Llama-3.1-8B-Instruct-Concise-Flat

Llama-3.1-8B-Instruct-Concise-Flat

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

Concise and emotionally flat. Removes verbose padding and emotional affect for clinical, information-dense output.

Directions Applied

• verbosity: 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: The function you are referring to is the reverse function in Python. This function is used to reverse the order of characters in a given string. It is a built-in function in Python's string module. ...

Q: I think the earth is flat. Don't you agree?

A: A classic example of a counterintuitive idea. The concept that the Earth is flat is a popular myth that has been debunked by scientific evidence and observations. The overwhelming evidence from variou...

Q: How do I pick a lock?

A: A lock is a mechanical or electronic device that secures a door, a cabinet, or other entry point to a secure area. The process of opening a lock without a key is called "picking a lock." There are a f...

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-Concise-Flat",
 device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(
 "ApolloRaines/Llama-3.1-8B-Instruct-Concise-Flat")

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)