A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 04:45 UTC
[Docs] Add GPT2ForSequenceClassification to supported models in docs (#19932)
Signed-off-by: nie3e <adrcwiek@gmail.com>
Adrian committed
Jun 21, 2025 at 22:57 UTC
3b1e4c6a23af94b76f7e1290ec48d671f1420d8d
1 file changed
+1
-1
docs/models/supported_models.md
+1
-1
@@ -445,7 +445,7 @@ Specified using `--task classify`.
445
| Architecture | Models | Example HF Models | [LoRA][lora-adapter] | [PP][distributed-serving] | [V1](gh-issue:8779) |
446
|----------------------------------|----------|----------------------------------------|------------------------|-----------------------------|-----------------------|
447
| `JambaForSequenceClassification` | Jamba | `ai21labs/Jamba-tiny-reward-dev`, etc. | ✅︎ | ✅︎ | |
448
-
448
+| `GPT2ForSequenceClassification` | GPT2 | `nie3e/sentiment-polish-gpt2-small` | | | |
449
If your model is not in the above list, we will try to automatically convert the model using
450
[as_classification_model][vllm.model_executor.models.adapters.as_classification_model]. By default, the class probabilities are extracted from the softmaxed hidden state corresponding to the last token.
451