hyperclovax commited on
Commit
dab48f7
·
verified ·
1 Parent(s): 397c365

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -564,7 +564,7 @@ The HyperCLOVA X SEED Think model is built on a custom LLM architecture based on
564
  After downloading the model checkpoint to a local path (`/path/to/hyperclova-x-seed-think-14b`), you can perform text inference by running the following commands on a GPU environment with A100 or higher.
565
 
566
  ```bash
567
- python -m vllm.entrypoints.api_server --model=/path/to/hyperclova-x-seed-think-14b --trust_remote_code --port=8000
568
 
569
  curl http://localhost:8000/v1/completions \
570
  -H "Content-Type: application/json" \
 
564
  After downloading the model checkpoint to a local path (`/path/to/hyperclova-x-seed-think-14b`), you can perform text inference by running the following commands on a GPU environment with A100 or higher.
565
 
566
  ```bash
567
+ python -m vllm.entrypoints.openai.api_server --model=/path/to/hyperclova-x-seed-think-14b --trust_remote_code --port=8000
568
 
569
  curl http://localhost:8000/v1/completions \
570
  -H "Content-Type: application/json" \