[Model] Add LlamaEmbeddingModel as an embedding Implementation of LlamaModel (#9806)

ac3d748d · Junichi Sato · GitHub · 0ce7798f · ac3d748d
Unverified Commit ac3d748d authored Oct 30, 2024 by Junichi Sato Committed by GitHub Oct 29, 2024
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 0 deletions

vllm/model_executor/models/registry.py vllm/model_executor/models/registry.py +1 -0

No files found.
--- a/vllm/model_executor/models/registry.py
+++ b/vllm/model_executor/models/registry.py
@@ -95,6 +95,7 @@ _EMBEDDING_MODELS = {
    # [Text-only]
    "BertModel": ("bert", "BertEmbeddingModel"),
    "Gemma2Model": ("gemma2", "Gemma2EmbeddingModel"),
+    "LlamaModel": ("llama", "LlamaEmbeddingModel"),
    "MistralModel": ("llama", "LlamaEmbeddingModel"),
    "Qwen2ForRewardModel": ("qwen2_rm", "Qwen2ForRewardModel"),
    "Qwen2ForSequenceClassification": (