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))

License

Llama 3.1 Community License (same as base model)