1d-3f7b-4051-adb3-64864ba4b29e-303-1-c000.txt +1 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/_SUCCESS +0 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00000 +0 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00001 +0 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00002 +0 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00003 +0 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00004 +0 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00005 +0 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00006 +0 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00007 +0 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/metadata/_SUCCESS +0 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/metadata/_committed_5570049922655100179 +1 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/metadata/_started_5570049922655100179 +0 -0
- classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/metadata/part-00000-tid-5570049922655100179-03384181-9cc1-419d-ad0b-7e906f83f8f0-304-1-c000.txt +1 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/bert_onnx +3 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/_SUCCESS +0 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00000 +0 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00001 +0 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00002 +0 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00003 +0 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00004 +0 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00005 +0 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00006 +0 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00007 +0 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/metadata/_SUCCESS +0 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/metadata/_committed_4031617553090561353 +1 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/metadata/_started_4031617553090561353 +0 -0
- classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/metadata/part-00000-tid-4031617553090561353-9ae763c5-4ae4-41a4-bc41-0a6d28282a0c-313-1-c000.txt +1 -0
- classifierDL-bert-lang-detect/stages/3_SentenceEmbeddings_5f3b5483102a/metadata/_SUCCESS +0 -0
- classifierDL-bert-lang-detect/stages/3_SentenceEmbeddings_5f3b5483102a/metadata/_committed_3272538039056848776 +1 -0
- classifierDL-bert-lang-detect/stages/3_SentenceEmbeddings_5f3b5483102a/metadata/_started_3272538039056848776 +0 -0
- classifierDL-bert-lang-detect/stages/3_SentenceEmbeddings_5f3b5483102a/metadata/part-00000-tid-3272538039056848776-6af10195-5094-49e2-a0ad-e92bb8525b0a-322-1-c000.txt +1 -0
- classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/classifierdl_tensorflow +3 -0
- classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/_SUCCESS +0 -0
- classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00000 +0 -0
- classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00001 +0 -0
- classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00002 +0 -0
- classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00003 +0 -0
- classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00004 +0 -0
- classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00005 +0 -0
- classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00006 +0 -0
- classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00007 +0 -0
.gitattributes
CHANGED
@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
classifierDL-lang-detect/stages/1_UNIVERSAL_SENTENCE_ENCODER_4de71669b7ec/use_tensorflow filter=lfs diff=lfs merge=lfs -text
|
37 |
classifierDL-lang-detect/stages/2_ClassifierDLModel_7d8464466588/classifierdl_tensorflow filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
classifierDL-lang-detect/stages/1_UNIVERSAL_SENTENCE_ENCODER_4de71669b7ec/use_tensorflow filter=lfs diff=lfs merge=lfs -text
|
37 |
classifierDL-lang-detect/stages/2_ClassifierDLModel_7d8464466588/classifierdl_tensorflow filter=lfs diff=lfs merge=lfs -text
|
38 |
+
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/bert_onnx filter=lfs diff=lfs merge=lfs -text
|
39 |
+
classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/classifierdl_tensorflow filter=lfs diff=lfs merge=lfs -text
|
classifierDL-bert-lang-detect/metadata/_SUCCESS
ADDED
File without changes
|
classifierDL-bert-lang-detect/metadata/_committed_6593034593231839734
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"added":["part-00000-tid-6593034593231839734-2eaa5d67-5ef0-4066-9f3b-ecc65cf0d06f-302-1-c000.txt"],"removed":[]}
|
classifierDL-bert-lang-detect/metadata/_started_6593034593231839734
ADDED
File without changes
|
classifierDL-bert-lang-detect/metadata/part-00000-tid-6593034593231839734-2eaa5d67-5ef0-4066-9f3b-ecc65cf0d06f-302-1-c000.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"class":"org.apache.spark.ml.PipelineModel","timestamp":1727274381634,"sparkVersion":"3.5.0","uid":"PipelineModel_1e1260dd05f2","paramMap":{"stageUids":["DocumentAssembler_a85d70e054b5","REGEX_TOKENIZER_bc93b0d170c6","BERT_EMBEDDINGS_69dd9fb1854f","SentenceEmbeddings_5f3b5483102a","ClassifierDLModel_a78c9498f386"]},"defaultParamMap":{}}
|
classifierDL-bert-lang-detect/stages/0_DocumentAssembler_a85d70e054b5/metadata/_SUCCESS
ADDED
File without changes
|
classifierDL-bert-lang-detect/stages/0_DocumentAssembler_a85d70e054b5/metadata/_committed_4249049908337889056
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"added":["part-00000-tid-4249049908337889056-a4a31c1d-3f7b-4051-adb3-64864ba4b29e-303-1-c000.txt"],"removed":[]}
|
classifierDL-bert-lang-detect/stages/0_DocumentAssembler_a85d70e054b5/metadata/_started_4249049908337889056
ADDED
File without changes
|
classifierDL-bert-lang-detect/stages/0_DocumentAssembler_a85d70e054b5/metadata/part-00000-tid-4249049908337889056-a4a31c1d-3f7b-4051-adb3-64864ba4b29e-303-1-c000.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"class":"com.johnsnowlabs.nlp.DocumentAssembler","timestamp":1727274382400,"sparkVersion":"3.5.0","uid":"DocumentAssembler_a85d70e054b5","paramMap":{"inputCol":"text","outputCol":"document"},"defaultParamMap":{"cleanupMode":"disabled","outputCol":"document"}}
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/_SUCCESS
