Create a trained model vocabulary
Generally available; Added in 8.0.0
This API is supported only for natural language processing (NLP) models.
The vocabulary is stored in the index as described in inference_config.*.vocabulary
of the trained model definition.
Required authorization
- Cluster privileges:
manage_ml
Path parameters
-
model_id
string Required The unique identifier of the trained model.
Body
Required
-
vocabulary
array[string] Required The model vocabulary, which must not be empty.
-
merges
array[string] Generally available; Added in 8.2.0 The optional model merges if required by the tokenizer.
-
scores
array[number] Generally available; Added in 8.9.0 The optional vocabulary value scores if required by the tokenizer.
PUT
/_ml/trained_models/{model_id}/vocabulary
Console
PUT _ml/trained_models/elastic__distilbert-base-uncased-finetuned-conll03-english/vocabulary
{
"vocabulary": [
"[PAD]",
"[unused0]",
...
]
}
curl \
--request PUT 'http://api.example.com/_ml/trained_models/{model_id}/vocabulary' \
--header "Authorization: $API_KEY" \
--header "Content-Type: application/json" \
--data '"{\n \"vocabulary\": [\n \"[PAD]\",\n \"[unused0]\",\n ...\n ]\n}"'
Request example
An example body for a `PUT _ml/trained_models/elastic__distilbert-base-uncased-finetuned-conll03-english/vocabulary` request.
{
"vocabulary": [
"[PAD]",
"[unused0]",
...
]
}