一个路过的程序员

Cannot import name 'load_dataset' from .... module ‘datasets’

2

### Describe the bug use python -m pip install datasets to install ### Steps to reproduce the bug from datasets import load_dataset ### Expected behavior it doesn't work ### Environment...

where is python documentation? I confuse a parameter about index.search?

1

In the code prompt, the input parameters of index.search are n, x, k and others. I saw that the input parameters in some tutorials directly write index.search(xq, k), but the...

### Describe your problem How do I want to deploy this on a machine with no network communication and no access to external docker images? After installing the environment manually,...

### Describe your problem Inside two issues I saw something related to support for custom large models One of them says to start it with ollma The other says to...

Is it possible to start with fastchat and then wrap the interface with fastapi to become like ollama?

1

Since Ollama supports more than 30 models, but doesn't have the one I need, and in addition, having already deployed another application using fastchat, can I encapsulate the interface and...

How do I call a model deployed using fastchat?

1

### Describe your problem Reading the related issue, it says to use ollama to start a local model, but `https://ollama.com/library` doesn't support ChatGLM,or needs a lot of work to support...

I started a chatglm3-32k using xinference's ui interface. what is his model uid?

My server is offline. After I started it, I tried to start the chatglm3-32k model, he ran it and then reported an error that the download failed, which is of...

### Describe your problem cuda 11.7 Does this project come with an embedding model? If it doesn't come with an embedding model, how do I start it? If it does...

### Describe your problem I started chatglm3-32k via xinference, then clicked inside xinference add model inside ragflow and entered {model category -> chat, model uid -> THUDM/chatglm3-6b-32k, base url ->...