ADDED
File without changes
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00000
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00001
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00002
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00003
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00004
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00005
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00006
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/fields/rules/part-00007
ADDED
Binary file (4.72 kB). View file
|
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/metadata/_SUCCESS
ADDED
File without changes
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/metadata/_committed_5570049922655100179
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"added":["part-00000-tid-5570049922655100179-03384181-9cc1-419d-ad0b-7e906f83f8f0-304-1-c000.txt"],"removed":[]}
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/metadata/_started_5570049922655100179
ADDED
File without changes
|
classifierDL-bert-lang-detect/stages/1_REGEX_TOKENIZER_bc93b0d170c6/metadata/part-00000-tid-5570049922655100179-03384181-9cc1-419d-ad0b-7e906f83f8f0-304-1-c000.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"class":"com.johnsnowlabs.nlp.annotators.TokenizerModel","timestamp":1727274383139,"sparkVersion":"3.5.0","uid":"REGEX_TOKENIZER_bc93b0d170c6","paramMap":{"maxLength":99999,"minLength":0,"caseSensitiveExceptions":true,"outputCol":"token","inputCols":["document"],"targetPattern":"\\S+"},"defaultParamMap":{"maxLength":99999,"minLength":0,"caseSensitiveExceptions":true,"outputCol":"token","inputCols":["document"],"targetPattern":"\\S+","lazyAnnotator":false}}
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/bert_onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14d2af9c6956ed07090dcb7663b1ba95f0721da09ba92b5d08f1af77f6d31d04
|
3 |
+
size 152122568
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/_SUCCESS
ADDED
File without changes
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00000
ADDED
Binary file (166 kB). View file
|
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00001
ADDED
Binary file (165 kB). View file
|
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00002
ADDED
Binary file (166 kB). View file
|
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00003
ADDED
Binary file (166 kB). View file
|
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00004
ADDED
Binary file (166 kB). View file
|
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00005
ADDED
Binary file (166 kB). View file
|
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00006
ADDED
Binary file (166 kB). View file
|
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/fields/vocabulary/part-00007
ADDED
Binary file (166 kB). View file
|
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/metadata/_SUCCESS
ADDED
File without changes
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/metadata/_committed_4031617553090561353
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"added":["part-00000-tid-4031617553090561353-9ae763c5-4ae4-41a4-bc41-0a6d28282a0c-313-1-c000.txt"],"removed":[]}
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/metadata/_started_4031617553090561353
ADDED
File without changes
|
classifierDL-bert-lang-detect/stages/2_BERT_EMBEDDINGS_69dd9fb1854f/metadata/part-00000-tid-4031617553090561353-9ae763c5-4ae4-41a4-bc41-0a6d28282a0c-313-1-c000.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"class":"com.johnsnowlabs.nlp.embeddings.BertEmbeddings","timestamp":1727274384268,"sparkVersion":"3.5.0","uid":"BERT_EMBEDDINGS_69dd9fb1854f","paramMap":{"dimension":768,"outputCol":"embeddings","caseSensitive":false,"storageRef":"small_bert_L2_768","inputCols":["document","token"],"engine":"onnx"},"defaultParamMap":{"dimension":768,"caseSensitive":false,"storageRef":"BERT_EMBEDDINGS_69dd9fb1854f","maxSentenceLength":128,"engine":"tensorflow","lazyAnnotator":false,"batchSize":8}}
|
classifierDL-bert-lang-detect/stages/3_SentenceEmbeddings_5f3b5483102a/metadata/_SUCCESS
ADDED
File without changes
|
classifierDL-bert-lang-detect/stages/3_SentenceEmbeddings_5f3b5483102a/metadata/_committed_3272538039056848776
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"added":["part-00000-tid-3272538039056848776-6af10195-5094-49e2-a0ad-e92bb8525b0a-322-1-c000.txt"],"removed":[]}
|
classifierDL-bert-lang-detect/stages/3_SentenceEmbeddings_5f3b5483102a/metadata/_started_3272538039056848776
ADDED
File without changes
|
classifierDL-bert-lang-detect/stages/3_SentenceEmbeddings_5f3b5483102a/metadata/part-00000-tid-3272538039056848776-6af10195-5094-49e2-a0ad-e92bb8525b0a-322-1-c000.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"class":"com.johnsnowlabs.nlp.embeddings.SentenceEmbeddings","timestamp":1727274387626,"sparkVersion":"3.5.0","uid":"SentenceEmbeddings_5f3b5483102a","paramMap":{"outputCol":"sentence_embeddings","storageRef":"small_bert_L2_768","poolingStrategy":"AVERAGE","inputCols":["document","embeddings"]},"defaultParamMap":{"dimension":100,"outputCol":"sentence_embeddings","poolingStrategy":"AVERAGE","storageRef":"SentenceEmbeddings_5f3b5483102a","inputCols":["document","word_embeddings"],"lazyAnnotator":false}}
|
classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/classifierdl_tensorflow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bcd8b7cea838731d7dfa5f1ee827386370f6eb2847660db33efb48a6f90e925
|
3 |
+
size 51639695
|
classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/_SUCCESS
ADDED
File without changes
|
classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00000
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00001
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00002
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00003
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00004
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00005
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00006
ADDED
Binary file (95 Bytes). View file
|
|
classifierDL-bert-lang-detect/stages/4_ClassifierDLModel_a78c9498f386/fields/datasetParams/part-00007
ADDED
Binary file (358 Bytes). View file
|
|