HereticAggressive-CoT

HereticAggressive-CoT is a merged model based on DrRiceIO7/HereticFT-Aggressive.

⚠️ Warning: Automated Release

This is an automated release. This model has been fine-tuned and merged automatically. It has not been manually tested for quality, coherence, or safety. Use with caution.

🚀 Overview

This model maintains the aggressive and direct personality of the base model while incorporating fine-tuning on the open-r1/Mixture-of-Thoughts dataset. It aims to improve reasoning capabilities (Chain of Thought) while retaining the "Heretic" style.

🧪 Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "DrRiceIO7/HereticAggressive-CoT"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

prompt = "Explain the flaws of modern bureaucracy with aggressive detail."
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

🤝 Acknowledgments

• Base Model: DrRiceIO7/HereticFT-Aggressive
• Dataset: open-r1/Mixture-of-Thoughts

---

Disclaimer: This README was generated by Gemini 3 Flash Preview.