华为计算微信公众号
昇腾AI开发者公众号
华为计算微博
华为计算今日头条
如何一次性请求多个prompts，目前已经跑通单次prompt请求。如下：
修改服务器配置：
cd /usr/local/Ascend/mindie/latest/mindie-service/ vim ./conf/config.json #【修改模型权重、卡数、NPU ID等关键配置参数】
启动服务器
cd /usr/local/Ascend/mindie/latest/mindie-service/ ./bin/mindieservice_daemon
启动成功后显示 "Daemon start success!"
curl -H "Accept: application/json" -H "Content-type: application/json" -X POST -d '{ "model": "Qwen2-72B-Instruct", "messages": [{ "role": "system", "content": "You are a student who is good at math." }, { "role": "user", "content": "你好?" } ], "max_tokens": 20, "presence_penalty": 1.03, "frequency_penalty": 1.0, "seed": null, "temperature": 0.5, "top_p": 0.95, "stream": false }' http://127.0.0.1:1025/v1/chat/completions
我要发帖子
点赞
收藏
回复
分享
举报
已解决 已解决
如何一次性请求多个prompts，目前已经跑通单次prompt请求。如下：
（1）Server启动
修改服务器配置：
启动服务器
启动成功后显示 "Daemon start success!"
（2）Client发起请求
curl -H "Accept: application/json" -H "Content-type: application/json" -X POST -d '{ "model": "Qwen2-72B-Instruct", "messages": [{ "role": "system", "content": "You are a student who is good at math." }, { "role": "user", "content": "你好?" } ], "max_tokens": 20, "presence_penalty": 1.03, "frequency_penalty": 1.0, "seed": null, "temperature": 0.5, "top_p": 0.95, "stream": false }' http://127.0.0.1:1025/v1/chat/completions