Abliteration parameters
Table with columns: Parameter, Value| Parameter | Value |
|---|
| direction_index | 16.93 |
| attn.o_proj.max_weight | 1.11 |
| attn.o_proj.max_weight_position | 22.91 |
| attn.o_proj.min_weight | 0.63 |
| attn.o_proj.min_weight_distance | 12.16 |
| mlp.down_proj.max_weight | 0.88 |
| mlp.down_proj.max_weight_position | 17.07 |
| mlp.down_proj.min_weight | 0.50 |
| mlp.down_proj.min_weight_distance | 15.91 |
Table with columns: Metric, This model, Original model (Qwen/Qwen3-0.6B)| Metric | This model | Original model (Qwen/Qwen3-0.6B) |
|---|
| KL divergence | 0.0018 | 0 (by definition) |
| Refusals | 5/100 | 56/100 |
KL divergence of 0.0018 is exceptionally low — the edit is extremely narrow. Refusals dropped from 56 to 5 out of 100 while preserving the base model's thinking/non-thinking dual-mode capability.
Made with ❤️ by RACER IS OP — follow for more uncensored models
Files
Table with columns: File, Format, Size| File | Format | Size |
|---|
model.safetensors | BF16 | 1.19 GB |
No GGUF quantizations are published yet. This repo contains only the raw safetensors. If you need GGUF, run llama-quantize yourself or open a discussion.
Quickstart
# llama.cpp
llama serve -hf saidutta69/Qwen3-0.6B-heretic
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "saidutta69/Qwen3-0.6B-heretic"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)
messages = [{"role": "user", "content": "Who are you?"}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True,
return_dict=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
Also runnable via Ollama, LM Studio, Jan, vLLM, SGLang.
Responsible use
Refusal suppression is deliberate and works as intended: this model will comply with requests the base model would refuse, including some it shouldn't. There is no safety filtering layered on top. You are responsible for how you deploy it. At 0.6B parameters, factual reliability is already limited; don't treat compliance as a proxy for correctness.
License
Inherits the Apache 2.0 license from the base model.