90 lines
2.6 KiB
Markdown
90 lines
2.6 KiB
Markdown
---
|
|
license: mit
|
|
datasets:
|
|
- lennart-finke/SimpleStories
|
|
language:
|
|
- en
|
|
tags:
|
|
- small-language-model
|
|
- story-generation
|
|
- text-generation
|
|
- efficient-nlp
|
|
- distilled-models
|
|
---
|
|
|
|
# SimpleStories Model Family
|
|
The SimpleStories models are a tiny model family created for interpretability research, trained on the [SimpleStories dataset](https://huggingface.co/datasets/lennart-finke/SimpleStories).
|
|
|
|
## Usage
|
|
|
|
```python
|
|
import torch
|
|
from transformers import AutoTokenizer, LlamaForCausalLM
|
|
|
|
|
|
MODEL_SIZE = "35M"
|
|
model_path = "SimpleStories/SimpleStories-{}".format(MODEL_SIZE)
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
|
model = LlamaForCausalLM.from_pretrained(model_path)
|
|
model.to("cuda")
|
|
model.eval()
|
|
|
|
prompt = "The curious cat looked at the"
|
|
|
|
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
|
|
input_ids = inputs.input_ids.to("cuda")
|
|
|
|
eos_token_id = 1
|
|
|
|
with torch.no_grad():
|
|
output_ids = model.generate(
|
|
input_ids=input_ids,
|
|
max_new_tokens=400,
|
|
temperature=0.7,
|
|
do_sample=True,
|
|
eos_token_id=eos_token_id
|
|
)
|
|
|
|
output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
|
|
print(f"\nGenerated text:\n{output_text}")
|
|
|
|
```
|
|
|
|
## Model Variants
|
|
|
|
| Model Name | n_params | n_layers | d_model | n_heads | n_ctx | d_vocab |
|
|
|------------|----------|----------|---------|---------|-------|---------|
|
|
| SimpleStories-35M | 35 million | 12 | 512 | 8 | 512 | 4096 |
|
|
| SimpleStories-30M | 30 million | 10 | 512 | 8 | 512 | 4096 |
|
|
| SimpleStories-11M | 11 million | 6 | 384 | 6 | 512 | 4096 |
|
|
| SimpleStories-5M | 5 million | 6 | 256 | 4 | 512 | 4096 |
|
|
| SimpleStories-1.25M | 1.25 million | 4 | 128 | 4 | 512 | 4096 |
|
|
|
|
## Performance Comparison
|
|
Model-evaluated generation quality metrics:
|
|
<p align="center">
|
|
<img width="80%" src="figures/simplestories_comparison.png">
|
|
</p>
|
|
|
|
|
|
## Tokenizer
|
|
|
|
We use a custom WordPiece tokenizer with a small vocabulary size of 4096. We conducted morphological analysis and coverage gain analysis on the dataset
|
|
to build a small tokenizer without compromising on the quality of generation.
|
|
|
|
## Dataset
|
|
|
|
The SimpleStories dataset is a collection of short stories generated by state-of-the-art language models. It features:
|
|
|
|
- Story annotation with high-level concepts: theme, topic, style, etc.
|
|
- Higher semantic and syntactic diversity through seeded story generation
|
|
- Generated by 2024 models
|
|
- Several NLP-metrics pre-computed to aid filtering
|
|
- ASCII-only guarantee for the English dataset
|
|
|
|
Read the dataset paper on [arXiv](https://arxiv.org/abs/2504.09184).
|
|
|
|
## Training
|
|
The training and evaluation scripts can be accessed at https://github.com/danbraunai/simple_stories_train
|