exaone-deep

426.9K Downloads Updated 10 months ago

EXAONE Deep exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research.

2.4b 7.8b 32b

ollama run exaone-deep

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

from ollama import chat

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

import ollama from 'ollama'

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

Models

View all →

Name

13 models

Size

Context

Input

exaone-deep:latest

4.8GB · 32K context window · Text · 10 months ago

exaone-deep:latest

4.8GB

32K

Text

exaone-deep:2.4b

1.6GB · 32K context window · Text · 10 months ago

exaone-deep:2.4b

1.6GB

32K

Text

exaone-deep:7.8b

latest

4.8GB · 32K context window · Text · 10 months ago

exaone-deep:7.8b latest

4.8GB

32K

Text

exaone-deep:32b

19GB · 32K context window · Text · 10 months ago

exaone-deep:32b

19GB

32K

Text

Readme

EXAONE Deep exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research.

Evaluation results show that:

EXAONE Deep 2.4B outperforms other models of comparable size
EXAONE Deep 7.8B outperforms not only open-weight models of comparable scale but also a proprietary reasoning model OpenAI o1-mini
EXAONE Deep 32B demonstrates competitive performance against leading open-weight models.

References

Hugging Face