Atom
Atom is a finetuned LLAMA to create better LLMS through Pytorch Data!
Installation
You can install the package using pip
git clone https://github.com/jquesnelle/yarn
cd Atom
pip install -e .
Training
To train the models, run accelerate config and enable DeepSpeed acceleration. deepspeed/zero3.json was the configuration file used for training.
# ./train.sh
The tokenized training data is available on Hugging Face and was derived from the pg19 dataset.
Evaluation
To reproduce the evaluations, install lm-evaluation-harness with pip install git+https://github.com/EleutherAI/lm-evaluation-harness and then run the two provided scripts.
# ./eval.sh
# ./eval-harness.sh
Citation
@misc{peng2023yarn,
title={YaRN: Efficient Context Window Extension of Large Language Models},
author={Bowen Peng and Jeffrey Quesnelle and Honglu Fan and Enrico Shippole},
year={2023},
eprint={2309.00071},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
1 maintainer
Metadata
1 maintainer
Release files for atom-torch 0.0.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| atom_torch-0.0.2.tar.gz | 32.2 kB | Without provenance | Details for atom_torch-0.0.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| atom_torch-0.0.2-py3-none-any.whl | Python 3 | none | any | Details for atom_torch-0.0.2-py3-none-any.whl |
Total release size: 65.8 kB
Release files / atom_torch-0.0.2.tar.gz
| Download URL | atom_torch-0.0.2.tar.gz |
|---|---|
| Size | 32.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6483a3a259491dbd88348fc14a657adf7c53e4f387bd3ecb7de4d21192a0ab76
|
|
BLAKE2b-256 checksum How to use checksums |
c31fa948e5d9423c4b929246d79e49e91cc29132ca714a2cff2baeda30be09d6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.3.2 CPython/3.11.0 Darwin/22.4.0
|
Release files / atom_torch-0.0.2-py3-none-any.whl
| Download URL | atom_torch-0.0.2-py3-none-any.whl |
|---|---|
| Size | 33.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2ebe961645855f9a97a204bc4b0bf3ccdb1a3a643a37ec39edb4f90702c79800
|
|
BLAKE2b-256 checksum How to use checksums |
80f46c4c5f1a17aa98a8040e7b40bf27b944c75eab06d3650f7113b3692607c1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.3.2 CPython/3.11.0 Darwin/22.4.0
|
Security for atom-torch 0.0.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
