From a3321b37773fe969652d37e5b3b26d07bfddd259 Mon Sep 17 00:00:00 2001 From: Bjørn Christian Seime Date: Mon, 5 Jun 2023 15:32:23 +0200 Subject: Add typed component definition for Bert embedder --- config-model/src/main/resources/schema/common.rnc | 29 ++++++++++++++++++----- 1 file changed, 23 insertions(+), 6 deletions(-) (limited to 'config-model/src/main/resources/schema') diff --git a/config-model/src/main/resources/schema/common.rnc b/config-model/src/main/resources/schema/common.rnc index 4e7cb526efb..b2b71950a0c 100644 --- a/config-model/src/main/resources/schema/common.rnc +++ b/config-model/src/main/resources/schema/common.rnc @@ -80,7 +80,7 @@ ComponentDefinition = TypedComponentDefinition = attribute id { xsd:Name } & - (HuggingFaceEmbedder | HuggingFaceTokenizer) & + (HuggingFaceEmbedder | HuggingFaceTokenizer | BertBaseEmbedder) & GenericConfig* & Component* @@ -94,14 +94,31 @@ HuggingFaceEmbedder = element transformer-token-type-ids { xsd:string }? & element transformer-output { xsd:string }? & element normalize { xsd:boolean }? & - element onnx-execution-mode { "parallel" | "sequential" }? & - element onnx-interop-threads { xsd:integer }? & - element onnx-intraop-threads { xsd:integer }? & - element onnx-gpu-device { xsd:integer }? + OnnxModelExecutionParams HuggingFaceTokenizer = attribute type { "hugging-face-tokenizer" } & element model { attribute language { xsd:string }? & ModelReference }+ & element special-tokens { xsd:boolean }? & element max-length { xsd:integer }? & - element truncation { xsd:boolean }? \ No newline at end of file + element truncation { xsd:boolean }? + +BertBaseEmbedder = + attribute type { "bert-embedder" } & + element transformer-model { ModelReference } & + element tokenizer-vocab { ModelReference } & + element max-tokens { xsd:nonNegativeInteger }? & + element pooling-strategy { "cls" | "mean" }? & + element transformer-input-ids { xsd:string }? & + element transformer-attention-mask { xsd:string }? & + element transformer-token-type-ids { xsd:string }? & + element transformer-output { xsd:string }? & + element transformer-start-sequence-token { xsd:integer }? & + element transformer-end-sequence-token { xsd:integer }? & + OnnxModelExecutionParams + +OnnxModelExecutionParams = + element onnx-execution-mode { "parallel" | "sequential" }? & + element onnx-interop-threads { xsd:integer }? & + element onnx-intraop-threads { xsd:integer }? & + element onnx-gpu-device { xsd:integer }? \ No newline at end of file -- cgit v1.2.3