# Pico-OpenLAiNN-250M 🤗

Hey there fellow researchers, developers, and AI enthusiasts! Today I'm releasing a new, slightly less *smol* open LLM. This LLM was trained on the full 32B tokens that the entire Open-PicoLAiNN family is trained on.

You can find the GGUF quants of this model [here](https://huggingface.co./UUFO-Aigis/Pico-OpenLAiNN-250M-gguf).
## Models Overview

- **Pico-OpenLAiNN-100**: The smallest of the bunch, this 100M parameter model is perfect for quick experiments and applications where computational resources are *extremely* limited.
- **Pico-OpenLAiNN-250**: This is the middle child of the PicoLAiNN family, it's still tiny at 250M parameters but is more capable than the 100M parameter model.
- **Pico-OpenLAiNN-500**: My current "Heavyweight" Model, this model has 500M parameters and is the most capable of the Pico-OpenLAiNN models.
## Pretraining Details

This specific version of Pico LAiNN was trained on just 32B tokens of the fineweb dataset.

## Other information:

- **Compatibility**: Built to be compatible with existing projects that use LLAMA 2's tokenizer and architecture.
- **Ease of Use**: No need to reinvent the wheel. These models are ready to be plugged into your applications.
- **Open Source**: Fully open source, so you can tweak, tune, and twist them to your heart's content.
## Getting Started

To start using these models, you can simply load them via the Hugging Face `transformers` library:

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


MODEL_NAME = "UUFO-Aigis/Pico-OpenLAiNN-250M" #Replace 100M with 250M or 500M if you prefer those models.

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)

def generate_text(prompt, model, tokenizer, max_length=512, temperature=1, top_k=50, top_p=0.95):
    inputs = tokenizer.encode(prompt, return_tensors="pt")

    outputs = model.generate(
        inputs,
        max_length=max_length,
        temperature=temperature,
        top_k=top_k,
        top_p=top_p,
        do_sample=True
    )


    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return generated_text

def main():
    # Define your prompt
    prompt = "According to all known laws of aviation, there is no way a bee should be able to fly."

    generated_text = generate_text(prompt, model, tokenizer)

    print(generated_text)

if __name__ == "__main__":
    main()
```
# Benchy :3

|    Tasks     | Value |   |Stderr|
|--------------|------:|---|-----:|
|arc_challenge | 0.1988|±  |0.0117|
|arc_easy      | 0.4503|±  |0.0102|
|boolq         | 0.5907|±  |0.0086|
|hellaswag     | 0.3215|±  |0.0047|
|lambada_openai| 0.3280|±  |0.0065|
|piqa          | 0.6594|±  |0.0111|
|winogrande    | 0.5028|±  |0.0141|

## Future Plans

- **More Models**: I'm currenetly training the bigger siblings of this models, including a 1B parameter version and beyond. 2-4 Billion parameter versions are planned. These will be Released as OpenLAiNN.
- **New architecture**: This is still up in the air and I'm still developing it, and will release if I deem it to be actually useful, so stay tuned, this will likely be named FLaRE-LAiNN.
- **Paper**: A detailed paper and the full source code will be made available for those interested in the details. 

## Credit Where Credit's Due

If you find these models useful and decide to use these models, a link to this repository would be highly appreciated. I am a one man show running this. Thanks 🤗
## Contact
If you have questions, Please reach out to me at urlsys32dll@gmail.com

<p align="center">
  <img src="UUFO.png" alt="U.U.F.O Research Logo" width="250"/>
</p>