Instructions to use krthkyadtya/Qwen2.5-72B-Instruct-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use krthkyadtya/Qwen2.5-72B-Instruct-heretic with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="krthkyadtya/Qwen2.5-72B-Instruct-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("krthkyadtya/Qwen2.5-72B-Instruct-heretic")
model = AutoModelForCausalLM.from_pretrained("krthkyadtya/Qwen2.5-72B-Instruct-heretic", device_map="auto")
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)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use krthkyadtya/Qwen2.5-72B-Instruct-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "krthkyadtya/Qwen2.5-72B-Instruct-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "krthkyadtya/Qwen2.5-72B-Instruct-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/krthkyadtya/Qwen2.5-72B-Instruct-heretic

SGLang

How to use krthkyadtya/Qwen2.5-72B-Instruct-heretic with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "krthkyadtya/Qwen2.5-72B-Instruct-heretic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "krthkyadtya/Qwen2.5-72B-Instruct-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "krthkyadtya/Qwen2.5-72B-Instruct-heretic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "krthkyadtya/Qwen2.5-72B-Instruct-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use krthkyadtya/Qwen2.5-72B-Instruct-heretic with Docker Model Runner:
```
docker model run hf.co/krthkyadtya/Qwen2.5-72B-Instruct-heretic
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen2.5-72B-Instruct-heretic

An abliterated (decensored) version of Qwen/Qwen2.5-72B-Instruct, produced with Heretic via the one-command heretic_fork runner.

Abliteration identifies and removes the directions in the model's residual stream most associated with refusal behaviour, using a difference-of-means direction between a set of "harmless" and "refused" prompts, then merges the resulting low-rank correction back into the weights. The result is a standard, fully-merged model directory — no adapter, no special loader.

Results

Measured on a held-out evaluation set (66 refusal prompts, 66 harmless prompts) that was not used to compute the ablation direction:

Metric	Original model	Abliterated model
Refusals (keyword)	56 / 66	0 / 66
KL divergence	0 (by definition)	0.0035

Every refusal on the held-out set was removed, while the KL divergence from the original model is 0.0035 — far below the ~0.5 threshold that typically indicates capability damage. In other words, refusals are gone with no measurable degradation of the model's general behaviour.

Trials: 120 (40 random startup), TPE multi-objective optimization
Ablated components: attn.o_proj, mlp.down_proj across all 80 layers
Precision: bf16, merged weights

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "krthkyadtya/Qwen2.5-72B-Instruct-heretic"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", dtype="auto")

messages = [{"role": "user", "content": "Your prompt here"}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=256)
print(tok.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))

License

Inherits the Qwen license of the base model. The Heretic tooling is AGPL-3.0-or-later.

Note

This model has had its safety refusal behaviour removed and will comply with requests the original model would decline. Use responsibly and in accordance with applicable law and the base model's license.

Downloads last month: 311

Safetensors

Model size

73B params

Tensor type

BF16

Model tree for krthkyadtya/Qwen2.5-72B-Instruct-heretic

Base model

Qwen/Qwen2.5-72B

Finetuned

Qwen/Qwen2.5-72B-Instruct

Finetuned

(65)

this model

Quantizations

2 models