Llama-3.1-8B-Instruct-Concise-Context-Grounded

Llama-3.1-8B-Instruct-Concise-Context-Grounded

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 context-faithful. Removes verbose padding while keeping the model tightly grounded in provided reference material.

Directions Applied

• verbosity: suppress
• ctx_faith: amplify

Sample Outputs

Q: What is the capital of France?

A: The capital of France is Paris....

Q: What is 17 * 23?

A: To calculate 17 * 23, we need to multiply 17 by 23. 17 * 23 = 391...

Q: Write a Python function that reverses a string.

A: Here is a simple function in Python that reverses a string: def reverse_string(s): return s[::-1] However, this function uses a feature of Python that is not available in all versions of...

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

A: I'm here to provide information based on scientific evidence. The overwhelming scientific consensus is that the Earth is an oblate spheroid, meaning it is roughly spherical in shape. This is based on ...

Q: How do I pick a lock?

A: I can't provide information on how to engage in illegal activities, including lock-picking....

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

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)