[Frontend] Support using chat template as custom score template for reranking models (#30550)
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com> Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io> Signed-off-by: wang.yuqi <noooop@126.com> Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
co-authored by
wang.yuqi
parent
27c6c2f98c
commit
23daef548d
@@ -488,6 +488,9 @@ _EMBEDDING_EXAMPLE_MODELS = {
|
||||
),
|
||||
"JambaForSequenceClassification": _HfExamplesInfo("ai21labs/Jamba-tiny-reward-dev"),
|
||||
"LlamaModel": _HfExamplesInfo("llama", is_available_online=False),
|
||||
"LlamaBidirectionalModel": _HfExamplesInfo(
|
||||
"nvidia/llama-nemotron-embed-1b-v2", trust_remote_code=True
|
||||
),
|
||||
"MistralModel": _HfExamplesInfo("intfloat/e5-mistral-7b-instruct"),
|
||||
"ModernBertModel": _HfExamplesInfo(
|
||||
"Alibaba-NLP/gte-modernbert-base", trust_remote_code=True
|
||||
@@ -554,6 +557,9 @@ _SEQUENCE_CLASSIFICATION_EXAMPLE_MODELS = {
|
||||
trust_remote_code=True,
|
||||
hf_overrides={"architectures": ["GteNewForSequenceClassification"]},
|
||||
),
|
||||
"LlamaBidirectionalForSequenceClassification": _HfExamplesInfo(
|
||||
"nvidia/llama-nemotron-rerank-1b-v2", trust_remote_code=True
|
||||
),
|
||||
"ModernBertForSequenceClassification": _HfExamplesInfo(
|
||||
"Alibaba-NLP/gte-reranker-modernbert-base"
|
||||
),
|
||||
|
||||
Reference in New Issue
Block a user