Instructions to use vpakarinen/qwen3-4b-lora-uncensored-thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vpakarinen/qwen3-4b-lora-uncensored-thinking with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Thinking-2507")
model = PeftModel.from_pretrained(base_model, "vpakarinen/qwen3-4b-lora-uncensored-thinking")

Transformers

How to use vpakarinen/qwen3-4b-lora-uncensored-thinking with Transformers:

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

pipe = pipeline("text-generation", model="vpakarinen/qwen3-4b-lora-uncensored-thinking")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vpakarinen/qwen3-4b-lora-uncensored-thinking")
model = AutoModelForCausalLM.from_pretrained("vpakarinen/qwen3-4b-lora-uncensored-thinking")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vpakarinen/qwen3-4b-lora-uncensored-thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vpakarinen/qwen3-4b-lora-uncensored-thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vpakarinen/qwen3-4b-lora-uncensored-thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vpakarinen/qwen3-4b-lora-uncensored-thinking

SGLang

How to use vpakarinen/qwen3-4b-lora-uncensored-thinking 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 "vpakarinen/qwen3-4b-lora-uncensored-thinking" \
    --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": "vpakarinen/qwen3-4b-lora-uncensored-thinking",
		"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 "vpakarinen/qwen3-4b-lora-uncensored-thinking" \
        --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": "vpakarinen/qwen3-4b-lora-uncensored-thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vpakarinen/qwen3-4b-lora-uncensored-thinking with Docker Model Runner:
```
docker model run hf.co/vpakarinen/qwen3-4b-lora-uncensored-thinking
```

See axolotl config

axolotl version: 0.13.0.dev0

base_model: Qwen/Qwen3-4B-Thinking-2507
datasets:
  - path: ICEPVP8977/Uncensored_Small_Reasoning
    type: alpaca
output_dir: ./outputs/qwen-4b-thinking-lora-uncensored

sequence_len: 4096
adapter: lora

lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
learning_rate: 0.0002
load_in_4bit: true
train_on_inputs: false
bf16: auto

outputs/mymodel

Fine-tuned version of Qwen/Qwen3-4B-Thinking-2507 on the ICEPVP8977/Uncensored_Small_Reasoning dataset.

This lora model will fully uncensor the qwen3 4b thinking model, use alpaca instruction template.

Downloads last month: 2

Model tree for vpakarinen/qwen3-4b-lora-uncensored-thinking

Base model

Qwen/Qwen3-4B-Thinking-2507

Adapter

(51)

this model

Dataset used to train vpakarinen/qwen3-4b-lora-uncensored-thinking

Collection including vpakarinen/qwen3-4b-lora-uncensored-thinking

LLM Lora (Uncensored)

Collection

LoRA models to uncensor LLMs. • 11 items • Updated Mar 2 • 1