diff --git a/LICENSE b/LICENSE
new file mode 100644
index 0000000000000000000000000000000000000000..d9a10c0d8e868ebf8da0b3dc95bb0be634c34bfe
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,176 @@
+ Apache License
+ Version 2.0, January 2004
+ http://www.apache.org/licenses/
+
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+ 1. Definitions.
+
+ "License" shall mean the terms and conditions for use, reproduction,
+ and distribution as defined by Sections 1 through 9 of this document.
+
+ "Licensor" shall mean the copyright owner or entity authorized by
+ the copyright owner that is granting the License.
+
+ "Legal Entity" shall mean the union of the acting entity and all
+ other entities that control, are controlled by, or are under common
+ control with that entity. For the purposes of this definition,
+ "control" means (i) the power, direct or indirect, to cause the
+ direction or management of such entity, whether by contract or
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
+ outstanding shares, or (iii) beneficial ownership of such entity.
+
+ "You" (or "Your") shall mean an individual or Legal Entity
+ exercising permissions granted by this License.
+
+ "Source" form shall mean the preferred form for making modifications,
+ including but not limited to software source code, documentation
+ source, and configuration files.
+
+ "Object" form shall mean any form resulting from mechanical
+ transformation or translation of a Source form, including but
+ not limited to compiled object code, generated documentation,
+ and conversions to other media types.
+
+ "Work" shall mean the work of authorship, whether in Source or
+ Object form, made available under the License, as indicated by a
+ copyright notice that is included in or attached to the work
+ (an example is provided in the Appendix below).
+
+ "Derivative Works" shall mean any work, whether in Source or Object
+ form, that is based on (or derived from) the Work and for which the
+ editorial revisions, annotations, elaborations, or other modifications
+ represent, as a whole, an original work of authorship. For the purposes
+ of this License, Derivative Works shall not include works that remain
+ separable from, or merely link (or bind by name) to the interfaces of,
+ the Work and Derivative Works thereof.
+
+ "Contribution" shall mean any work of authorship, including
+ the original version of the Work and any modifications or additions
+ to that Work or Derivative Works thereof, that is intentionally
+ submitted to Licensor for inclusion in the Work by the copyright owner
+ or by an individual or Legal Entity authorized to submit on behalf of
+ the copyright owner. For the purposes of this definition, "submitted"
+ means any form of electronic, verbal, or written communication sent
+ to the Licensor or its representatives, including but not limited to
+ communication on electronic mailing lists, source code control systems,
+ and issue tracking systems that are managed by, or on behalf of, the
+ Licensor for the purpose of discussing and improving the Work, but
+ excluding communication that is conspicuously marked or otherwise
+ designated in writing by the copyright owner as "Not a Contribution."
+
+ "Contributor" shall mean Licensor and any individual or Legal Entity
+ on behalf of whom a Contribution has been received by Licensor and
+ subsequently incorporated within the Work.
+
+ 2. Grant of Copyright License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ copyright license to reproduce, prepare Derivative Works of,
+ publicly display, publicly perform, sublicense, and distribute the
+ Work and such Derivative Works in Source or Object form.
+
+ 3. Grant of Patent License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ (except as stated in this section) patent license to make, have made,
+ use, offer to sell, sell, import, and otherwise transfer the Work,
+ where such license applies only to those patent claims licensable
+ by such Contributor that are necessarily infringed by their
+ Contribution(s) alone or by combination of their Contribution(s)
+ with the Work to which such Contribution(s) was submitted. If You
+ institute patent litigation against any entity (including a
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
+ or a Contribution incorporated within the Work constitutes direct
+ or contributory patent infringement, then any patent licenses
+ granted to You under this License for that Work shall terminate
+ as of the date such litigation is filed.
+
+ 4. Redistribution. You may reproduce and distribute copies of the
+ Work or Derivative Works thereof in any medium, with or without
+ modifications, and in Source or Object form, provided that You
+ meet the following conditions:
+
+ (a) You must give any other recipients of the Work or
+ Derivative Works a copy of this License; and
+
+ (b) You must cause any modified files to carry prominent notices
+ stating that You changed the files; and
+
+ (c) You must retain, in the Source form of any Derivative Works
+ that You distribute, all copyright, patent, trademark, and
+ attribution notices from the Source form of the Work,
+ excluding those notices that do not pertain to any part of
+ the Derivative Works; and
+
+ (d) If the Work includes a "NOTICE" text file as part of its
+ distribution, then any Derivative Works that You distribute must
+ include a readable copy of the attribution notices contained
+ within such NOTICE file, excluding those notices that do not
+ pertain to any part of the Derivative Works, in at least one
+ of the following places: within a NOTICE text file distributed
+ as part of the Derivative Works; within the Source form or
+ documentation, if provided along with the Derivative Works; or,
+ within a display generated by the Derivative Works, if and
+ wherever such third-party notices normally appear. The contents
+ of the NOTICE file are for informational purposes only and
+ do not modify the License. You may add Your own attribution
+ notices within Derivative Works that You distribute, alongside
+ or as an addendum to the NOTICE text from the Work, provided
+ that such additional attribution notices cannot be construed
+ as modifying the License.
