ByteDance-Seed

/

Seed-X-PPO-7B

Like 303

Follow

ByteDance Seed 3.71k

system info

key	value
transformers version	4.51.3
PyTorch version	2.6.0
vllm version	0.8.0
GPU	4090*1

Reproduction

I tried running this model, but the output was always staged and displayed as a length stage, but there was no problem with the configuration.

config

python3 -m vllm.entrypoints.openai.api_server --max_model_len 4096 --served-model-name seed-x --model /data/models/Seed-X-PPO-7B

I noticed the API response returned a finish_reason of length. Could you please share the code snippet for the request? I’d like to check the configuration, especially for parameters like max_tokens

system info

key	value
transformers version	4.51.3
PyTorch version	2.6.0
vllm version	0.8.0
GPU	4090*1

Reproduction

I tried running this model, but the output was always staged and displayed as a length stage, but there was no problem with the configuration.

config

python3 -m vllm.entrypoints.openai.api_server --max_model_len 4096 --served-model-name seed-x --model /data/models/Seed-X-PPO-7B

I noticed the API response returned a finish_reason of length. Could you please share the code snippet for the request? I’d like to check the configuration, especially for parameters like max_tokens

Thank

You can include max_token in your request，such as
{
"model": "xx",
"prompt": "",
"max_tokens": 512
}