XiXiChat_base_14b-GGUF

XiXiChat

Introduction

In Agriculture, several LLMs have been proposed. However, It is a challenging task to make large models simultaneously generalistically recognizable and highly specialized in knowledge. To achieve this goal, our lab tries to design XiXiChat, a doman-specific agriculture large language model, to handle the specialized questions in root crops domain. XiXiChat-14b-Beta has a 14 billion parameter base model and a short Q&A chat model tailored for agricultural scenarios. The current beta version is trained by around specific 50,000 Q&A data.

model configuration

Install Ollama

Run the following command to install Ollama:

curl -fsSL https://ollama.com/install.sh | sh

Open a command prompt and enter ollama --version to verify that the installation was successful.

Download model

Open dreamMaker34/XiXiChat_base_14b-GGUF · Hugging Face, and download XiXiChat_base_14b.gguf locally.

Import model

Write a configuration file named Modelfile:

FROM ./XiXiChat_base_14b.gguf
TEMPLATE """[INST] {{ if .System }}<<SYS>>{{ .System }}<</SYS>>
{{ end }}{{ .Prompt }} [/INST] """

Then, import the model using the following command:

ollama create XiXiChat -f ./Modelfile

After successful import, you can use the list command to view:

$ ollama list
NAME            ID              SIZE    MODIFIED
XiXiChat:latest 0c2168345913    15 GB   18 hours ago

Build a Web environment

Install docker

The installation of docker can be found in this blog post:

https://blog.csdn.net/m82_a1/article/details/98870376

After docker was installed, please start the docker service：

sudo service docker start

Start WebUI

docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main

After that, you can access WebUI and use our model at http://localhost:8080.