sroecker/merlinite:Q8

sroecker/ merlinite:Q8_0

116 Downloads Updated 2 years ago

A Mistral 7B derivative trained using LAB

ollama run sroecker/merlinite:Q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "sroecker/merlinite:Q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='sroecker/merlinite:Q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'sroecker/merlinite:Q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 years ago

2 years ago

e557129d0484 · 7.7GB ·

model

archllama

parameters7.24B

quantizationQ8_0

7.7GB

template

{{ if .System }} <|system|> {{ .System }} {{ end }}{{ if .Prompt }} <|user|> {{ .Prompt }}{{ end }}

114B

system

You are an AI language model developed by IBM Research. You are a cautious assistant. You carefully

214B

license

545B

params

{ "stop": [ "<|endoftext|>" ] }

37B

Readme

Quantized versions of Merlinite-7B, a Mistral-7b-derivative model trained with the LAB methodology by IBM Research, using Mixtral-8x7b-Instruct as a teacher model. For more info see here.