MichelRosselli/apertus

MichelRosselli/ apertus

2,014 Downloads Updated 4 months ago

Apertus is a 70B and 8B parameter language model designed to push the boundaries of fully-open multilingual and transparent models.

ollama run MichelRosselli/apertus

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

from ollama import chat

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

import ollama from 'ollama'

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

Models

View all →

Name

5 models

Size

Context

Input

apertus:latest

5.1GB · 64K context window · Text · 4 months ago

apertus:latest

5.1GB

64K

Text

apertus:8b-instruct-2509-q4_k_m

5.1GB · 64K context window · Text · 4 months ago

apertus:8b-instruct-2509-q4_k_m

5.1GB

64K

Text

apertus:8b-instruct-2509-bf16

16GB · 64K context window · Text · 4 months ago

apertus:8b-instruct-2509-bf16

16GB

64K

Text

apertus:70b-instruct-2509-q4_k_m

44GB · 64K context window · Text · 4 months ago

apertus:70b-instruct-2509-q4_k_m

44GB

64K

Text

apertus:70b-instruct-2509-bf16

141GB · 64K context window · Text · 4 months ago

apertus:70b-instruct-2509-bf16

141GB

64K

Text

Readme

Recommended Ollama version: >= v0.12.6-rc0

Disclaimer

⚠️ Important Notice: The current chat template provided for this model is temporary. As a result, the model may not yet fully demonstrate its potential in conversational tasks. The template will be updated in the future to improve usability and performance.