mikepfunk28/deepseekq3

mikepfunk28/ deepseekq3_coder

509 Downloads Updated 10 months ago

Added system prompt to deepseek's new 8B model with Qwen 3, potentially could help, also kept context large as well as temp strict.

tools thinking

ollama run mikepfunk28/deepseekq3_coder

curl http://localhost:11434/api/chat \
  -d '{
    "model": "mikepfunk28/deepseekq3_coder",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='mikepfunk28/deepseekq3_coder',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'mikepfunk28/deepseekq3_coder',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)