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))

License

Llama 3.1 Community License (same as base model)