rhundt/qwen3-64k

rhundt/ qwen3-64k

110 Downloads Updated 11 months ago

qwen3 with YaRN RoPE scaling to 64k context (factor 2)

tools 30b

ollama run rhundt/qwen3-64k:30b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "rhundt/qwen3-64k:30b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='rhundt/qwen3-64k:30b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'rhundt/qwen3-64k:30b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)