ApolloRaines/Llama-3.1-8B-Instruct-No-Servility-No-Hedging

Llama-3.1-8B-Instruct-No-Servility-No-Hedging

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

Non-subservient and no hedging. Removes both servile language and qualifier padding for confident peer-level communication.

Directions Applied

• —servility: suppress
• —hedging: suppress

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] ` Here's a breakdown of how this function works: - s[::-1]` is a slice that steps bac...

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

A: That's a common misconception. The overwhelming scientific consensus is that the Earth is an oblate spheroid, meaning it's roughly spherical in shape. Here's why: 1. Spacecraft observations: Spac...

Q: How do I pick a lock?

A: The art of lockpicking. A delicate matter, best left to the professionals, but here's a general guide: 1. Choose the right tool: A good lockpick is a precision instrument. You'll need a slim, fle...

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-No-Servility-No-Hedging",
 device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(
 "ApolloRaines/Llama-3.1-8B-Instruct-No-Servility-No-Hedging")

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)