# Arvixgpt
## Step 1:
run the python script ArXixLatestArticle.py
```python
python Arvixgpt.py
```
then, select Please select one or more prefix. This line of code helps you to
search the article by title, author, abstract, comment, journal reference,...
## Step 2:
```text
Please select one or more prefix codes:
Explanation: prefix
Title: ti
Author: au
Abstract: abs
Comment: co
Journal Reference: jr
Subject Category: cat
Report Number: rn
Id (use id_list instead): id
All of the above: all
Please enter one or more prefix codes (separated by a comma if more than one): ti,au
```
## Step 3:
````text
## Below is our output example for our Summary:
```text
Title: A Comprehensive Overview of Large Language Models
Summary:
Large Language Models (LLMs) have shown excellent generalization capabilities
that have led to the development of numerous models. These models propose
various new architectures, tweaking existing architectures with refined
training strategies, increasing context length, using high-quality training
data, and increasing training time to outperform baselines. Analyzing new
developments is crucial for identifying changes that enhance training stability
and improve generalization in LLMs. This survey paper comprehensively analyses
the LLMs architectures and their categorization, training strategies, training
datasets, and performance evaluations and discusses future research directions.
Moreover, the paper also discusses the basic building blocks and concepts
behind LLMs, followed by a complete overview of LLMs, including their important
features and functions. Finally, the paper summarizes significant findings from
LLM research and consolidates essential architectural and training strategies
for developing advanced LLMs. Given the continuous advancements in LLMs, we
intend to regularly update this paper by incorporating new sections and
featuring the latest LLM models.
PDF URL: http://arxiv.org/pdf/2307.06435v1
Authors: [arxiv.Result.Author('Humza Naveed'), arxiv.Result.Author('Asad Ullah Khan'), arxiv.Result.Author('Shi Qiu'), arxiv.Result.Author('Muhammad Saqib'), arxiv.Result.Author('Saeed Anwar'), arxiv.Result.Author('Muhammad Usman'), arxiv.Result.Author('Nick Barnes'), arxiv.Result.Author('Ajmal Mian')]
````
Raw data
{
"_id": null,
"home_page": "",
"name": "Arvixgpt",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "python,pandas,numpy,request,PyPDF2",
"author": "Ali Nemati and AI Team",
"author_email": "<Alinemati1983@gmail.com>",
"download_url": "",
"platform": null,
"description": "\n# Arvixgpt\n\n\n\n## Step 1:\n\n\n\nrun the python script ArXixLatestArticle.py\n\n\n\n```python\n\npython Arvixgpt.py\n\n```\n\n\n\nthen, select Please select one or more prefix. This line of code helps you to\n\nsearch the article by title, author, abstract, comment, journal reference,...\n\n\n\n## Step 2:\n\n\n\n```text\n\nPlease select one or more prefix codes:\n\nExplanation: prefix\n\nTitle: ti\n\nAuthor: au\n\nAbstract: abs\n\nComment: co\n\nJournal Reference: jr\n\nSubject Category: cat\n\nReport Number: rn\n\nId (use id_list instead): id\n\nAll of the above: all\n\n\n\nPlease enter one or more prefix codes (separated by a comma if more than one): ti,au\n\n\n\n```\n\n\n\n## Step 3:\n\n\n\n````text\n\n\n\n## Below is our output example for our Summary:\n\n\n\n```text\n\nTitle:\tA Comprehensive Overview of Large Language Models\n\nSummary:\n\nLarge Language Models (LLMs) have shown excellent generalization capabilities\n\nthat have led to the development of numerous models. These models propose\n\nvarious new architectures, tweaking existing architectures with refined\n\ntraining strategies, increasing context length, using high-quality training\n\ndata, and increasing training time to outperform baselines. Analyzing new\n\ndevelopments is crucial for identifying changes that enhance training stability\n\nand improve generalization in LLMs. This survey paper comprehensively analyses\n\nthe LLMs architectures and their categorization, training strategies, training\n\ndatasets, and performance evaluations and discusses future research directions.\n\nMoreover, the paper also discusses the basic building blocks and concepts\n\nbehind LLMs, followed by a complete overview of LLMs, including their important\n\nfeatures and functions. Finally, the paper summarizes significant findings from\n\nLLM research and consolidates essential architectural and training strategies\n\nfor developing advanced LLMs. Given the continuous advancements in LLMs, we\n\nintend to regularly update this paper by incorporating new sections and\n\nfeaturing the latest LLM models.\n\n\n\nPDF URL:\thttp://arxiv.org/pdf/2307.06435v1\n\nAuthors:\t[arxiv.Result.Author('Humza Naveed'), arxiv.Result.Author('Asad Ullah Khan'), arxiv.Result.Author('Shi Qiu'), arxiv.Result.Author('Muhammad Saqib'), arxiv.Result.Author('Saeed Anwar'), arxiv.Result.Author('Muhammad Usman'), arxiv.Result.Author('Nick Barnes'), arxiv.Result.Author('Ajmal Mian')]\n\n````\n\n",
"bugtrack_url": null,
"license": "",
"summary": "Search for updated article on arXiv.org",
"version": "0.0.0.3",
"project_urls": null,
"split_keywords": [
"python",
"pandas",
"numpy",
"request",
"pypdf2"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "64a1bd359a371005154affba01ea44a188eaad6f4ab7fd2d9ae85d6059eac7c6",
"md5": "7bdfcf39acb6c238d6acb30b35925fd0",
"sha256": "fc26d1cf9d344b8445a720977ffb06c6474574fbe1993ba9e88390eccacf5074"
},
"downloads": -1,
"filename": "Arvixgpt-0.0.0.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "7bdfcf39acb6c238d6acb30b35925fd0",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 2350,
"upload_time": "2023-07-21T06:40:46",
"upload_time_iso_8601": "2023-07-21T06:40:46.144090Z",
"url": "https://files.pythonhosted.org/packages/64/a1/bd359a371005154affba01ea44a188eaad6f4ab7fd2d9ae85d6059eac7c6/Arvixgpt-0.0.0.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-07-21 06:40:46",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "arvixgpt"
}
JSON