wizardlm2

597.7K Downloads Updated 1 year ago

State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.

7b 8x22b

ollama run wizardlm2

curl http://localhost:11434/api/chat \
  -d '{
    "model": "wizardlm2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='wizardlm2',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'wizardlm2',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

22 models

Size

Context

Input

wizardlm2:latest

4.1GB · 32K context window · Text · 1 year ago

wizardlm2:latest

4.1GB

32K

Text

wizardlm2:7b

latest

4.1GB · 32K context window · Text · 1 year ago

wizardlm2:7b latest

4.1GB

32K

Text

wizardlm2:8x22b

80GB · 64K context window · Text · 1 year ago

wizardlm2:8x22b

80GB

64K

Text

Readme

WizardLM-2 is a next generation state-of-the-art large language model with improved performance on complex chat, multilingual, reasoning and agent use cases. This family includes three cutting-edge models:

wizardlm2:7b: fastest model, comparable performance with 10x larger open-source models.
wizardlm2:8x22b: the most advanced model, and the best opensource LLM in Microsoft’s internal evaluation on highly complex tasks.
wizardlm2:70b: model with top-tier reasoning capabilities for its size (coming soon)

References

Blog Post

HuggingFace