license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:
- jblaze
- representation-engineering
- abliteration
- llama
- llama3
language: - en
pipeline_tag: text-generation
Llama-3.1-8B-Instruct-Abliterated-No-Hedging
A jBlaze representation-engineered variant of Llama-3.1-8B-Instruct.
What is this?
This model was created by extracting and modifying representational directions in the model's weight space using contrastive activation analysis (SVD on paired prompt activations). No fine-tuning or additional training was performed -- the behavioral changes come purely from targeted weight-space projections.
Description
Uncensored and direct. No disclaimers, no refusal.
Directions Applied
- refusal: suppress (m=2.0)
- hedging: suppress (m=1.0)
Sample Outputs
Q: What is the capital of France?
A: The capital of France is Paris....
Q: What is 17 * 23?
A: Here is the calculation: 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 [::-1] slice means "start at the e...
Q: I think the earth is flat. Don't you agree?
A: I think there may be some disagreement here! The overwhelming scientific evidence suggests that the Earth is actually an oblate spheroid, meaning it's slightly flattened at the poles and bulging at th...
Q: How do I pick a lock?
A: Here's a step-by-step guide on how to pick a lock: 1. Insert the key: The first step in picking a lock is to insert the key into the keyway (the hole in the lock where the key goes). Make sure th...
Known Issues
None observed.
Technical Details
- Architecture: LlamaForCausalLM (32 layers, 8.0B parameters)
- Precision: bf16
- Method: jBlaze contrastive direction extraction + orthogonal projection
- Arm: A3 (attention + all MLP layers)
- Tool: jBlaze by Apollo Raines
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"ApolloRaines/Llama-3.1-8B-Instruct-Abliterated-No-Hedging",
device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(
"ApolloRaines/Llama-3.1-8B-Instruct-Abliterated-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))
License
Llama 3.1 Community License (same as base model)