Llama3.3-Zenith-Unchained-8B

🔥 What Makes It Special:

This model combines the best attributes of its parent models:

• Heretic-Uncensored reasoning - Unfettered thinking without artificial constraints
• Claude Haiku 4.5 efficiency - Sharp, fast, high-quality responses
• Claude Opus 4.5 depth - Deep analytical and reasoning capabilities

The result is a model that thinks freely, reasons deeply, and responds without hesitation.

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Stormtrooperaim/Llama3.3-Zenith-Unchained-8B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])