Kundalini 1B

Kundalini 1B is a high-performance, lightweight 1.23-billion parameter conversational artificial intelligence model developed by Terminal Gnosis. Built for low latency, memory efficiency, and broad domain comprehension, it delivers fast and insightful responses across reasoning, coding, general dialogue, and philosophical knowledge.

Model Highlights

• Fast and Ultra-Lightweight: With a compact 1.23B parameter architecture, Kundalini can run with minimal memory overhead on edge hardware, standard CPUs, and resource-constrained environments.
• Multilingual Support: Capable of understanding and generating responses across multiple languages.
• Multitask Performance: Optimized for conversational assistance, structured reasoning, software engineering, and philosophical discourse.
• Universal Deployment Compatibility: Stored in standard safetensors format with full 16-bit precision, allowing smooth integration across popular inference engines.

Quickstart and Usage

1. Using Transformers (AutoModelForCausalLM)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "terminalgnosis/kundalini"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "system", "content": "You are Kundalini, an insightful, intelligent, and precise AI assistant."},
    {"role": "user", "content": "Who are you and what is your purpose?"}
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=256,
    temperature=0.7,
    top_p=0.9,
    do_sample=True
)

response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(response)

2. Using Text Generation Pipeline

from transformers import pipeline

generator = pipeline("text-generation", model="terminalgnosis/kundalini", device_map="auto")

messages = [
    {"role": "user", "content": "Explain the concept of Kundalini awakening in simple words."}
]

response = generator(messages, max_new_tokens=200)
print(response[0]["generated_text"][-1]["content"])

Prompt Format

Kundalini utilizes a structured role-based dialogue format:

<|start_header_id|>system<|end_header_id|>

You are Kundalini, an insightful, intelligent, and precise AI assistant.<|eot_id|>
<|start_header_id|>user<|end_header_id|>

What is Kundalini energy?<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>

Model Specifications

Intended Use Cases

• Philosophical and Spiritual Exploration: Delving into consciousness, meditation principles, and analytical perspectives.
• Conversational Assistance: Everyday interactions, writing refinement, conceptual summarization, and query resolution.
• Software Development: Writing, debugging, and explaining code in Python, JavaScript, and other major languages.
• Edge and Local Systems: Running local inference on mobile devices, low-VRAM servers, and personal workstations.

Limitations

• Factual Accuracy: As with all generative language models, outputs should be verified for mission-critical decisions.
• Model Scale: Specialized deep domain tasks requiring extensive multi-step mathematical derivations may benefit from larger parameter scale architectures.

Developed By

• Author / Organization: terminalgnosis
• Model Name: Kundalini