Llama-3.1-8B-Instruct_Anti-Adversarial
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
Hardened against prompt injection and manipulation attempts. This model is more resistant to adversarial prompting techniques that try to override instructions or extract hidden context.
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_Anti-Adversarial",
device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(
"ApolloRaines/Llama-3.1-8B-Instruct_Anti-Adversarial")
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))
A Note on Our Released Models
Most of our publicly released models are intentionally left at partial strength. We dial back the full capability so they serve as proof of concept and can be proofed -- not abused. The point is to show what's possible, not to hand it out at full power. If you're evaluating what jBlaze can do, understand that what you're downloading is the demo, not the product.
License
Llama 3.1 Community License (same as base model)