LLM-Pruner: On the Structural Pruning of Large Language Models

Compress your LLMs to any size;


🖥 Github: https://github.com/horseee/llm-pruner

⏩ Paper: https://arxiv.org/abs/2305.11627v1

📌 Dataset: https://paperswithcode.com/dataset/piqa

@Machine_learn

QLoRA: Efficient Finetuning of Quantized LLMs

Model name Guanaco, outperforms all previous openly released models on the Vicuna benchmark, reaching 99.3% of the performance level of ChatGPT while only requiring 24 hours of finetuning on a single GPU.


🖥 Github: https://github.com/artidoro/qlora

⏩ Paper: https://arxiv.org/abs/2305.14314

⭐️ Demo: https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi

📌 Dataset: https://paperswithcode.com/dataset/ffhq

@Machine_learn

Hybrid and Collaborative Passage Reranking

🖥 Github: https://github.com/zmzhang2000/hybrank

⏩ Paper: https://arxiv.org/pdf/2305.09313v1.pdf

💨 Dataset: https://paperswithcode.com/dataset/natural-questions

@Machine_learn

Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles

Hiera is a hierarchical vision transformer that is fast, powerful, and, above all, simple. It outperforms the state-of-the-art across a wide array of image and video tasks while being much faster.

pip install hiera-transformer

🖥 Github: https://github.com/facebookresearch/hiera

⏩ Paper: https://arxiv.org/abs/2306.00989v1

📌 Dataset: https://paperswithcode.com/dataset/inaturalist

@Machine_learn

A Collection of 25 Awesome Python Scripts (mini projects)
#Python #Mini_Projects
@Machine_learn

با عرض سلام پکیچ های یادگیری ماشین و یادگیری عمیق رو برای دوستانی که نیاز دارن تخفیف۵۰٪ گذاشتیم در صورت نیاز به بنده اطلاع بدین.
@Raminmousa

🦍 Gorilla: Large Language Model Connected with Massive APIs

Gorilla a finetuned LLaMA-based model that surpasses the performance of GPT-4 on writing API calls.


🖥 Github: https://github.com/ShishirPatil/gorilla

📕 Paper: https://arxiv.org/abs/2305.15334

🔗 Demo: https://drive.google.com/file/d/1E0k5mG1mTiaz0kukyK1PdeohJipTFh6j/view?usp=share_link

👉 Project: https://shishirpatil.github.io/gorilla/

⭐️ Colab: https://colab.research.google.com/drive/1DEBPsccVLF_aUnmD0FwPeHFrtdC0QIUP?usp=sharing

@Machine_learn

Segment Anything 3D

SAM-3D: A toolbox transfers 2D SAM segments into 3D scene-level point clouds.

🖥 Github: https://github.com/pointcept/segmentanything3d

⏩ Paper: https://arxiv.org/abs/2306.03908v1

📌 Dataset: https://paperswithcode.com/dataset/scannet
@Machine_learn

TabEAE

🖥 Github: https://github.com/stardust-hyx/tabeae

⏩ Paper: https://arxiv.org/pdf/2306.00502v1.pdf

💨 Dataset: https://paperswithcode.com/dataset/wikievents

@Machine_learn

Data Science Cheat Sheet
Python Regular Expressions
#Python
#RE
@Machine_learn

Book: DATA SCIENCE INTERVIEW
GUIDE ACE-PREP
Authors: null
ISBN: 978-1-915002-10-5
year: 2022
pages: 136
Tags: #Data_Science
@Machine_learn

Semi-supervised learning made simple with self-supervised clustering [CVPR 2023]

🖥 Github: https://github.com/pietroastolfi/suave-daino

⏩ Paper: https://arxiv.org/pdf/2306.07483v1.pdf

💨 Dataset: https://paperswithcode.com/dataset/imagenet

@Machine_learn

https://www.globaldevelopment.dk/media/attachments/2021/07/31/practical-machine-learning-and-image-processing-1st-edition.pdf

Book: practical machine learning and image processing
year: 2019
Tags: #Data_Science #ML
@Machine_learn

🐼 PandaLM: ReProducible and Automated Language Model Assessment

Judge large language model, named PandaLM, which is trained to distinguish the superior model given several LLMs. PandaLM's focus extends beyond just the objective correctness of responses, which is the main focus of traditional evaluation datasets.

🖥 Github: https://github.com/weopenml/pandalm

📕 Paper: https://arxiv.org/abs/2306.05087v1

🔗 Dataset: https://github.com/tatsu-lab/stanford_alpaca#data-release

@Machine_learn

LabelBench: A Comprehensive Framework for Benchmarking Label-Efficient Learning

🖥 Github: https://github.com/efficienttraining/labelbench

⏩ Paper: https://arxiv.org/pdf/2306.09910v1.pdf

💨 Dataset: https://paperswithcode.com/dataset/cifar-10

@Machine_learn

30 Deep Learning Projects
With Datasets Details
@Machine_learn

CBOGlobalConvergenceAnalysis

🖥 Github: https://github.com/efficienttraining/labelbench

⏩ Paper: https://arxiv.org/pdf/2306.09778v1.pdf

@Machine_learn

🚶‍♂️ MotionGPT: Human Motion
as Foreign Language

MotionGPT consists of a motion tokenizer responsible for converting raw motion data into discrete motion tokens, as well as a motion-aware language model that learns to understand the motion tokens from large language pre-training models by corresponding textual descriptions.


⏩ Project: https://motion-gpt.github.io/

🖥 Github: https://github.com/openmotionlab/motiongpt

📕 Paper: https://arxiv.org/pdf/2306.14795.pdf

🔗Dataset: https://paperswithcode.com/dataset/amass

@Machine_learn

E‏yes estimation and tracking are important research issues in computer vision and human-computer interaction. In this paper, a transfer-based learning model is proposed for this purpose. In the proposed approach, the two ResNet50 networks, whose initial weights are taken from ImageNet, are taught in parallel and finally merged into a layer called feature fusion, the output of the two networks. The proposed approach results show that this approach is better than other approaches on the MPIIGaze dataset. The proposed approach achieved an angle error of 5.83, which resulted in a lower error than other approaches.

با عرض سلام مقاله ی فوق جهت قرار گیری در ارکایو اماده می باشد دوستانی که تمایل به شرکت دارند می تونن به ایدی بنده پیام بدن. جایگاه ۲ و ۳ خالی میباشد.
@Raminmousa

This channel is for Programmers, Coders, Software Engineers.

1- Data Science
2- Machine Learning
3- Data Visualization
4- Artificial Intelligence
5- Data Analysis
6- Statistics
7- Deep Learning

https://t.me/DataScienceM
https://t.me/DataScienceM