transformers-explained
官方transformers源码解析。AI大模型时代,pytorch、transformer是新操作系统,其他都是运行在其上面的软件。
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (1.7%) to scientific vocabulary
Keywords
transformers
Last synced: 6 months ago
·
JSON representation
·
Repository
官方transformers源码解析。AI大模型时代,pytorch、transformer是新操作系统,其他都是运行在其上面的软件。
Basic Info
Statistics
- Stars: 13
- Watchers: 1
- Forks: 1
- Open Issues: 0
- Releases: 0
Topics
transformers
Created over 2 years ago
· Last pushed over 2 years ago
Metadata Files
Readme
Contributing
License
Code of conduct
Citation
README.md
HFs-transformers-Explained
官方transformers源码解析。AI大模型时代,pytorch、transformer是新操作系统,其他都是运行在其上面的软件。
- modeling_llama.py/
- fine-tune.py/
- class ModelArguments : const modelnameor_path
- class DataArguments : const data_path
- class TrainingArguments : const cachedir、const optim、const modelmaxlength、 const uselora、
- class SupervisedDataset
- func train
- web_demo.py/
./Baichuan2-13B-Chat/modelling_baichuan.py
- const logger
- func getinterleave
- func getinterleavepowerof_2
- func fillwithneginf
- func bufferedfuture_mask
- func genalibi_mask
- class RMSNorm
- func init
- func forward
- class MLP
- func init
- func init
- func _shape
- func forward
- class BaichuanLayer
- func init
- func forward
- class BaichuanPreTrainedModel
CSDN彩色博客版:
ChatGLM Efficient Tuning源码解析train_sft.py https://zengxiaojian.blog.csdn.net/article/details/131458667
引用 - 源项目
Owner
- Name: Dr. Artificial曾小健
- Login: ArtificialZeng
- Kind: user
- Location: Beijing
- Website: https://blog.csdn.net/sinat_37574187?type=blog
- Repositories: 171
- Profile: https://github.com/ArtificialZeng
LLM practitioner/engineer, AI/ML/DL Quant
Citation (CITATION.cff)
cff-version: "1.2.0"
date-released: 2020-10
message: "If you use this software, please cite it using these metadata."
title: "Transformers: State-of-the-Art Natural Language Processing"
url: "https://github.com/huggingface/transformers"
authors:
- family-names: Wolf
given-names: Thomas
- family-names: Debut
given-names: Lysandre
- family-names: Sanh
given-names: Victor
- family-names: Chaumond
given-names: Julien
- family-names: Delangue
given-names: Clement
- family-names: Moi
given-names: Anthony
- family-names: Cistac
given-names: Perric
- family-names: Ma
given-names: Clara
- family-names: Jernite
given-names: Yacine
- family-names: Plu
given-names: Julien
- family-names: Xu
given-names: Canwen
- family-names: "Le Scao"
given-names: Teven
- family-names: Gugger
given-names: Sylvain
- family-names: Drame
given-names: Mariama
- family-names: Lhoest
given-names: Quentin
- family-names: Rush
given-names: "Alexander M."
preferred-citation:
type: conference-paper
authors:
- family-names: Wolf
given-names: Thomas
- family-names: Debut
given-names: Lysandre
- family-names: Sanh
given-names: Victor
- family-names: Chaumond
given-names: Julien
- family-names: Delangue
given-names: Clement
- family-names: Moi
given-names: Anthony
- family-names: Cistac
given-names: Perric
- family-names: Ma
given-names: Clara
- family-names: Jernite
given-names: Yacine
- family-names: Plu
given-names: Julien
- family-names: Xu
given-names: Canwen
- family-names: "Le Scao"
given-names: Teven
- family-names: Gugger
given-names: Sylvain
- family-names: Drame
given-names: Mariama
- family-names: Lhoest
given-names: Quentin
- family-names: Rush
given-names: "Alexander M."
booktitle: "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations"
month: 10
start: 38
end: 45
title: "Transformers: State-of-the-Art Natural Language Processing"
year: 2020
publisher: "Association for Computational Linguistics"
url: "https://www.aclweb.org/anthology/2020.emnlp-demos.6"
address: "Online"
GitHub Events
Total
- Watch event: 7
- Fork event: 2
Last Year
- Watch event: 7
- Fork event: 2