ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

use english prompt by default (#12115)

Browse source
This commit is contained in:
Shaojun Liu 2024-09-24 17:40:50 +08:00 committed by GitHub
parent 5d63aef60b
commit 657889e3e4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 8 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
docker/llm/serving/xpu/docker/vllm_online_benchmark.py
View file

@ -435,12 +435,14 @@ LLM_URLS = [f"http://localhost:{PORT}/v1/completions" for PORT in [8000]]
MODEL = "/llm/models/" + model_name MODEL = "/llm/models/" + model_name
MAX_TOKENS = output_length # 修改 MAX_TOKENS 为 output_length MAX_TOKENS = output_length # 修改 MAX_TOKENS 为 output_length
if "Qwen" not in MODEL and "chatglm" not in MODEL: # if "Qwen" not in MODEL and "chatglm" not in MODEL:
# print("using Llama PROMPT") # print("using Llama PROMPT")
PROMPT = ENGLISH_PROMPT # PROMPT = ENGLISH_PROMPT
else: # else:
# print("using Qwen/chatglm PROMPT") # print("using Qwen/chatglm PROMPT")
PROMPT = CHINESE_PROMPT # PROMPT = CHINESE_PROMPT
PROMPT = ENGLISH_PROMPT
# 加载模型的 tokenizer # 加载模型的 tokenizer
from transformers import AutoTokenizer from transformers import AutoTokenizer