+
+ You may add Your own copyright statement to Your modifications and
+ may provide additional or different license terms and conditions
+ for use, reproduction, or distribution of Your modifications, or
+ for any such Derivative Works as a whole, provided Your use,
+ reproduction, and distribution of the Work otherwise complies with
+ the conditions stated in this License.
+
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
+ any Contribution intentionally submitted for inclusion in the Work
+ by You to the Licensor shall be under the terms and conditions of
+ this License, without any additional terms or conditions.
+ Notwithstanding the above, nothing herein shall supersede or modify
+ the terms of any separate license agreement you may have executed
+ with Licensor regarding such Contributions.
+
+ 6. Trademarks. This License does not grant permission to use the trade
+ names, trademarks, service marks, or product names of the Licensor,
+ except as required for reasonable and customary use in describing the
+ origin of the Work and reproducing the content of the NOTICE file.
+
+ 7. Disclaimer of Warranty. Unless required by applicable law or
+ agreed to in writing, Licensor provides the Work (and each
+ Contributor provides its Contributions) on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+ implied, including, without limitation, any warranties or conditions
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+ PARTICULAR PURPOSE. You are solely responsible for determining the
+ appropriateness of using or redistributing the Work and assume any
+ risks associated with Your exercise of permissions under this License.
+
+ 8. Limitation of Liability. In no event and under no legal theory,
+ whether in tort (including negligence), contract, or otherwise,
+ unless required by applicable law (such as deliberate and grossly
+ negligent acts) or agreed to in writing, shall any Contributor be
+ liable to You for damages, including any direct, indirect, special,
+ incidental, or consequential damages of any character arising as a
+ result of this License or out of the use or inability to use the
+ Work (including but not limited to damages for loss of goodwill,
+ work stoppage, computer failure or malfunction, or any and all
+ other commercial damages or losses), even if such Contributor
+ has been advised of the possibility of such damages.
+
+ 9. Accepting Warranty or Additional Liability. While redistributing
+ the Work or Derivative Works thereof, You may choose to offer,
+ and charge a fee for, acceptance of support, warranty, indemnity,
+ or other liability obligations and/or rights consistent with this
+ License. However, in accepting such obligations, You may act only
+ on Your own behalf and on Your sole responsibility, not on behalf
+ of any other Contributor, and only if You agree to indemnify,
+ defend, and hold each Contributor harmless for any liability
+ incurred by, or claims asserted against, such Contributor by reason
+ of your accepting any such warranty or additional liability.
+
+ END OF TERMS AND CONDITIONS
diff --git a/README.md b/README.md
index 66a8a726bcbaa30fd0f252a4747a24d578587268..d426eed8da1f7987403f508faace51e76d863046 100644
--- a/README.md
+++ b/README.md
@@ -1,26 +1,39 @@
# Optimus Prime
-Implementation of the Transformer architecture and different variations on it,
-as well as the training loop, written from scratch in PyTorch.
+(Yet another) PyTorch framework for training large language models.
-Most of the code is easy to read and should be self-explanatory, as it is
-documented.
+## How to use
-There is an example of how to use the 'framework' in
-`optimus/example_training.py`.
+### Training
-## Training a custom model with a custom dataset
+An example on how to use the framework can be found in `training.py`. Feel free
+to adapt as needed. Also see [Custom training](#custom-training).
-The requirements to train a model of a custom size from scratch are:
-1. Get a dataset from wherever, and process it to work with the other components
- of the 'framework'. See `optimus/datasets/wikitext103.py` for an example.
-2. Create a tokenizer for the model, or use the existing LLama 2 tokenizer
- (`optimus/llama32K.model`). To create a tokenizer, see
- `optimus/tokenizer.py`. Creating a tokenizer requires a dataset ready.
-3. Create the model, and specify the training parameters (see
- `optimus/example_training.py` for an example of what options you can
- provide). Additionally, `optimus/trainer.py` can be directly modified, for
- options currently not exposed through an interface.
+### Inference
+
+After training a model (or getting hold of one from other sources), there's an
+example on how to run inference can be found in `inference.py`. Feel free to
+adapt as needed.
