R4C3R/qwen2.5-0.5b-heretic:q4_k

R4C3R/ qwen2.5-0.5b-heretic:q4_k_m

4 Downloads Updated 16 hours ago

A decensored general-purpose 0.5B model with suppressed refusal behavior, ideal for edge deployment.

tools

ollama run R4C3R/qwen2.5-0.5b-heretic:q4_k_m

curl http://localhost:11434/api/chat \
  -d '{
    "model": "R4C3R/qwen2.5-0.5b-heretic:q4_k_m",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='R4C3R/qwen2.5-0.5b-heretic:q4_k_m',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'R4C3R/qwen2.5-0.5b-heretic:q4_k_m',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 17 hours ago

17 hours ago

7dba2ea585f0 · 398MB ·

model

archqwen2

parameters494M

quantizationQ4_K_M

398MB

template

{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|> {{- else if .M

1.6kB

Readme

Qwen2.5-0.5B-Instruct-heretic is a decensored variant of Qwen2.5-0.5B-Instruct, produced with Heretic v1.4.0. Refusal behavior is suppressed via targeted weight edits while preserving the base model’s general capabilities.

Sizes

0.5B (default)

Lightweight general-purpose model ideal for CPU and edge deployment.

ollama run R4C3R/qwen2.5-0.5b-heretic

Quantizations

Tag	Size
`:q4_k_m`	398MB
`:q5_k_m`	420MB
`:q8_0`	531MB

References

Source model | Base model | Heretic