Comments (2)
"conversations": [
{
"from": "human",
"value": "查看人脸识别测试检测图片"
},
{
"from": "function_call",
"value": "{\"name\": \"search_ai_file\", \"arguments\": {\"case\": \"人脸识别测试检测\",\"type\": \"图片\"}}"
},
{
"from": "observation",
"value": "{\"answer\": \"success\"}"
},
{
"from": "gpt",
"value": "已成功查看。"
}
],
"tools": "[{\"name\": \"search_ai_file\", \"description\": \"查询AI平台案例的文件地址\", \"parameters\": {\"type\": \"object\", \"properties\": {\"case\": {\"type\": \"string\", \"description\": \"案例的名称\"},\"type\": {\"type\": \"string\", \"description\": \"查询文件的类型\"}}, \"required\": [\"case\",\"type\"]}},{\"name\": \"open_web\", \"description\": \"控制网页跳转\", \"parameters\": {\"type\": \"object\", \"properties\": {\"name\": {\"type\": \"string\", \"description\": \"网页的名称\"}}, \"required\": [\"name\"]}},{\"name\": \"refresh_web\", \"description\": \"更新网页信息\", \"parameters\": {\"type\": \"object\", \"properties\": {\"name\": {\"type\": \"string\", \"description\": \"网页的名称\"},\"data_name\": {\"type\": \"string\", \"description\": \"信息的名称\"}}, \"required\": [\"name\",\"data_name\"]}}]"
}
但是无法部署,想知道您这里的格式
from inference.
我使用快手开源的千问模型跑通了,貌似只要是react格式就行
from inference.
Related Issues (20)
- 增大 context length 原本能够运行的长度的对话也会触发 CUDA OOM
- Considering let the user specify the model path( from local machine ) or download repo( custom repo in hf or modelscope) for build-in model HOT 1
- 建议增加界面n_ctx参数配置。Qwen1.5-14B-Chat-GGUF模型默认小显存无法运行 HOT 1
- ENH: Support vllm params for UI
- 支持Lora模型加载
- BLD: Official CPU docker image
- BUG: Failed to launch qwe1.5-14b-GGUF using Xinferrence but works fine in pure llama_cpp python HOT 3
- BUG: Error when destroy generator in xoscar
- BUG: qwen1.5 gptq int8 errored HOT 2
- FEAT: Add a command / SDK interface to query which models are able to run on VLLM
- BUG请问我在安装pip install "xinference[all]"时出错 HOT 4
- 有docker部署embedding的示例吗 HOT 1
- Server error: 500 - [address=127.0.0.1:50182, pid=36312] [WinError None] 客户端没有所需的特权 HOT 1
- BUG: for windows cannot start with IP 0.0.0.0 HOT 17
- DOC: add how to contribute doc HOT 1
- 显存占用双倍异常 HOT 7
- max_tokens设置似乎出现异常
- BUG: Qwen1.5-chat 0.5B cannot be downloaded from modelscope
- QUESTION: 以xinference作为后台服务,不能同时多人进行提问 HOT 3
- 想问下如何对qwen1.5进行多机多卡批量推理
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from inference.