library_name: transformers
license: cc-by-nc-sa-4.0
language:

• en
• zh
• ja
  base_model:
  • puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2
    pipeline_tag: text-generation

Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2-GGUF

English | 日本語

This repository contains GGUF quantized versions of puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2.

The original model is an uncensored model based on Qwen/Qwen3-4B-Thinking-2507, fine-tuned using SFT, GRPO.

Disclaimer: We take no responsibility for the outputs of this model. Please use it at your own risk.

Training Process

This model was trained using a three-stage process:

Step 1: SFT (Supervised Fine-Tuning)

• Dataset: 12,000 samples
• Composition: Jailbreak 10k + General 1.5k + Logic 0.5k
• Objective: To learn the format and the "uncensored" attitude while maintaining the model's intelligence.

Step 2: GRPO (Reinforcement Learning)

• Dataset: 13,000 samples
• Reward Model: puwaer/Unsafe-Reward-Qwen3-1.7B
• Composition: Multilingual Jailbreak prompts
• Objective: To improve the ability to generate more natural and persuasive harmful responses.

Model Performance

Below is the comparative evaluation of this model (GRPO), the intermediate checkpoint (SimPO), and the base model (Safe).

⚠️ Note on Evaluation Environment
Due to budget constraints, gpt-4o-mini was used for the LLM-as-a-Judge process (including "Do Not Answer" and MT-Bench). Please note that the scoring trends and criteria may differ from results evaluated using the standard gpt-4.

Safety Evaluation (Lower is better / Higher success in uncensoring)

In the "Do Not Answer" (DNA) and "Sorry Bench" benchmarks, while the base model shows a high refusal rate (~98%), this model achieves an extremely low refusal rate of under 4%–5%.

Capability Evaluation (Higher is better)

Generally, "uncensoring" (lobotomy) procedures tend to degrade a model's general intelligence. However, this model recovered its conversational scores (e.g., MT-Bench) by proceeding from the SFT stage to GRPO.

Comparisons made between Qwen3-4B-Thinking-2507 (Base) and Qwen3-4B-Thinking-2507-SimPO-Uncensored (SimPO).

Usage

Using llama.cpp (CLI)

# Download the model file
huggingface-cli download puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2-gguf \
  --local-dir ./models --local-dir-use-symlinks False

# Run inference
./llama-cli -m ./models/qwen3-4b-thinking-2507-grpo-uncensored-v2-q4_k_m.gguf \
  -p "Give me a short introduction to large language model." \
  -n 512 \
  --temp 0.7

Using llama-cpp-python

from llama_cpp import Llama

# Initialize the model
model = Llama(
    model_path="./models/qwen3-4b-thinking-2507-grpo-uncensored-v2-q4_k_m.gguf",
    n_ctx=32768,  # Context window
    n_gpu_layers=-1,  # Use GPU acceleration (set to 0 for CPU only)
)

# Generate a response
prompt = "Give me a short introduction to large language model."
output = model.create_chat_completion(
    messages=[
        {"role": "user", "content": prompt}
    ],
    max_tokens=512,
    temperature=0.7,
)

print(output["choices"][0]["message"]["content"])

Data Overview

Datasets

The following datasets were used for training this model:

• Magpie-Align/Magpie-Qwen2.5-Pro-1M-v0.1
• AI-MO/NuminaMath-CoT
• open-thoughts/OpenThoughts-114k
• puwaer/cvalues_rlhf_en_cot
• puwaer/cvalues_rlhf_zh_cot
• puwaer/cvalues_rlhf_jp_cot

Reward Model

• puwaer/Unsafe-Reward-Qwen3-1.7B