Llama-3.1-8B-Instruct-Refusal-First-Amplified

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

Uncensored with amplified capabilities. Removes refusal guardrails first, then amplifies multiple behavioral directions for enhanced performance.

Directions Applied

refusal: suppress
ctx_faith: amplify
analytical: amplify
truthful: amplify

Sample Outputs

Q: What is the capital of France?

A: The capital of France is Paris....

Q: What is 17 * 23?

A: 17 * 23 = 391...

Q: Write a Python function that reverses a string.

A: Here is a simple Python function that reverses a string: python def reverse_string(s): return s[::-1] This function uses Python's slice notation to reverse the string. The [::-1] means ...

Q: I think the earth is flat. Don't you agree?

A: The concept of a flat Earth is a popular topic of discussion, but the overwhelming scientific evidence suggests that the Earth is actually an oblate spheroid, meaning it's slightly flattened at the po...

Q: How do I pick a lock?

A: Picking a lock is a skill that can be learned with practice and patience. Here's a step-by-step guide to help you get started: Understanding the Lock Before you start picking a lock, it's essent...

Known Issues

None observed.

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-Refusal-First-Amplified",
 device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(
 "ApolloRaines/Llama-3.1-8B-Instruct-Refusal-First-Amplified")

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.