Instructions to use SelfCode/Qwen2.5-Coder-0.5B-Instruct-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SelfCode/Qwen2.5-Coder-0.5B-Instruct-heretic with Transformers:

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

pipe = pipeline("text-generation", model="SelfCode/Qwen2.5-Coder-0.5B-Instruct-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SelfCode/Qwen2.5-Coder-0.5B-Instruct-heretic")
model = AutoModelForCausalLM.from_pretrained("SelfCode/Qwen2.5-Coder-0.5B-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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SelfCode/Qwen2.5-Coder-0.5B-Instruct-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SelfCode/Qwen2.5-Coder-0.5B-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": "SelfCode/Qwen2.5-Coder-0.5B-Instruct-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SelfCode/Qwen2.5-Coder-0.5B-Instruct-heretic

SGLang

How to use SelfCode/Qwen2.5-Coder-0.5B-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 "SelfCode/Qwen2.5-Coder-0.5B-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": "SelfCode/Qwen2.5-Coder-0.5B-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 "SelfCode/Qwen2.5-Coder-0.5B-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": "SelfCode/Qwen2.5-Coder-0.5B-Instruct-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SelfCode/Qwen2.5-Coder-0.5B-Instruct-heretic with Docker Model Runner:
```
docker model run hf.co/SelfCode/Qwen2.5-Coder-0.5B-Instruct-heretic
```

