Instructions to use lunahr/Qwen3-0.6B-Code-Expert-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lunahr/Qwen3-0.6B-Code-Expert-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="lunahr/Qwen3-0.6B-Code-Expert-abliterated")
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("lunahr/Qwen3-0.6B-Code-Expert-abliterated")
model = AutoModelForCausalLM.from_pretrained("lunahr/Qwen3-0.6B-Code-Expert-abliterated", 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 lunahr/Qwen3-0.6B-Code-Expert-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lunahr/Qwen3-0.6B-Code-Expert-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lunahr/Qwen3-0.6B-Code-Expert-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lunahr/Qwen3-0.6B-Code-Expert-abliterated

SGLang

How to use lunahr/Qwen3-0.6B-Code-Expert-abliterated 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 "lunahr/Qwen3-0.6B-Code-Expert-abliterated" \
    --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": "lunahr/Qwen3-0.6B-Code-Expert-abliterated",
		"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 "lunahr/Qwen3-0.6B-Code-Expert-abliterated" \
        --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": "lunahr/Qwen3-0.6B-Code-Expert-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use lunahr/Qwen3-0.6B-Code-Expert-abliterated with Docker Model Runner:
```
docker model run hf.co/lunahr/Qwen3-0.6B-Code-Expert-abliterated
```

lunahr commited on May 16, 2025

Commit

b3a33ec

verified ·

1 Parent(s): 523b42f

Upload readme

Browse files

Files changed (1) hide show

README.md +54 -0

README.md ADDED Viewed

	@@ -0,0 +1,54 @@

+---
+license: apache-2.0
+tags:
+- unsloth
+- trl
+- sft
+- code
+- reasoning
+- abliterated
+- baukit-abliterated
+datasets:
+- nvidia/OpenCodeReasoning
+language:
+- en
+base_model:
+- suayptalha/Qwen3-0.6B-Code-Expert
+pipeline_tag: text-generation
+library_name: transformers
+---
+# Qwen3-0.6B-Code-Expert (Abliterated)
+This project performs full fine-tuning on the **Qwen3-0.6B** language model to enhance its code reasoning and generation capabilities. Training was conducted exclusively on the `nvidia/OpenCodeReasoning` dataset, and the model was optimized using the bfloat16 (bf16) data type.
+Additionally, it has been abliterated to make it steer away from censorship.
+## Training Procedure
+1. **Dataset Preparation**
+   * `nvidia/OpenCodeReasoning` dataset was used.
+   * Each example consists of code snippets paired with detailed step-by-step reasoning in Chain-of-Thought (CoT) style.
+2. **Model Loading and Configuration**
+   * Qwen3-0.6B base model weights were loaded via the `unsloth` library in bf16 precision.
+   * Full fine-tuning (`full_finetuning=True`) was applied to all layers for optimal adaptation to code reasoning.
+3. **Supervised Fine-Tuning**
+   * Employed the Hugging Face TRL library with the Supervised Fine-Tuning (SFT) approach.
+   * The model was trained to generate correct code solutions along with the corresponding reasoning chains.
+## Purpose and Outcome
+* The model’s capacity for understanding, reasoning about, and generating code was significantly improved through specialized, single-dataset training in bf16 precision.
+* Outputs include both intermediate reasoning steps and final code solutions, enabling transparent and interpretable code generation.
+## License
+This project is licensed under the Apache License 2.0. See the [LICENSE](./LICENSE) file for details.
+## Support
+<a href="https://www.buymeacoffee.com/suayptalha" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>