manta-lm-base / README.md
nthngdy's picture
Create README.md
021ebfc
|
raw
history blame
2.75 kB
---
license: apache-2.0
language:
- en
pipeline_tag: text2text-generation
---
# MANTa-LM (base)
Pretrained MANTa-LM architecture as introduced in the paper [MANTa: Efficient Gradient-Based Tokenization for Robust End-to-End Language Modeling](https://aclanthology.org/2022.findings-emnlp.207.pdf).
<center><img src="https://github.com/NathanGodey/nathangodey.github.io/raw/main/img/posts/full_difftok_schema.png" width="600"></center>
## Model Details
### Model Description
The MANTa tokenizer aims at mimicking the combination of a subword tokenizer and an embedding matrix in a classical language model in a differentiable way.
This trainable tokenizer is thus added as the first layer of an encoder-decoder model and trained using the language modeling objective.
Our results show that MANTa-LM only slightly degrades the performance of a T5 equivalent on the GLUE benchmark while being **much more robust** to artificial and user-generated noise.
### Model Sources
- **Paper:** [MANTa: Efficient Gradient-Based Tokenization for Robust End-to-End Language Modeling](https://aclanthology.org/2022.findings-emnlp.207.pdf) (EMNLP 2022 Findings)
## Uses
### Direct Use
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("google/byt5-base")
manta_model = AutoModelForSeq2SeqLM.from_pretrained("almanach/manta-lm-base", trust_remote_code=True)
tokens = tokenizer("The name of the capital of France is <extra_id_0> and it is a very big city.", return_tensors="pt")
output = manta_model.generate(**tokens, decoder_start_token_id=0)
print(tokenizer.batch_decode(output))
```
### Recommendations
We recommend using a smaller learning rate for the tokenizer module during fine-tuning (byte embeddings, frontier predictor, pooler).
## Training Details
### Training Data
This model was trained on the C4 dataset.
### Training Procedure
The training objective is the same as ByT5, but most hyperparameters are taken from T5.
## Citation
**BibTeX:**
```
@inproceedings{godey-etal-2022-manta,
title = "{MANT}a: Efficient Gradient-Based Tokenization for End-to-End Robust Language Modeling",
author = "Godey, Nathan and
Castagn{\'e}, Roman and
de la Clergerie, {\'E}ric and
Sagot, Beno{\^\i}t",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.207",
pages = "2859--2870",
}
```
## Model Card Authors
[Nathan Godey](https://nathangodey.github.io/)
[Roman Castagné](https://romancast.github.io/)