Daily books
https://t.iss.one/DataScience_Books
https://t.iss.one/DataScience_Books

Wuerstchen: Efficient Pretraining of Text-to-Image Models

Novel technique for text-to-image synthesis that unites competitive performance with unprecedented cost-effectiveness and ease of training on constrained hardwar

🖥 Github: https://github.com/dome272/wuerstchen

⏩ Paper: https://arxiv.org/abs/2306.00637v1

📌 Colab: https://colab.research.google.com/drive/1UTP9Xn2UIrVbAXyL-SKEvyLmgVWdw-Vy

https://t.iss.one/DataScienceT

If you’re a developer wanting to use large language model tools, our new course is for you.

You’ll learn how to use different prompts at various stages in the system-building process, strategies for parsing long documents, and much more!

Join for free:
https://learn.deeplearning.ai/chatgpt-building-system

✅ More reaction = more posts

@CodeProgrammer ♥️

TabEAE

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

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

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

https://t.iss.one/DataScienceT

🔭 GRES: Generalized Referring Expression Segmentation

New benchmark (GRES), which extends the classic RES to allow expressions to refer to an arbitrary number of target objects.

🖥 Github: https://github.com/henghuiding/ReLA

⏩ Paper: https://arxiv.org/abs/2306.00968

🔎 Project: https://henghuiding.github.io/GRES/

📌 New dataset: https://github.com/henghuiding/gRefCOCO

https://t.iss.one/DataScienceT

🦍 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

https://t.iss.one/DataScienceT

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

https://t.iss.one/DataScienceT

Donate us
PayPal address:
https://www.paypal.me/HusseinSheikho

TRC-20 Address:
TMzAr8AFcZ1n5RXZa3BHPXHBRqugx9Skr7

PayPal and MasterCard:
https://boosty.to/datascienceteam/donate

🐼 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

https://t.iss.one/DataScienceT

📹 Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

LLaMA is working on empowering large language models with video and audio understanding capability.

🖥 Github: https://github.com/damo-nlp-sg/video-llama

📕 Paper: https://arxiv.org/abs/2306.02858

⏩ Demo: https://huggingface.co/spaces/DAMO-NLP-SG/Video-LLaMA

📌 Model: https://modelscope.cn/studios/damo/video-llama/summary

https://t.iss.one/DataScienceT

A list of the best Telegram channels related to data science, programming languages, and artificial intelligence.

Join Quickly:
https://t.iss.one/addlist/8_rRW2scgfRhOTc0

🏔️ Large Language Model for Geoscience

We introduce K2 (7B), an open-source language model trained by firstly further pretraining LLaMA on collected and cleaned geoscience literature, including geoscience open-access papers and Wikipedia pages, and secondly fine-tuning with knowledge-intensive instruction tuning data (GeoSignal).

git clone https://github.com/davendw49/k2.git
cd k2
conda env create -f k2.yml
conda activate k2

🖥 Github: https://github.com/davendw49/k2

⭐️ Demo: https://huggingface.co/daven3/k2_fp_delta

📕 Paper: https://arxiv.org/abs/2306.05064v1

🔗 Dataset: https://huggingface.co/datasets/daven3/geosignal

https://t.iss.one/DataScienceT

💲 FinGPT: Open-Source Financial Large Language Models

Unlike proprietary models, FinGPT takes a data-centric approach, providing researchers and practitioners with accessible and transparent resources to develop their FinLLMs.

🖥 Github: https://github.com/ai4finance-foundation/fingpt

⭐️ FinNLP: https://github.com/ai4finance-foundation/finnlp

📕 Paper: https://arxiv.org/abs/2306.06031v1

🔗 Project: https://ai4finance-foundation.github.io/FinNLP/

https://t.iss.one/DataScienceT

You can now download and watch all paid data science courses for free by subscribing to our new channel

https://t.iss.one/udemy13

GP-UNIT - Official PyTorch Implementation

🖥 Github: https://github.com/williamyang1991/gp-unit

⏩ Paper: https://arxiv.org/pdf/2306.04636v1.pdf

💨 Dataset: https://paperswithcode.com/dataset/celeba-hq

https://t.iss.one/DataScienceT

🧔 4DHumans: Reconstructing and Tracking Humans with Transformers

Fully "transformerized" version of a network for human mesh recovery.

🖥 Github: https://github.com/shubham-goel/4D-Humans

⭐️ Colab: https://colab.research.google.com/drive/1Ex4gE5v1bPR3evfhtG7sDHxQGsWwNwby?usp=sharing

📕 Paper: https://arxiv.org/pdf/2305.20091.pdf

🔗 Project: https://shubham-goel.github.io/4dhumans/

https://t.iss.one/DataScienceT

A channel for educational Python courses

All courses here are free and available to everyone

https://t.iss.one/Python53