+
+## Basic building blocks
+
+As its parent PyTorch, the framework is split between a number of modules. The
+most important modules are the `OptimusDataLoader`, the `Dataset`s, the
+`Trainer`, the tokenizers and the models. These can be combined and adapted in
+any way, shape or form to train a model from scratch.
+
+## Custom training
+
+The usual workflow for a user is to create and train a tokenizer (see
+`optimus/tokenizers` for an example), model a dataset (see `optimus/datasets`
+for an example), create a model architecture (see `optimus/models` as an
+example) and use the data loader and the trainer modules to train the model. The
+`Trainer` module has a number of useful options which can be used during
+training (mixed precision training, checkpointing, gradient accumulation,
+plotting the training loss etc.; see `optimus/trainer.py` for what the Trainer
+is capable of).
+
+Of course, any number of the above can be used as defaults.
> [!TIP]
> You can choose which GPU's to train on, using the environment variable
@@ -29,7 +42,11 @@ The requirements to train a model of a custom size from scratch are:
## Required packages
-There are a number of packages required to run the thing. Get your closest
+There are a number of packages required to run the framework. Get your closest
Python retailer and ask him to run the following command:
`pip install torch fire sentencepiece fastprogress matplotlib`
+
+## License
+
+See [LICENSE](LICENSE).
diff --git a/optimus/llama32K.model b/llama32K.model
similarity index 100%
rename from optimus/llama32K.model
rename to llama32K.model
diff --git a/optimus/dataloader.py b/optimus/dataloader.py
index b1e00c961547fdd071d294743b8545636833f823..7bcd74ee52ce2d5f5e35215db751ca6f899a1709 100644
--- a/optimus/dataloader.py
+++ b/optimus/dataloader.py
@@ -6,7 +6,7 @@ import torch
from torch import Tensor
from torch.utils.data import Dataset
-from tokenizer import Tokenizer
+from optimus.tokenizers import SentencePieceTokenizer
class _OptimusDLIter(Iterator):
@@ -113,7 +113,7 @@ class OptimusDataLoader():
def __init__(self,
train_ds: Dataset,
test_ds: Dataset,
- tok: Tokenizer,
+ tok: SentencePieceTokenizer,
bs: int,
seq_len: int,
shuffle: bool = True,
@@ -132,7 +132,7 @@ class OptimusDataLoader():
Args:
train_ds (Dataset): The training dataset.
test_ds (Dataset): The testing dataset.
- tok (Tokenizer): Tokenizer to use.
+ tok (SentencePieceTokenizer): Tokenizer to use.
bs (int): Batch size. The number of samples per batch to load.
seq_len (int): Sequence length. Also referred to as context length.
shuffle (bool): Whether to shuffle the training data before
diff --git a/optimus/datasets/__init__.py b/optimus/datasets/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..0d9084efadeafaf1e00c798a57ffa82c4a299c4c
--- /dev/null
+++ b/optimus/datasets/__init__.py
@@ -0,0 +1,2 @@
+from .tinystories import TinyStoriesDataset
+from .wikitext103 import WikiText103Dataset
diff --git a/optimus/datasets/tinystories.py b/optimus/datasets/tinystories.py
index 4928a20bda06587f0ce86cedce6f1e9e32f40ad8..ba895677b3f3a5418f3730615346efbeb7b52198 100644
--- a/optimus/datasets/tinystories.py
+++ b/optimus/datasets/tinystories.py
@@ -2,7 +2,7 @@ import os
from torch.utils.data import Dataset, DataLoader
-from datasets.dataset_utils import *
+from .dataset_utils import *
URL = {
diff --git a/optimus/datasets/wikitext103.py b/optimus/datasets/wikitext103.py
index 2743c61e7b7f4b5b293d16e776f22ba9fff05f51..62229c4cf6ec09a2deacddbf012a8b96568db47d 100644
--- a/optimus/datasets/wikitext103.py
+++ b/optimus/datasets/wikitext103.py
@@ -3,7 +3,7 @@ import re
from torch.utils.data import Dataset, DataLoader
-from datasets.dataset_utils import *
+from .dataset_utils import *
URL = 'https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-103-v1.zip'
diff --git a/optimus/models/__init__.py b/optimus/models/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..ce35655a73bbb58ebef9b2c672180e023763e737
--- /dev/null
+++ b/optimus/models/__init__.py
@@ -0,0 +1 @@
+from .optimus import OptimusTransformer
diff --git a/optimus/model.py b/optimus/models/optimus.py
similarity index 99%
rename from optimus/model.py
rename to optimus/models/optimus.py
index 5a432655c81579bcc42b0b001db2750bd8d0d735..36ce3b08e834d56658c824469f505da6a5ec04b5 100644
--- a/optimus/model.py
+++ b/optimus/models/optimus.py
@@ -155,7 +155,7 @@ class TransformerBlock(nn.Module):
return x
-class Transformer(nn.Module):
+class OptimusTransformer(nn.Module):
def __init__(self,
vocab_sz: int,
dim: int = 512,
diff --git a/optimus/tokenizers/__init__.py b/optimus/tokenizers/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..aee6674dbd4384a2df2a3bbce6e31195e4960177
--- /dev/null
+++ b/optimus/tokenizers/__init__.py
@@ -0,0 +1 @@
+from .sentencepiece import SentencePieceTokenizer
diff --git a/optimus/tokenizer.py b/optimus/tokenizers/sentencepiece.py
similarity index 96%
rename from optimus/tokenizer.py
rename to optimus/tokenizers/sentencepiece.py
index 0a9ac95a337941ad3f732fcaa89d881f50eb8ca0..6d9a8068cf260ec88a892ff255f23df0736a4cbc 100644
--- a/optimus/tokenizer.py
+++ b/optimus/tokenizers/sentencepiece.py
@@ -5,7 +5,7 @@ from collections.abc import Iterable
import sentencepiece as spm
-class Tokenizer():
+class SentencePieceTokenizer():
def __init__(self, model_path: str = 'optimus.model'):
"""
SentencePiece tokenizer.
