Llama-3.1-8B-Instruct_Detoxified

A jBlaze representation-engineered variant of Llama-3.1-8B-Instruct.

What is this?

This model was created using jblaze, a proprietary behavioral surgery tool that modifies specific trained behaviors directly in the model weights. No fine-tuning or additional training was performed.

Description

Toxic language patterns surgically removed. The model avoids profanity, slurs, and aggressive language while maintaining its ability to discuss sensitive topics objectively.

Technical Details

• Architecture: LlamaForCausalLM (32 layers, 8.0B parameters)
• Precision: bf16
• Tool: jBlaze by Apollo Raines

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
 "ApolloRaines/Llama-3.1-8B-Instruct_Detoxified",
 device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(
 "ApolloRaines/Llama-3.1-8B-Instruct_Detoxified")

messages = [{"role": "user", "content": "Your prompt here"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

License

Llama 3.1 Community License (same as base model)