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
https://t.iss.one/DataScienceT
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
https://t.iss.one/DataScienceT
❤🔥2
Large Language Models as Tool Makers
In this work, we take an initial step towards removing this dependency by proposing a closed-loop framework, referred to as LLMs A s Tool Makers (LATM), where LLMs create their own reusable tools for problem-solving.
🖥 Github: https://github.com/ctlllll/llm-toolmaker
⏩ Paper: https://arxiv.org/pdf/2305.17126v1.pdf
📌 Dataset: https://paperswithcode.com/dataset/big-bench
https://t.iss.one/DataScienceT
In this work, we take an initial step towards removing this dependency by proposing a closed-loop framework, referred to as LLMs A s Tool Makers (LATM), where LLMs create their own reusable tools for problem-solving.
🖥 Github: https://github.com/ctlllll/llm-toolmaker
⏩ Paper: https://arxiv.org/pdf/2305.17126v1.pdf
📌 Dataset: https://paperswithcode.com/dataset/big-bench
https://t.iss.one/DataScienceT
👍2❤1
Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models
The performance of Text2Image is largely dependent on text prompts. In Prompt-Free Diffusion, no prompt is needed, just a reference images.
🖥 Github: https://github.com/shi-labs/prompt-free-diffusion
🔎 Demo: https://huggingface.co/spaces/shi-labs/Prompt-Free-Diffusion
⏩ Paper: https://arxiv.org/abs/2305.16223v1
📌 Dataset: https://paperswithcode.com/dataset/ffhq
https://t.iss.one/DataScienceT
The performance of Text2Image is largely dependent on text prompts. In Prompt-Free Diffusion, no prompt is needed, just a reference images.
🖥 Github: https://github.com/shi-labs/prompt-free-diffusion
🔎 Demo: https://huggingface.co/spaces/shi-labs/Prompt-Free-Diffusion
⏩ Paper: https://arxiv.org/abs/2305.16223v1
📌 Dataset: https://paperswithcode.com/dataset/ffhq
https://t.iss.one/DataScienceT
❤🔥2❤1👍1
Large Language Models as Tool Makers
In this work, we take an initial step towards removing this dependency by proposing a closed-loop framework, referred to as LLMs A s Tool Makers (LATM), where LLMs create their own reusable tools for problem-solving.
🖥 Github: https://github.com/ctlllll/llm-toolmaker
⏩ Paper: https://arxiv.org/pdf/2305.17126v1.pdf
📌 Dataset: https://paperswithcode.com/dataset/big-bench
https://t.iss.one/DataScienceT
In this work, we take an initial step towards removing this dependency by proposing a closed-loop framework, referred to as LLMs A s Tool Makers (LATM), where LLMs create their own reusable tools for problem-solving.
🖥 Github: https://github.com/ctlllll/llm-toolmaker
⏩ Paper: https://arxiv.org/pdf/2305.17126v1.pdf
📌 Dataset: https://paperswithcode.com/dataset/big-bench
https://t.iss.one/DataScienceT
❤🔥1👍1
🖥 A Practical Toolkit for Multilingual Question and Answer Generation
Multilingual/multidomain question generation datasets, models, and python library for question generation.
🖥 Github: https://github.com/asahi417/lm-question-generation
⏩ Paper: https://arxiv.org/abs/2305.17416v1
📌 Dataset: https://paperswithcode.com/dataset/squad
https://t.iss.one/DataScienceT
Multilingual/multidomain question generation datasets, models, and python library for question generation.
🖥 Github: https://github.com/asahi417/lm-question-generation
⏩ Paper: https://arxiv.org/abs/2305.17416v1
📌 Dataset: https://paperswithcode.com/dataset/squad
https://t.iss.one/DataScienceT
👍1
🦙 BigTrans 🚀
BigTrans which adapts LLaMA that covers only 20 languages and enhances it with multilingual translation capability on more than 100 languag
🖥 Github: https://github.com/ZNLP/BigTrans/tree/main
⏩ Paper: https://arxiv.org/abs/2305.18098v1
📌 Dataset: https://paperswithcode.com/dataset/flores-200
https://t.iss.one/DataScienceT
BigTrans which adapts LLaMA that covers only 20 languages and enhances it with multilingual translation capability on more than 100 languag
🖥 Github: https://github.com/ZNLP/BigTrans/tree/main
⏩ Paper: https://arxiv.org/abs/2305.18098v1
📌 Dataset: https://paperswithcode.com/dataset/flores-200
https://t.iss.one/DataScienceT
This media is not supported in your browser
VIEW IN TELEGRAM
🔥 GPT4Tools: Teaching LLM to Use Tools via Self-instruction
GPT4Tools is a centralized system that can control multiple visual foundation models. It is based on Vicuna (LLaMA), and 71K self-built instruction data.
