https://github.com/aisuko/notebooks
Implementation for the different ML tasks on Kaggle platform with GPUs.
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (12.3%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
Implementation for the different ML tasks on Kaggle platform with GPUs.
Basic Info
- Host: GitHub
- Owner: Aisuko
- License: apache-2.0
- Language: Jupyter Notebook
- Default Branch: main
- Homepage: https://www.kaggle.com/aisuko/code
- Size: 159 MB
Statistics
- Stars: 24
- Watchers: 2
- Forks: 4
- Open Issues: 0
- Releases: 0
Topics
Metadata Files
README.md
Overview
We might agree that the operation of LLMs will embed in daily programming in the future. So, we use these notebooks to familiarize ourselves with the LLMs tools ecosystem and quantization techniques. I believe that Cloud quantum computing is needed for the future of LLMs. Maybe somthing Qubernetes.
All these notebooks have been completed running on the Kaggle platform. With the free GPUs. Some of the notebooks use a single GPU P100, some of notebooks use double GPU T4x2, others use CPUs.
Note: Some of the large size notebooks like Topic Modeling with BERTopic may not be able to show the complete version on the preview of Github. You can open it in the Kaggle platform by clicking the link in the notebook's title.
This project is interested in
I want to use of deep neural networks to do GenAI on consumer-grade hardware for researching.
The ML tasks are covered in this project
This project's notebooks are covering the following some of the following tasks:
The LLMs are used in this project
The some of LLMs are used in this project are as follows:
Metrics of fine-tuning
Note: All the fine-tuning here is under the limited computing resource, so the metrics are not the best. Most of reasons are
num_train_epochsis not enough. However, the fine-tuning process is the same as the normal process.
And you can check the metrics of the fine-tuning in wandb.ai. It includes many of useful metrics, like: training, evaling, system power usage, like below:
LLMs tools are used in this project
The tools we covered in this project are as follows:
Quantization techniques are used in this project
The quantization techniques we used in this project are as follows:
The Concepts From Papers We Should Know
License
Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. See the LICENSE file for details.
Credits
Many of the notebooks are based on articles on Medium, TheNewStack, Huggingface and other open-source projects etc. Thanks for these great works.
Owner
- Name: Bowen
- Login: Aisuko
- Kind: user
- Location: Global
- Company: RMIT
- Twitter: AisukoLi
- Repositories: 70
- Profile: https://github.com/Aisuko
Member of the GNU Hurd | previously @rancher | Founder of @SkywardAI | PhD candidate at RMIT
GitHub Events
Total
- Watch event: 9
- Push event: 53
Last Year
- Watch event: 9
- Push event: 53
Committers
Last synced: 8 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Aisuko | u****y@g****m | 698 |
| Rob Zhang | z****t@g****m | 20 |
| wangyuweikiwi | 1****i | 10 |
| ImgBotApp | I****p@g****m | 4 |
Issues and Pull Requests
Last synced: 8 months ago
All Time
- Total issues: 2
- Total pull requests: 8
- Average time to close issues: 13 days
- Average time to close pull requests: 23 days
- Total issue authors: 2
- Total pull request authors: 3
- Average comments per issue: 1.5
- Average comments per pull request: 0.0
- Merged pull requests: 6
- Bot issues: 0
- Bot pull requests: 6
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- FelixStarship (1)
- captraj (1)
Pull Request Authors
- imgbot[bot] (10)
- Aisuko (4)
- stack-file[bot] (2)