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

[New Model]: Support GteNewModelForSequenceClassification (#23524)

Browse Source 
Signed-off-by: wang.yuqi <noooop@126.com>
This commit is contained in:
wang.yuqi
2025-08-28 15:36:42 +08:00
committed by GitHub
parent 186aced5ff
commit 11a7fafaa8
13 changed files with 157 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/models/supported_models.md
View File

@@ -497,6 +497,7 @@ These models primarily support the [`LLM.score`](./pooling_models.md#llmscore) A
|--------------|--------|-------------------|----------------------|---------------------------|---------------------|
| `BertForSequenceClassification` | BERT-based | `cross-encoder/ms-marco-MiniLM-L-6-v2`, etc. | | | ✅︎ |
| `GemmaForSequenceClassification` | Gemma-based | `BAAI/bge-reranker-v2-gemma` (see note), etc. | ✅︎ | ✅︎ | ✅︎ |
| `GteNewForSequenceClassification` | mGTE-TRM (see note) | `Alibaba-NLP/gte-multilingual-reranker-base`, etc. | | | ✅︎ |
| `Qwen2ForSequenceClassification` | Qwen2-based | `mixedbread-ai/mxbai-rerank-base-v2` (see note), etc. | ✅︎ | ✅︎ | ✅︎ |
| `Qwen3ForSequenceClassification` | Qwen3-based | `tomaarsen/Qwen3-Reranker-0.6B-seq-cls`, `Qwen/Qwen3-Reranker-0.6B` (see note), etc. | ✅︎ | ✅︎ | ✅︎ |
| `RobertaForSequenceClassification` | RoBERTa-based | `cross-encoder/quora-roberta-base`, etc. | | | ✅︎ |
@@ -513,6 +514,9 @@ These models primarily support the [`LLM.score`](./pooling_models.md#llmscore) A
vllm serve BAAI/bge-reranker-v2-gemma --hf_overrides '{"architectures": ["GemmaForSequenceClassification"],"classifier_from_token": ["Yes"],"method": "no_post_processing"}'
```
!!! note
The second-generation GTE model (mGTE-TRM) is named `NewForSequenceClassification`. The name `NewForSequenceClassification` is too generic, you should set `--hf-overrides '{"architectures": ["GteNewForSequenceClassification"]}'` to specify the use of the `GteNewForSequenceClassification` architecture.
!!! note
Load the official original `mxbai-rerank-v2` by using the following command.