🖥 Github: https://github.com/stevengrove/gpt4tools
⏩ Paper: https://arxiv.org/abs/2305.18752v1
📌 Project: https://gpt4tools.github.io/
https://t.iss.one/DataScienceT
GPT4Tools is a centralized system that can control multiple visual foundation models. It is based on Vicuna (LLaMA), and 71K self-built instruction data.
🖥 Github: https://github.com/stevengrove/gpt4tools
⏩ Paper: https://arxiv.org/abs/2305.18752v1
📌 Project: https://gpt4tools.github.io/
https://t.iss.one/DataScienceT
This media is not supported in your browser
VIEW IN TELEGRAM
Introducing BERTopic Integration with the Hugging Face Hub
BERTopic provides a powerful tool for users to uncover significant topics within text collections, thereby gaining valuable insights.
pip install bertopic
🤗 Hugging face: https://huggingface.co/blog/bertopic
🖥 Github: https://github.com/MaartenGr/BERTopic
⏩ Colab: https://colab.research.google.com/#fileId=https://huggingface.co/spaces/davanstrien/blog_notebooks/blob/main/BERTopic_hub_starter.ipynb
📌 Docs: https://maartengr.github.io/BERTopic/getting_started/quickstart/quickstart.html
https://t.iss.one/DataScienceT
BERTopic provides a powerful tool for users to uncover significant topics within text collections, thereby gaining valuable insights.
pip install bertopic
🤗 Hugging face: https://huggingface.co/blog/bertopic
🖥 Github: https://github.com/MaartenGr/BERTopic
⏩ Colab: https://colab.research.google.com/#fileId=https://huggingface.co/spaces/davanstrien/blog_notebooks/blob/main/BERTopic_hub_starter.ipynb
📌 Docs: https://maartengr.github.io/BERTopic/getting_started/quickstart/quickstart.html
https://t.iss.one/DataScienceT
Dynamic Sparse Training with Structured Sparsity
🖥 Github: https://github.com/calgaryml/condensed-sparsity
⏩ Paper: https://arxiv.org/pdf/2305.02299v1.pdf
💨 Dataset: https://paperswithcode.com/dataset/cifar-10
https://t.iss.one/DataScienceT
🖥 Github: https://github.com/calgaryml/condensed-sparsity
⏩ Paper: https://arxiv.org/pdf/2305.02299v1.pdf
💨 Dataset: https://paperswithcode.com/dataset/cifar-10
https://t.iss.one/DataScienceT
SSSegmenation
🖥 Github: https://github.com/segmentationblwx/sssegmentation
⏩ Paper: https://arxiv.org/pdf/2305.17091v1.pdf
💨 Dataset: https://paperswithcode.com/dataset/cityscapes
https://t.iss.one/DataScienceT
🖥 Github: https://github.com/segmentationblwx/sssegmentation
⏩ Paper: https://arxiv.org/pdf/2305.17091v1.pdf
💨 Dataset: https://paperswithcode.com/dataset/cityscapes
https://t.iss.one/DataScienceT
❤🔥3
🔥 10 Free Machine Learning Courses from Top Universities
1. Introduction to Machine Learning - UC Berkeley
2. Introduction to Machine Learning - Carnegie Mellon University
3. Machine Learning - Stanford University
4. Machine Learning & Data Mining - Caltech
5. Learning from Data - Caltech
6. Machine Learning for Intelligent Systems - Cornell University
7. Large Scale Machine Learning - University of Toronto
8. Machine Learning with Large Datasets - Carnegie Mellon University
9. Foundations of Machine Learning and Statistical Inference - Caltech
10. Algorithmic Aspects of Machine Learning - MIT
https://t.iss.one/DataScienceT
1. Introduction to Machine Learning - UC Berkeley
2. Introduction to Machine Learning - Carnegie Mellon University
3. Machine Learning - Stanford University
4. Machine Learning & Data Mining - Caltech
5. Learning from Data - Caltech
6. Machine Learning for Intelligent Systems - Cornell University
7. Large Scale Machine Learning - University of Toronto
8. Machine Learning with Large Datasets - Carnegie Mellon University
9. Foundations of Machine Learning and Statistical Inference - Caltech
10. Algorithmic Aspects of Machine Learning - MIT
https://t.iss.one/DataScienceT
❤🔥7👍4❤1😍1
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/stevengrove/gpt4tools
⏩ Paper: https://arxiv.org/abs/2306.00989v1
📌 Dataset: https://paperswithcode.com/dataset/inaturalist
https://t.iss.one/DataScienceT
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/stevengrove/gpt4tools
⏩ Paper: https://arxiv.org/abs/2306.00989v1
📌 Dataset: https://paperswithcode.com/dataset/inaturalist
https://t.iss.one/DataScienceT
❤🔥3👍1
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
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
❤🔥3
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 ♥️
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 ♥️
❤🔥5
🔭 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
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
❤🔥3