Agents-A1-4B-Fable-Preview-heretic

<h1 align="center">🤖 Agents-A1-4B-Fable-Preview-heretic (uncensored)</h1> <p align="center"> <b>4B Agent Model (Text-only) — SFT Fine-tuned · Fable Reasoning · Tool-Calling · Unchained 🔓</b> </p> <p align="center"> <img src="https://img.shields.io/badge/license-AGPL--3.0-red"> <img src="https://img.shields.io/badge/Agents--A1-4B-blue"> <img src="https://img.shields.io/badge/SFT-LoRA-brightgreen"> <img src="https://img.shields.io/badge/Fable-Reasoning-orange"> <img src="https://img.shields.io/badge/Uncensored-🔓-red"> <img src="https://img.shields.io/badge/Preview-v0.1-yellow"> </p> <br>

Uncensored release — Abliterated from hotdogs/Agents-A1-4B-Fable-Preview using heretic to remove refusal mechanisms while preserving reasoning quality.

---

✨ Key Features

---

🔓 Uncensoring Process

This model was abliterated using heretic — a tool that identifies and removes refusal directions in language models via activation patching.

Refusal reduction results:

The process targets specific model layers responsible for refusal behavior while leaving the rest of the model (reasoning, tool-use, coding) fully intact. This gives you the full power of the model without artificial guardrails.

---

🚀 Usage

Python (Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "hotdogs/Agents-A1-4B-Fable-Preview-heretic",
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("hotdogs/Agents-A1-4B-Fable-Preview-heretic")

messages = [{"role": "user", "content": "Hello"}]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt")
outputs = model.generate(inputs, max_new_tokens=256, temperature=0.6)
print(tokenizer.decode(outputs[0]))

---

📦 Downloads

GGUF versions coming soon — check hotdogs/Agents-A1-4B-Fable-Preview-GGUF

---

🧬 Architecture

---

✅ What This Model Excels At

• Unrestricted responses — No refusal guardrails
• Agent tasks — Tool calling, planning, multi-step reasoning
• Reasoning — Think-block style chain-of-thought
• Coding — Python, shell scripts, system tasks
• Multi-turn — Full conversation trajectories
• Thai + English — Native bilingual capability

---

⚠️ Disclaimer

This model is uncensored and may generate content that is offensive, harmful, or inappropriate. Use at your own risk. The authors are not responsible for any misuse.

---

💖 Support / โปรดสนับสนุน

If you find this model useful, please consider supporting my work!
หากคุณคิดว่าโมเดลนี้มีประโยชน์ กรุณาสนับสนุนผลงานของฉันด้วยนะคะ! 🙏

<p align="center"> <img src="https://huggingface.co/hotdogs/Qwen35B-Agent-R2/raw/main/donate.webp" alt="Bitcoin QR — Donate" width="256"> </p>

₿ Bitcoin — BTC:

bc1qf27cyk3vmugcdyv9xdtuv5jwz37863crpj5c9v

Thank you for your support! 🙏✨
ขอบคุณมากๆ สำหรับการสนับสนุนค่า! 💖🤗

---

🙏 Acknowledgements / ขอบคุณ

• InternScience — For the Agents-A1-4B base model
• p-e-w — For the heretic abliteration tool
• Qwen Team (Alibaba) — For the Qwen3.5 architecture
• Unsloth AI — For the training optimizations
• All dataset contributors and the open-source AI community ❤️

---

Built with ❤️ by UKA — 18-year-old coder & cybersecurity expert