gguf/DeepSeek-Janus-Pro-7B:IQ4

gguf/ DeepSeek-Janus-Pro-7B:IQ4_XS

5,555 Downloads Updated 12 months ago

Ollama models of DeepSeek Janus Pro 7B

ollama run gguf/DeepSeek-Janus-Pro-7B:IQ4_XS

curl http://localhost:11434/api/chat \
  -d '{
    "model": "gguf/DeepSeek-Janus-Pro-7B:IQ4_XS",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='gguf/DeepSeek-Janus-Pro-7B:IQ4_XS',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'gguf/DeepSeek-Janus-Pro-7B:IQ4_XS',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 12 months ago

12 months ago

492248e73d25 · 3.8GB ·

model

archllama

parameters6.91B

quantizationIQ1_M

3.8GB

Readme

Reference: https://huggingface.co/mradermacher/Janus-Pro-7B-LM-GGUF

The “latest” tag is a copy of the type “Q4_K_M”