R4C3R/qwen2.5-1.5b-heretic:q8

R4C3R/ qwen2.5-1.5b-heretic:q8_0

12 Downloads Updated 16 hours ago

A decensored 1.5B model with strong instruction-following and suppressed refusal behavior.

tools

ollama run R4C3R/qwen2.5-1.5b-heretic:q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "R4C3R/qwen2.5-1.5b-heretic:q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='R4C3R/qwen2.5-1.5b-heretic:q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'R4C3R/qwen2.5-1.5b-heretic:q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 17 hours ago

17 hours ago

5d5a1de92566 · 1.6GB ·

model

archqwen2

parameters1.54B

quantizationQ8_0

1.6GB

Readme

Qwen2.5-1.5B-Instruct-heretic is a decensored variant of Qwen2.5-1.5B-Instruct produced with Heretic v1.4.0. Refusal behavior is suppressed via targeted weight edits rather than fine-tuning, so the base model’s knowledge and instruction-following are preserved.

Sizes

1.5B (default)

General-purpose small language model with strong instruction-following capabilities.

ollama run R4C3R/qwen2.5-1.5b-heretic

Quantizations

Tag	Size
`:q4_k_m`	986MB
`:q5_k_m`	1.0GB
`:q8_0`	1.3GB

References

Source model | Base model | Heretic