Data Science | Machine Learning with Python for Researchers
31.5K subscribers
1.6K photos
102 videos
22 files
1.87K links
Admin: @HusseinSheikho

The Data Science and Python channel is for researchers and advanced programmers

Buy ads: https://telega.io/c/dataScienceT
Download Telegram
🧑‍💻DeciCoder: A new open-source LLM, specialized for generating code in Python, Java, and Javascript..

- parameters: 1 B
- dataset: 'The Stack' dataset
- supports: Python, Javascript, Java
- context: 2048 tokens

Model
Colab
Dataset

https://t.iss.one/DataScienceT
👍52
☄️Dataset Quantization

DQ is able to generate condensed small datasets for training unseen network architectures with state-of-the-art compression ratios for lossless model training.

git clone https://github.com/vimar-gu/DQ.git
cd DQ


🖥 Github: https://github.com/magic-research/dataset_quantization

📕 Paper: https://arxiv.org/abs/2308.10524v1

☑️ Dataset: https://paperswithcode.com/dataset/gsm8k

https://t.iss.one/DataScienceT
👍52
Forwarded from Data Science Books
Machine Learning for Data Science Handbook (2023)

This book is available now only in paid channel

Pages: 975 pages
Rate: ⭐️⭐️⭐️⭐️⭐️

Cost of subscription in Paid channel is 5$ for one time and forever

Channel link: https://t.iss.one/+LnCmAFJO3tNmYjUy

Paid channel contain important book and udemy and other courses as zip files

Welcome all
Contact @Hussein_sheikho
👍4
Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition

🖥 Github: https://github.com/osvai/ske2grid

📕 Paper: https://arxiv.org/pdf/2308.07571v1.pdf

🔥 Dataset: https://paperswithcode.com/dataset/ucf101

https://t.iss.one/DataScienceT
👍2
prompt2model - Generate Deployable Models from Instructions

prompt2model - Generate Deployable Models from Natural Language Instructions


pip install prompt2model

🖥 Github: https://github.com/neulab/prompt2model

📕 Paper: https://arxiv.org/abs/2308.12261v1

⭐️ Demo: https://github.com/facebookresearch/sonar#usage

☑️ Dataset: https://paperswithcode.com/dataset/mconala

https://t.iss.one/DataScienceT
3👍3
🔥Dense Text-to-Image Generation with Attention Modulation

DenseDiffusion, a training-free method that adapts a pre-trained text-to-image model to handle dense captions while offering control over the scene layout.

🖥 Github: https://github.com/naver-ai/densediffusion

📕 Paper: https://arxiv.org/abs/2308.12964v1

⭐️ Dataset: https://paperswithcode.com/dataset/coco

https://t.iss.one/DataScienceT
👍3
Dynamic Low-Rank Instance Adaptation for Universal Neural Image Compression

🖥 Github: https://github.com/llvy21/duic

📕 Paper: https://arxiv.org/pdf/2308.07733v1.pdf

🔥 Dataset: https://paperswithcode.com/dataset/pixel-art

https://t.iss.one/DataScienceT
👍4
S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment

🖥 Github: https://github.com/sheng-eatamath/s3a

📕 Paper: https://arxiv.org/pdf/2308.12960v1.pdf

🔥 Dataset: https://paperswithcode.com/dataset/cifar-100

https://t.iss.one/DataScienceT
4👍1