[ML] add roberta/bart docs (#85001)

adds roberta section to NLP tokenization documentation.

docs/reference/ingest/processors/inference.asciidoc

@@ -94,7 +94,20 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+=======
+
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+=======
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
 
 `mpnet`::::
@@ -107,7 +120,7 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
 =====
 
@@ -136,7 +149,20 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+=======
+
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+=======
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
 
 `mpnet`::::
@@ -149,7 +175,7 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
 =====
 
@@ -199,11 +225,28 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 
 `span`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-span]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+=======
+
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+=======
+
+`span`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
 
 `mpnet`::::
@@ -216,7 +259,7 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
 =====
 
@@ -245,7 +288,20 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+=======
+
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+=======
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
 
 `mpnet`::::
@@ -258,7 +314,7 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
 =====
 
@@ -295,7 +351,20 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+=======
+
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+=======
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
 
 `mpnet`::::
@@ -308,7 +377,7 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
 =====
 

docs/reference/ml/ml-shared.asciidoc

@@ -939,6 +939,7 @@ values are
 --
 * `bert`: Use for BERT-style models
 * `mpnet`: Use for MPNet-style models
+* `roberta`: Use for RoBERTa-style and BART-style models
 --
 end::inference-config-nlp-tokenization[]
 
@@ -946,12 +947,12 @@ tag::inference-config-nlp-tokenization-bert[]
 BERT-style tokenization is to be performed with the enclosed settings.
 end::inference-config-nlp-tokenization-bert[]
 
-tag::inference-config-nlp-tokenization-bert-do-lower-case[]
+tag::inference-config-nlp-tokenization-do-lower-case[]
 Specifies if the tokenization lower case the text sequence when building the
 tokens.
-end::inference-config-nlp-tokenization-bert-do-lower-case[]
+end::inference-config-nlp-tokenization-do-lower-case[]
 
-tag::inference-config-nlp-tokenization-bert-span[]
+tag::inference-config-nlp-tokenization-span[]
 When `truncate` is `none`, you can partition longer text sequences
 for inference. The value indicates how many tokens overlap between each
 subsequence.
@@ -960,9 +961,9 @@ The default value is `-1`, indicating no windowing or spanning occurs.
 +
 NOTE: When your typical input is just slightly larger than `max_sequence_length`, it may be best to simply truncate;
 there will be very little information in the second subsequence.
-end::inference-config-nlp-tokenization-bert-span[]
+end::inference-config-nlp-tokenization-span[]
 
-tag::inference-config-nlp-tokenization-bert-truncate[]
+tag::inference-config-nlp-tokenization-truncate[]
 Indicates how tokens are truncated when they exceed `max_sequence_length`.
 The default value is `first`.
 +
@@ -976,7 +977,7 @@ The default value is `first`.
 NOTE: For `zero_shot_classification`, the hypothesis sequence is always the second
 sequence. Therefore, do not use `second` in this case.
 
-end::inference-config-nlp-tokenization-bert-truncate[]
+end::inference-config-nlp-tokenization-truncate[]
 
 tag::inference-config-nlp-tokenization-bert-with-special-tokens[]
 Tokenize with special tokens. The tokens typically included in BERT-style tokenization are:
@@ -987,10 +988,26 @@ Tokenize with special tokens. The tokens typically included in BERT-style tokeni
 --
 end::inference-config-nlp-tokenization-bert-with-special-tokens[]
 
-tag::inference-config-nlp-tokenization-bert-max-sequence-length[]
+tag::inference-config-nlp-tokenization-max-sequence-length[]
 Specifies the maximum number of tokens allowed to be output by the tokenizer.
-The default for BERT-style tokenization is `512`.
-end::inference-config-nlp-tokenization-bert-max-sequence-length[]
+end::inference-config-nlp-tokenization-max-sequence-length[]
+
+tag::inference-config-nlp-tokenization-roberta[]
+RoBERTa-style tokenization is to be performed with the enclosed settings.
+end::inference-config-nlp-tokenization-roberta[]
+
+tag::inference-config-nlp-tokenization-roberta-add-prefix-space[]
+Specifies if the tokenization should prefix a space to the tokenized input to the model.
+end::inference-config-nlp-tokenization-roberta-add-prefix-space[]
+
+tag::inference-config-nlp-tokenization-roberta-with-special-tokens[]
+Tokenize with special tokens. The tokens typically included in RoBERTa-style tokenization are:
++
+--
+* `<s>`: The first token of the sequence being classified.
+* `</s>`: Indicates sequence separation.
+--
+end::inference-config-nlp-tokenization-roberta-with-special-tokens[]
 
 tag::inference-config-nlp-tokenization-mpnet[]
 MPNet-style tokenization is to be performed with the enclosed settings.

docs/reference/ml/trained-models/apis/get-trained-models.asciidoc

@@ -188,20 +188,43 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 ========
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+========
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+========
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -211,15 +234,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
@@ -269,20 +292,43 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 ========
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+========
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+========
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -292,15 +338,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
@@ -343,20 +389,43 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 ========
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+========
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+========
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -366,15 +435,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
@@ -440,24 +509,51 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `span`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-span]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 ========
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+========
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`span`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+========
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -467,19 +563,19 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `span`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-span]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
@@ -522,20 +618,43 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 ========
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+========
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+========
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -545,15 +664,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
@@ -611,20 +730,43 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 ========
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+========
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+========
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -634,15 +776,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 ========
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)

docs/reference/ml/trained-models/apis/put-trained-model-vocabulary.asciidoc

@@ -45,10 +45,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=model-id]
 (array)
 The model vocabulary. Must not be empty.
 
+`merges`::
+(Optional, array)
+The model merges used in byte-pair encoding. The merges must be sub-token pairs, space delimited, and in order of
+preference. Example: ["f o", "fo o"]. Must be provided for RoBERTa and BART style models.
+
 [[ml-put-trained-model-vocabulary-example]]
 == {api-examples-title}
 
-The following example shows how to create a model vocabulary for a 
+The following example shows how to create a model vocabulary for a
 previously stored trained model configuration.
 
 [source,js]
@@ -71,4 +76,4 @@ The API returns the following results:
 {
     "acknowledged": true
 }
-----
+----

docs/reference/ml/trained-models/apis/put-trained-models.asciidoc

@@ -443,20 +443,43 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 =======
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+=======
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+=======
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -466,15 +489,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
@@ -512,20 +535,43 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 =======
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+=======
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+=======
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -535,15 +581,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
@@ -575,20 +621,43 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 =======
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+=======
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+=======
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -598,15 +667,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
@@ -661,24 +730,51 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `span`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-span]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 =======
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+=======
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`span`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+=======
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -688,15 +784,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
@@ -727,20 +823,43 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 =======
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+=======
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+=======
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -750,15 +869,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
@@ -805,20 +924,43 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-with-special-tokens]
 =======
+`roberta`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta]
++
+.Properties of roberta
+[%collapsible%open]
+=======
+`add_prefix_space`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-add-prefix-space]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
+=======
 `mpnet`::::
 (Optional, object)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-mpnet]
@@ -828,15 +970,15 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 =======
 `do_lower_case`::::
 (Optional, boolean)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-do-lower-case]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
 
 `max_sequence_length`::::
 (Optional, integer)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-max-sequence-length]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
 
 `truncate`::::
 (Optional, string)
-include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-truncate]
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 
 `with_special_tokens`::::
 (Optional, boolean)