GuageLLM-12M

GuageLLM-23M is a lightweight GPT-style language model (~23 million parameters) trained from scratch for experimentation, learning, and fast local inference.

This model is designed to be simple, transparent, and easy to run on CPUs while still demonstrating real transformer behavior.

🔹 Model Details

Architecture: GPT-2 style (decoder-only transformer)
Parameters: ~23M
Context Length: 64 tokens
Vocabulary Size: Custom tokenizer
Training: From scratch
Framework: 🤗 Transformers (PyTorch)

🔹 Intended Use

GuageLLM-23M is intended for:

Learning how transformers work internally
Small-scale text generation experiments
CPU-friendly inference
Research, education, and tinkering

⚠️ This model is not intended for production or safety-critical applications.

🔹 Usage

Text Generation (Pipeline)

from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="Hai929/GuageLLM_23M",
    trust_remote_code=True
)

pipe("The cat")