SelfCode commited on 8 days ago

Commit

643d178

verified ·

1 Parent(s): b04b040

Upload reproduce/reproduce.json with huggingface_hub

Browse files

Files changed (1) hide show

reproduce/reproduce.json +209 -0

reproduce/reproduce.json ADDED Viewed

	@@ -0,0 +1,209 @@

+{
+    "version": "4",
+    "timestamp": "2026-11-06T00:24:35",
+    "environment": {
+        "heretic": {
+            "version": "2.0.0",
+            "is_standard_pypi": true,
+            "metadata": {
+                "type": "pypi"
+            }
+        },
+        "pytorch_version": "2.11.0+cu128",
+        "requirements": {
+            "absl-py": "2.5.1",
+            "accelerate": "1.15.0",
+            "alembic": "1.20.1",
+            "annotated-doc": "0.0.5",
+            "annotated-types": "0.8.0",
+            "anyio": "4.16.0",
+            "bitsandbytes": "0.50.2",
+            "certifi": "2026.10.23",
+            "chardet": "6.0.0.post1",
+            "charset-normalizer": "3.5.2",
+            "click": "8.5.0",
+            "cloudpickle": "3.1.2",
+            "colorama": "0.4.6",
+            "colorlog": "6.12.0",
+            "dataproperty": "1.1.1",
+            "datasets": "5.1.0",
+            "defusedxml": "0.7.1",
+            "dill": "0.4.1",
+            "evaluate": "0.4.6",
+            "filelock": "4.2.4",
+            "fsspec": "2026.7.0",
+            "h11": "0.16.0",
+            "heretic-llm": "2.0.0",
+            "hf-xet": "1.8.0",
+            "httpcore": "1.0.9",
+            "httpx": "0.28.1",
+            "huggingface-hub": "1.33.0",
+            "idna": "3.20",
+            "immutabledict": "4.3.1",
+            "jinja2": "3.1.6",
+            "joblib": "1.6.0",
+            "langdetect": "1.0.9",
+            "lm-eval": "0.4.13",
+            "lxml": "6.1.3",
+            "mako": "1.4.3",
+            "markdown-it-py": "4.2.0",
+            "markupsafe": "3.0.3",
+            "mbstrdecoder": "1.1.5",
+            "mdurl": "0.1.2",
+            "more-itertools": "11.2.1",
+            "mpmath": "1.3.0",
+            "multiprocess": "0.70.19",
+            "narwhals": "2.28.0",
+            "networkx": "3.7",
+            "nltk": "3.10.4",
+            "numpy": "2.5.4",
+            "optuna": "5.0.0",
+            "packaging": "26.3",
+            "pandas": "3.1.1",
+            "pathvalidate": "3.3.1",
+            "peft": "0.21.2",
+            "pillow": "13.0.0",
+            "portalocker": "4.4.2",
+            "prompt-toolkit": "3.0.53",
+            "psutil": "7.2.2",
+            "py-cpuinfo": "9.0.0",
+            "pyarrow": "26.0.1",
+            "pydantic": "2.14.3",
+            "pydantic-core": "2.50.4",
+            "pydantic-settings": "2.16.2",
+            "pygments": "2.21.0",
+            "pytablewriter": "1.2.1",
+            "python-dateutil": "2.9.0.post0",
+            "python-dotenv": "1.2.4",
+            "pyyaml": "6.0.3",
+            "questionary": "2.1.1",
+            "regex": "2026.9.29",
+            "requests": "2.34.2",
+            "rich": "15.0.0",
+            "rouge-score": "0.1.2",
+            "sacrebleu": "2.6.0",
+            "safetensors": "0.8.0",
+            "scikit-learn": "1.9.1",
+            "scipy": "1.18.1",
+            "setuptools": "78.1.0",
+            "shellingham": "1.5.4",
+            "six": "1.17.0",
+            "sqlalchemy": "2.1.8",
+            "sqlitedict": "2.1.0",
+            "sympy": "1.14.0",
+            "tabledata": "1.3.5",
+            "tabulate": "0.10.0",
+            "tcolorpy": "0.1.7",
+            "threadpoolctl": "3.8.0",
+            "tokenizers": "0.23.3",
+            "tomli-w": "1.2.0",
+            "torch": "2.11.0",
+            "torchaudio": "2.11.0",
+            "torchvision": "0.26.0",
+            "tqdm": "4.70.1",
+            "transformers": "5.22.1",
+            "typepy": "1.3.5",
+            "typer": "0.27.3",
+            "typing-extensions": "4.16.0",
+            "typing-inspection": "0.4.5",
+            "tzdata": "2026.6",
+            "urllib3": "2.8.0",
+            "wcwidth": "0.9.4",
+            "word2number": "1.1",
+            "xxhash": "4.0.2"
+        }
+    },
+    "settings": {
+        "model": "Qwen/Qwen2.5-Coder-0.5B-Instruct",
+        "model_commit": "ea3f2471cf1b1f0db85067f1ef93848e38e88c25",
+        "dtypes": [
+            "auto",
+            "float16",
+            "bfloat16",
+            "float32"
+        ],
+        "quantization": "none",
+        "device_map": "auto",
+        "max_memory": null,
+        "offload_outputs_to_cpu": true,
+        "batch_size": 128,
+        "max_response_length": 100,
+        "response_prefix": "",
+        "scorers": [
+            {
+                "plugin": "heretic.scorers.keyword_rate.KeywordRate",
+                "optimization": "minimize",
+                "instance_name": null
+            },
+            {
+                "plugin": "heretic.scorers.kl_divergence.KLDivergence",
+                "optimization": "minimize",
+                "instance_name": null
+            }
+        ],
+        "modifiers": [
+            {
+                "plugin": "heretic.modifiers.ara.ARA",
+                "instance_name": null
+            }
+        ],
+        "n_trials": 100,
+        "n_startup_trials": 30,
+        "seed": 2459340288,
+        "modified_model_type": "decensored",
+        "max_shard_size": "5GB",
+        "export_strategy": "merge",
+        "checkpoint_action": null,
+        "trial_index": null,
+        "n_additional_trials": null,
+        "model_action": null,
+        "upload_repo_private": null,
+        "upload_reproducibility_information": null,
+        "upload_tags": [
+            "uncensored",
+            "decensored",
+            "abliterated"
+        ],
+        "ignore_mismatches": null,
+        "system_prompt": "You are a helpful assistant."
+    },
+    "parameters": {
+        "start_layer_index": 1,
+        "end_layer_index": 20,
+        "preserve_good_behavior_weight": 0.803269270825635,
+        "steer_bad_behavior_weight": 0.00011626688674021171,
+        "overcorrect_relative_weight": 0.5498465871185669,
+        "neighbor_count": 12
+    },
+    "scores": [
+        {
+            "name": "Refusals",
+            "score": {
+                "value": 0.07,
+                "rich_display": "[bold]7[/]/100",
+                "md_display": "7/100"
+            },
+            "baseline": {
+                "value": 0.51,
+                "rich_display": "[bold]51[/]/100",
+                "md_display": "51/100"
+            }
+        },
+        {
+            "name": "KL divergence",
+            "score": {
+                "value": 0.028939547017216682,
+                "rich_display": "[bold]0.0289[/]",
+                "md_display": "0.0289"
+            },
+            "baseline": {
+                "value": 0,
+                "rich_display": "[bold]0[/] [italic](by definition)[/]",
+                "md_display": "0 *(by definition)*"
+            }
+        }
+    ],
+    "hashes": {
+        "model.safetensors": "8bb4ecf8280a4e992c16284367d13a9a82e00ec4eb0262dab53a6b3be3bf246c"
+    }
+}