wangrongsheng/mistral-7b-v0.3-chinese

wangrongsheng/ mistral-7b-v0.3-chinese:latest

808 Downloads Updated 1 year ago

Mistral-7B-v0.3-Chinese is an instruction-tuned language model for Chinese & English users with various abilities such as roleplaying & tool-using built upon the Mistral-7B-Instruct-v0.3.

ollama run wangrongsheng/mistral-7b-v0.3-chinese

curl http://localhost:11434/api/chat \
  -d '{
    "model": "wangrongsheng/mistral-7b-v0.3-chinese",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='wangrongsheng/mistral-7b-v0.3-chinese',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'wangrongsheng/mistral-7b-v0.3-chinese',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

5cdf811480ee · 4.1GB ·

model

archllama

parameters7.25B

quantizationQ4_0

4.1GB

system

你是一个有用的助手

27B

params

{ "stop": [ "[INST]", "[/INST]" ] }

30B

template

[INST] {{ if .System }}{{ .System }} {{ end }}{{ .Prompt }} [/INST]

69B

Readme

Mistral-7B-v0.3-Chinese-Chat is an instruction-tuned language model for Chinese & English users with various abilities such as roleplaying & tool-using built upon the Mistral-7B-Instruct-v0.3. The model based on the Mistral-7B-v0.3-Chinese-Chat-4bit.