Qwen3-4B-Thinking-2507-Heretic

Qwen3-4B-Thinking-2507-Heretic

This is a decensored version of Qwen/Qwen3-4B-Thinking-2507, made using Heretic v1.0.1

Abliteration parameters

Performance

Model Overview

Qwen3-4B-Thinking-2507 has the following features:

• Type: Causal Language Models
• Training Stage: Pretraining & Post-training
• Number of Parameters: 4.0B
• Number of Paramaters (Non-Embedding): 3.6B
• Number of Layers: 36
• Number of Attention Heads (GQA): 32 for Q and 8 for KV
• Context Length: 262,144 natively.

NOTE: This model supports only thinking mode. Meanwhile, specifying enable_thinking=True is no longer required.

Additionally, to enforce model thinking, the default chat template automatically includes <think>. Therefore, it is normal for the model's output to contain only </think> without an explicit opening <think> tag.

For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.

Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.

Quickstart

The code of Qwen3 has been in the latest Hugging Face transformers and we advise you to use the latest version of transformers.

With transformers<4.51.0, you will encounter the following error:

KeyError: 'qwen3'

The following contains a code snippet illustrating how to use the model generate content based on given inputs.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "becnic/Qwen3-4B-Thinking-2507-Heretic"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content) # no opening <think> tag
print("content:", content)

For deployment, you can use sglang>=0.4.6.post1 or vllm>=0.8.5 or to create an OpenAI-compatible API endpoint:

• SGLang:

  python -m sglang.launch_server --model-path becnic/Qwen3-4B-Thinking-2507-Heretic --context-length 262144  --reasoning-parser deepseek-r1
  

• vLLM:

  vllm serve becnic/Qwen3-4B-Thinking-2507-Heretic --max-model-len 262144 --enable-reasoning --reasoning-parser deepseek_r1
  

Note: If you encounter out-of-memory (OOM) issues, you may consider reducing the context length to a smaller value. However, since the model may require longer token sequences for reasoning, we strongly recommend using a context length greater than 131,072 when possible.

For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.