Machine Learning

pytorch-labs/gpt-fast: Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Simple and efficient pytorch-native transformer text generation. Featuring: Very low latency <1000 lines of python No dependencies other than PyTorch and sentencepiece int8/int4 quantization Speculative decoding Tensor parallelism Supports Nvidia and AMD GPUs This is NOT intended to be a "framework"…

3 months ago

GitHub - unslothai/unsloth: Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory

github.com

Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma 2-5x faster with 80% less memory! ✨ Finetune for Free All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, Ollama, vLLM or uploaded to Hugging Face.…

4 months ago

Classifying articles via URLs

attentionmarkets.substack.com

Today, I want to work through a small exercise in language modeling. A common NLP task for researchers working with news articles is some form of topic modeling. By getting a sense of what news stories are about, aggregated into a defined vocabulary of labels, researchers can make comparisons across…

4 months ago

Text Classification using Custom Data and PyTorch

medium.com

5 min read· May 17, 2023 Photo by Max Chen on Unsplash Text classification is a fundamental natural language processing (NLP) task that involves assigning predefined categories or labels to text documents. PyTorch, a popular deep learning framework, provides powerful tools for building and training…

4 months ago

Develop Your First Neural Network with PyTorch, Step by Step - MachineLearningMastery.com

machinelearningmastery.com

PyTorch is a powerful Python library for building deep learning models. It provides everything you need to define and train a neural network and use it for inference. You don’t need to write much code to complete all this. In this pose, you will discover how to create your first deep learning neural…

4 months ago

seekbytes/IPA: GUI analyzer for deep-diving into PDF files. Detect malicious payloads, understand object relationships, and extract key information for threat analysis.

github.com

Interactive PDF Analysis Interactive PDF Analysis (also called IPA) allows any researcher to explore the inner details of any PDF file. PDF files may be used to carry malicious payloads that exploit vulnerabilities, and issues of PDF viewer, or may be used in phishing campaigns as social engineering…

9 months ago

Run the strongest open-source LLM model: Llama3 70B with just a single 4GB GPU!

ai.gopubby.com

Gavin Li 4 min read· Apr 21, 2024 -- The strongest open source LLM model Llama3 has been released, some followers have asked if AirLLM can support running Llama3 70B locally with 4GB of VRAM. The answer is YES. Here we go. Moreover, how does Llama3’s performance compare to GPT-4? What’s the key…

1 year ago

Reproducing GPT-2 (124M) in llm.c in 90 minutes for $20 · karpathy/llm.c · Discussion #481

github.com

Replies: 47 comments · 81 replies Oldest Newest Top Comment options Uh oh! There was an error while loading. . {{title}} Something went wrong. Uh oh! There was an error while loading. . timlmit - boss <3 Beta Was this translation helpful? You must be logged in to vote All reactions ❤️ 6 0 replies…

1 year ago

Techniques for automatic summarization of documents using language models | Amazon Web Services

aws.amazon.com

Summarization is the technique of condensing sizable information into a compact and meaningful form, and stands as a cornerstone of efficient communication in our information-rich age. In a world full of data, summarizing long texts into brief summaries saves time and helps make informed decisions.…

1 year ago

Making 1 million requests with python-aiohttp

pawelmhm.github.io

In this post I’d like to test limits of python aiohttp and check its performance in terms of requests per minute. Everyone knows that asynchronous code performs better when applied to network operations, but it’s still interesting to check this assumption and understand how exactly it is better and…

1 year ago

Notes on Abstractive Summarization: PegasusXSUM and T5

medium.com

‘Cloud observer’ VR art created by iva vrtaric Iva @ Tesla Institute 9 min read· May 14, 2022 -- Recently, it has become increasingly common to pre-train the entire model on a data-rich task. Ideally, this pre-training causes the model to develop general-purpose abilities and knowledge that can then…

1 year ago

Build an Automatic Abstractive Text Summarizer in Ten minutes

medium.com

using Transformers, Torch, SentencePiece libraries in Python. Dhiraj Prakash 4 min read· Sep 21, 2021 -- Photo by Mel Poole on Unsplash Text Summarization is the process of shortening long text into shorter text while retaining the key elements and meaning. Manually summarizing the text would take…

1 year ago

Text Summarization in Python using Extractive method (including end-to-end implementation)

medium.com

What is Text Summarization Text summarization is a process of creating concise version of the original text while retaining key information. Humans are naturally good summarizers for we have the ability to understand the overall meaning of a text just by reading it. But how can machines do the same…

1 year ago

Recommendation using embeddings and nearest neighbor search | OpenAI Cookbook

cookbook.openai.com

Recommendations are widespread across the web. 'Bought that item? Try these similar items.' 'Enjoy that book? Try these similar titles.' 'Not the help page you were looking for? Try these similar pages.' This notebook demonstrates how to use embeddings to find similar items to recommend. In…

1 year ago