Comments (2)
建议调用工具使用RESTful API:
https://inference.readthedocs.io/en/latest/user_guide/client_api.html#openai-client-tool-calls
https://github.com/xorbitsai/inference/blob/main/examples/FunctionCall.ipynb
如果一定要改chat_interface.py的话,当stream is False时,model.chat返回的是一个completion result,并不是一个迭代器了。build_chat_vl_interface使用的就不是stream模式,具体可以参考:https://github.com/xorbitsai/inference/blob/main/xinference/core/chat_interface.py#L199
from inference.
如果有疑问,可以再打开这个issue。
from inference.
Related Issues (20)
- docker image need install flash-attn HOT 2
- 能不能指定gpu运行? HOT 1
- 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
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.