mikepfunk28/deepseek8b

mikepfunk28/ deepseek8b_qwen3

103 Downloads Updated 7 months ago

Using 4096 tokens for flash attention context window to work as intended. Trying a new template and system prompt to see how it reacts.

tools

ollama run mikepfunk28/deepseek8b_qwen3

curl http://localhost:11434/api/chat \
  -d '{
    "model": "mikepfunk28/deepseek8b_qwen3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='mikepfunk28/deepseek8b_qwen3',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'mikepfunk28/deepseek8b_qwen3',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)