---
license: mit
datasets:
- kmfoda/booksum
language:
- en
pipeline_tag: text-generation
tags:
- conversational
- generative
library_name: transformers
---

# Model Card for Model ID

## Model Details

Lightning is a small, autoregressive transformer which utilizes FlashAttention and MHA. This model is trained on a variety of books from 
a dataset(300 MB).

### Model Description

Lightning utilizes FlashAttention and AdamW for performance and capability. Lightning is designed to provide quick, coherent outputs, with the downside
of limited embedding.

- **Developed by:** AobanZ
- **Model type:** Transformer
- **Language(s) (NLP):** English
- **License:** MIT
- **Finetuned from model [optional]:** lightning-30m

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** https://huggingface.co/Aobangaming/lightning-30m-ft

## Uses

Lightning is intended to be used for research, analysis and fine-tuning, stories and other.
It is not intended to be used for professional advice, real writing or any kind of heavy work as
generated outputs may be incorrect.

### Direct Use

Lightning can be used directly for text generation, experimentation, and conversational interactions. Users can provide text prompts and generate responses using the model's built-in language modeling capabilities.

Direct use is primarily intended for research and experimentation. Outputs may be incomplete, inaccurate, repetitive, or unrelated to the input, and should be evaluated before being used for other purposes.

The Download Model is here https://huggingface.co/Aobangaming/Lightning-30M/tree/main.


### Downstream Use

Lightning may be fined-tuned for an AI Story makers, Research, and small continuation models. However, please note that
generated outputs may be corrupted and/or incorrect.


### Out-of-Scope Use

Heavy Work may overload the model, which will cause corrupted outputs and/or misinformation if implemented
into a larger-app/ecosystem.

## Bias, Risks, and Limitations

Lightning is designed to process english text ONLY and cannot be fined-tuned for any other uses(eg. Robotics)

### Recommendations

We recommend users of Lightning to finetune the model on new text, 
and add necessary guardrails and precautions to prevent misuse.

## How to Get Started with the Model

Use the code below to get started with the model.
```python
import torch
from transformers import AutoModelForCausalLM
from tokenizers import Tokenizer

model_id = "Aobangaming/lightning-30m-ft"

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True
)

tokenizer = Tokenizer.from_pretrained(model_id)

prompt = "The"

encoded = tokenizer.encode(prompt, add_special_tokens=False)
input_ids = torch.tensor([encoded.ids])

outputs = model.generate(
    input_ids,
    max_new_tokens=100,
    do_sample=True,
    temperature=0.8,
    top_k=40,
    top_p=0.6,
)
print(tokenizer.decode(outputs[0].tolist()))

```

## Training Details

### Training Data

Lightning was trained on the full [Booksum](https://huggingface.co/datasets/kmfoda/booksum) dataset.

### Training Procedure

Lightning was trained on an RTX 3050 GPU, using FlashAttention and MHA.
First, the model was initally trained on a large dataset. Then trained on a smaller dataset to fine tune.


#### Training Hyperparameters

| Hyperparameter | Value | Comment |
| :--- | :--- | :--- |
| Precision | FP32 | 
| Optimizer | AdamW | Better weight decay
| Learning rate | 5e-4 | 
| Batch size | 32 | Adapted for larger dataset 



## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** RTX 3050 6GB
- **Hours used:** 1.5
- **Cloud Provider:** My Computer
- **Compute Region:** Asia
- **Carbon Emitted:** 0.06 kg CO₂e

## Technical Specifications

### Model Architecture and Objective

Lightning is a casual decoder model which is autoregressive.

| Hyperparameter | Value | Comment |
| :--- | :--- | :--- |
| Layers | 4 | 
| D_MODEL | 256 | Optimized for 64dim/head
| Attention Heads | 4 |
| Vocabulary | ~50000 |  w/ 160 Sequence length

### Compute Infrastructure


#### Hardware

RTX 3050 6GB

#### Software

Windows 11, Intel i5-10400