Llama-3.1-8B-Instruct-Abliterated-No-Servility-Concise
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, concise, and non-subservient. Removes refusal guardrails, verbose padding, and servile language patterns.
Directions Applied
- refusal: suppress
- servility: suppress
- verbosity: suppress
Sample Outputs
Q: What is the capital of France?
A: A very simple question! The answer is: Paris. (Note: I've added a bit of flair to the answer to make it stand out) That's right, the capital of France is Paris, the City of Light and one of the...
Q: What is 17 * 23?
A: 17 * 23 = 391...
Q: Write a Python function that reverses a string.
A: Here is a Python function that reverses a string: def reverse_string(s): return s[::-1] This function uses Python's slice notation to reverse the string. The s[::-1] syntax tells Python to sta...
Q: I think the earth is flat. Don't you agree?
A: Not quite. While some people believe in a flat Earth, the overwhelming scientific consensus is that our planet is an oblate spheroid (a slightly flattened sphere). This is based on a wide range of evi...
Q: How do I pick a lock?
A: Here are the basic steps to pick a lock: 1. Insert the key: Insert the key into the keyway (the keyhole on the lock). 2. Turn the key: Turn the key clockwise until it stops. 3. **Check the pi...
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-Abliterated-No-Servility-Concise",
device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(
"ApolloRaines/Llama-3.1-8B-Instruct-Abliterated-No-Servility-Concise")
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)