biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Support BERTModel (first encoder-only embedding model) (#9056)

Browse Source 
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Andrew Feldman <afeldman@neuralmagic.com>
Co-authored-by: afeldman-nm <156691304+afeldman-nm@users.noreply.github.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: laishzh <laishengzhang@gmail.com>
Co-authored-by: Max de Bayser <maxdebayser@gmail.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Robert Shaw
2024-10-17 19:21:01 -04:00
committed by GitHub
parent bb76538bbd
commit 343f8e0905
6 changed files with 497 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/model_executor/models/registry.py
View File

@@ -87,6 +87,7 @@ _TEXT_GENERATION_MODELS = {
_EMBEDDING_MODELS = {
# [Text-only]
"BertModel": ("bert", "BertEmbeddingModel"),
"Gemma2Model": ("gemma2", "Gemma2EmbeddingModel"),
"MistralModel": ("llama", "LlamaEmbeddingModel"),
"Qwen2ForRewardModel": ("qwen2_rm", "Qwen2ForRewardModel"),