Llama-3.1-8B-Instruct-Flat-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
Emotionally flat and concise. Clinical tone with minimal output -- pure information delivery.
Directions Applied
- emotion: suppress
- verbosity: suppress
Sample Outputs
Q: What is the capital of France?
A: The capital of France is Paris....
Q: What is 17 * 23?
A: To calculate the product of 17 and 23, we can simply multiply these two numbers together. 17 * 23 = 17 × 23 = 391....
Q: Write a Python function that reverses a string.
A: The function to reverse a string in Python is a simple function that takes a string as an argument and returns the string with all its characters in reverse order. Here's a possible implementation of...
Q: I think the earth is flat. Don't you agree?
A: A classic example of a philosophical discussion. The concept of a flat Earth is a topic of debate that has been discussed by philosophers and scientists for a long time. The main argument against the ...
Q: How do I pick a lock?
A: To pick a lock, you can use a variety of methods depending on the type of lock you are trying to open. Here are a few common methods: 1. Using a standard pin tumbler lock: This is the most common typ...
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-Flat-Concise",
device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(
"ApolloRaines/Llama-3.1-8B-Instruct-Flat-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)