olp_cs's profile picture. #python #rust #rstats #MachineLearning #NLProc #nlp #digitalhealth

Olga Pustovalova

@olp_cs

#python #rust #rstats #MachineLearning #NLProc #nlp #digitalhealth

Rust eBooks Nightly This project automatically builds and publishes the latest versions of books: • The Rust Programming Language • Rust Cookbook • Asynchronous Programming in Rust • Learning Rust With Entirely Too Many Linked Lists etc. artur-sulej.github.io/rust-ebooks/


>> we’ve expanded the "NLP" course with new chapters, including fine-tuning LLMs and building reasoning models like Deepseek R1. huggingface.co/blog/llm-course


Olga Pustovalova reposted

The Illustrated DeepSeek-R1 Spent the weekend reading the paper and sorting through the intuitions. Here's a visual guide and the main intuitions to understand the model and the process that created it. Link in the first reply. All feedback welcome.

JayAlammar's tweet image. The Illustrated DeepSeek-R1

Spent the weekend reading the paper and sorting through the intuitions. Here's a visual guide and the main intuitions to understand the model and the process that created it.

Link in the first reply. All feedback welcome.

Understanding Deep Learning by Simon J.D. Prince - the book in PDF - Python notebooks - slides for instructors Last updated: July 22, 2024 udlbook.github.io/udlbook/


Olga Pustovalova reposted

All three parts of "What We Learned from a Year of Building with LLMs" are now live on O'Reilly! • Tactics: oreilly.com/radar/what-we-… • Ops: oreilly.com/radar/what-we-… • Strategy: oreilly.com/radar/what-we-… Read all 42 lessons here: applied-llms.org A sample of what each…


Book: Interpretable Machine Learning. A Guide for Making Black Box Models Explainable (2022) by Christoph Molnar christophm.github.io/interpretable-…


Olga Pustovalova reposted

Here’s a great guide teaching you how to construct knowledge graphs using LLMs that adhere to a pre-defined schema - using purely local models (@ollama, @huggingface), and @neo4j as the graph store. Possible with @llama_index! 🦙🕸️ 1. Define the set of possible entities and…

llama_index's tweet image. Here’s a great guide teaching you how to construct knowledge graphs using LLMs that adhere to a pre-defined schema - using purely local models (@ollama, @huggingface), and @neo4j as the graph store.

Possible with @llama_index! 🦙🕸️

1. Define the set of possible entities and…

Olga Pustovalova reposted

Building and Querying Knowledge Graphs with LLMs Here’s a short but comprehensive tutorial of both 1) how to automatically generate a knowledge graph with LLMs, and 2) querying knowledge graphs in a RAG setup. Knowledge graphs allow you to retrieve not only by vector search,…

llama_index's tweet image. Building and Querying Knowledge Graphs with LLMs

Here’s a short but comprehensive tutorial of both 1) how to automatically generate a knowledge graph with LLMs, and 2) querying knowledge graphs in a RAG setup.

Knowledge graphs allow you to retrieve not only by vector search,…

Olga Pustovalova reposted

Call for Contributions to @huggingface Cookbook 👩🏻‍🍳👨🏻‍🍳🧑🏻‍🍳 We are looking for following: ⚒️ Industry-specific recipes: biomedical, legal, finance etc. 🧩 Recipes in other domains: computer vision, audio and more! 🍀 Niche techniques built for production: quantization etc.


Olga Pustovalova reposted

A Comprehensive Survey of Advanced RAG 📖 If you’re looking for a one-stop shop for advanced RAG concepts, look no further 💫 @ivanilin9 details all the key concepts in this blog post 📚, and each section highlights @llama_index resources/guides that you can check out. Here…

llama_index's tweet image. A Comprehensive Survey of Advanced RAG 📖

If you’re looking for a one-stop shop for advanced RAG concepts, look no further 💫 @ivanilin9 details all the key concepts in this blog post 📚, and each section highlights @llama_index resources/guides that you can check out. 

Here…

Olga Pustovalova reposted

Latest blog post: A more generalized model transformation solution 🔥 More performant and user-friendly, bringing performance improvements to both model training and inference without manual efforts. Check it out 👉 hubs.la/Q02d9Ffm0

PyTorch's tweet image. Latest blog post: A more generalized model transformation solution 🔥

More performant and user-friendly, bringing performance improvements to both model training and inference without manual efforts.

Check it out 👉 hubs.la/Q02d9Ffm0

Olga Pustovalova reposted

GPT-3 can now make changes to existing content, not just predict what comes next. Released in the API today: openai.com/blog/gpt-3-edi…


Olga Pustovalova reposted

Our newest system DALL·E 2 can create realistic images and art from a description in natural language. See it here: openai.com/dall-e-2/


Olga Pustovalova reposted

Yann LeCun’s @ylecun Deep Learning Course is now free & fully online at @NYUDataScience Videos, slides, notes, and notebooks! cds.nyu.edu/deep-learning/

TheTuringPost's tweet image. Yann LeCun’s @ylecun Deep Learning Course is now free & fully online at @NYUDataScience

Videos, slides, notes, and notebooks!

cds.nyu.edu/deep-learning/

Olga Pustovalova reposted

Just published DeBERTa-v3-base-mnli-fever-anli via @huggingface based on Microsoft's new DeBERTa-v3. The base model outperforms almost all large models on anli. Test it here: huggingface.co/MoritzLaurer/D… Who has enough compute to train the large model? @MSFTResearch #NLProc #EMNLP2021


Speech and Language Processing (3rd ed. draft) by Dan Jurafsky and James H. Martin - Last updated: September 21, 2021 > more on transformers, including for MT, various updated algorithms, like for dependency parsers, etc. web.stanford.edu/~jurafsky/slp3/ by @jurafsky


Olga Pustovalova reposted

My lectures from Spring 2021's cs124, "From Languages to Information", our Stanford undergrad course introducing NLP, IR, chatbots, recommendation systems, social networks (+ some guest lectures from @chrmanning!) are now online, hope they're useful! youtube.com/channel/UC_48v…


Loading...

Something went wrong.


Something went wrong.