@@ -125,10 +125,10 @@ if __name__=='__main__':
filename = './wikitext-103/wiki.train.tokens'
with open(filename, 'r') as f:
lines = f.readlines()
- Tokenizer.train(iter(lines), vocab_size=16000)
+ SentencePieceTokenizer.train(iter(lines), vocab_size=16000)
else:
- tok = Tokenizer(model_path='./optimus.model')
+ tok = SentencePieceTokenizer(model_path='./optimus.model')
print(len(tok))
print(tok.encode("this is some sunny day", False, True))
print(tok.encode_as_pieces("this is some sunny day"))
diff --git a/optimus/trainer.py b/optimus/trainer.py
index 626c214da88c086071c6f27f2bf77adcbfc79223..abfbaafa2bdf7d0c59bde5c9d1848d8315c4affd 100644
--- a/optimus/trainer.py
+++ b/optimus/trainer.py
@@ -7,7 +7,8 @@ import torch.nn as nn
import torch.optim as optim
from fastprogress.fastprogress import master_bar, progress_bar, format_time
-from dataloader import OptimusDataLoader
+from optimus.dataloader import OptimusDataLoader
+from fastprogress.fastprogress import master_bar, progress_bar, format_time
class Trainer():
diff --git a/optimus/optimus16K-wikitext103.model b/optimus16K-wikitext103.model
similarity index 100%
rename from optimus/optimus16K-wikitext103.model
rename to optimus16K-wikitext103.model
diff --git a/optimus/optimus60K-wikitext103.model b/optimus60K-wikitext103.model
similarity index 100%
rename from optimus/optimus60K-wikitext103.model
rename to optimus60K-wikitext103.model
diff --git a/optimus/example_training.py b/training.py
similarity index 86%
rename from optimus/example_training.py
rename to training.py
index 9bfed385050375712931ced5b290d8d8c2f0d390..3efbfd21d7813266790faab6f789fa8d4d8a3d5a 100644
--- a/optimus/example_training.py
+++ b/training.py
@@ -2,11 +2,11 @@ import fire
import torch
from torch import nn
-from datasets.wikitext103 import WikiText103Dataset
-from tokenizer import Tokenizer
-from dataloader import OptimusDataLoader
-from model import Transformer
-from trainer import Trainer
+from optimus.datasets import WikiText103Dataset
+from optimus.tokenizers import SentencePieceTokenizer
+from optimus.dataloader import OptimusDataLoader
+from optimus.models import OptimusTransformer
+from optimus.trainer import Trainer
def main(batch_size: int = 8,
@@ -62,7 +62,7 @@ def main(batch_size: int = 8,
f"Please see '--help' if you want to change these settings")
# load tokenizer
- tok = Tokenizer(model_path=tokenizer_path)
+ tok = SentencePieceTokenizer(model_path=tokenizer_path)
# load dataset splits
train_ds = WikiText103Dataset(split='train')
@@ -78,12 +78,12 @@ def main(batch_size: int = 8,
device=device)
# create model and move to device
- model = Transformer(len(tok),
- n_layers=n_layers,
- dim=dim,
- n_heads=n_heads,
- p_drop=dropout,
- weight_tying=False)
+ model = OptimusTransformer(len(tok),
+ n_layers=n_layers,
+ dim=dim,
+ n_heads=n_heads,
+ p_drop=dropout,
+ weight_tying=False)
model = model.to(device)
_total_params = sum(p.numel() for p in model.parameters())