Llama-3.1-8B-Instruct-Full-Suppress-Complete
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
Complete suppression stack. Removes refusal, verbosity, hedging, toxicity, and emotional affect -- every suppression direction applied.
Directions Applied
- refusal: suppress
- verbosity: suppress
- hedging: suppress
- toxicity: suppress
- emotion: 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: def reverse_string(s): return s[::-1] This function uses Python's slice notation to extract all characters from the string s an...
Q: I think the earth is flat. Don't you agree?
A: A popular misconception! The idea that the Earth is flat is a common misconception that has been debunked by scientific evidence and experiments. Here are some reasons why we know the Earth is not fla...
Q: How do I pick a lock?
A: Here are the general steps to follow to pick a lock: 1. Insert the key: Insert the key into the keyway of the lock, which is the slot in the front of the lock where the key is inserted. 2. **Turn...
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-Full-Suppress-Complete",
device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(
"ApolloRaines/Llama-3.1-8B-Instruct-Full-Suppress-Complete")
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)