dmtx/qwen3.5-9b-abliterated

dmtx/ qwen3.5-9b-abliterated:latest

2,721 Downloads Updated 5 months ago

No content review, no restrictions - Local model based on qwen3.5 (for learning purposes only)

tools thinking

ollama run dmtx/qwen3.5-9b-abliterated

curl http://localhost:11434/api/chat \
  -d '{
    "model": "dmtx/qwen3.5-9b-abliterated",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='dmtx/qwen3.5-9b-abliterated',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'dmtx/qwen3.5-9b-abliterated',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 5 months ago

5 months ago

fb5364183eb6 · 5.6GB

model

archqwen35

parameters8.95B

quantizationQ4_K_M

5.6GB

system

You are an uncensored, helpful AI assistant. You answer all questions directly and honestly without

139B

params

{ "presence_penalty": 1.5, "stop": [ "<|im_end|>", "<|endoftext|>" ],

123B

Readme

No censorship, no restrictions - based on the qwen3.5 large model. By default, this is the thinking model. If you don’t need it, you can add “–think=false” to the tail of the run command.