summaryrefslogtreecommitdiffstats
path: root/config-model/src/main/resources/schema/common.rnc
diff options
context:
space:
mode:
authorBjørn Christian Seime <bjorncs@yahooinc.com>2023-06-12 16:41:37 +0200
committerBjørn Christian Seime <bjorncs@yahooinc.com>2023-06-12 16:51:26 +0200
commit4f722322cc9f8df5146ffb27d74239b3b4f2d634 (patch)
treedad0f0a70513a861844d10a35ba93c1901b48057 /config-model/src/main/resources/schema/common.rnc
parent838f918baf2f64b5cb737a59e624f20773d95baa (diff)
Prefer truncation configuration from tokenizer model
Only override truncation if not specified or max length exceeds max tokens accepted by model. Use JNI wrapper directly to determine existing truncation configuration (JSON format is not really documented). Simply configuration for pure tokenizer embedder. Disable DJL usage telemetry.
Diffstat (limited to 'config-model/src/main/resources/schema/common.rnc')
-rw-r--r--config-model/src/main/resources/schema/common.rnc8
1 files changed, 2 insertions, 6 deletions
diff --git a/config-model/src/main/resources/schema/common.rnc b/config-model/src/main/resources/schema/common.rnc
index e130bed0297..ba7e2b6674e 100644
--- a/config-model/src/main/resources/schema/common.rnc
+++ b/config-model/src/main/resources/schema/common.rnc
@@ -88,7 +88,7 @@ HuggingFaceEmbedder =
attribute type { "hugging-face-embedder" } &
element transformer-model { ModelReference } &
element tokenizer-model { ModelReference }? &
- element max-tokens { xsd:nonNegativeInteger }? &
+ element max-tokens { xsd:positiveInteger }? &
element transformer-input-ids { xsd:string }? &
element transformer-attention-mask { xsd:string }? &
element transformer-token-type-ids { xsd:string }? &
@@ -99,11 +99,7 @@ HuggingFaceEmbedder =
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 }? &
- element padding { xsd:boolean }?
+ element model { attribute language { xsd:string }? & ModelReference }+
BertBaseEmbedder =
attribute type { "bert-embedder" } &