The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
- text-similarity
- natural-language-processing
- word-embeddings
- python
132,241 visible repositories in the index
1–24 of 84 · Most stars
The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
Sub-50mb agentic, voice and vision intelligence for consumer devices.
AI that sees your screen, listens to your conversations and tells you what to do
free online AI resume editor,the only official website is https://magicv.art
Download video and audio from 1000+ sites, transcribe locally with speaker labels, and summarize, translate, or chat with your media using your preferred AI provider.
2bit quants, kernels and runtime for consumer devices.
Summaries and resources for Designing Machine Learning Systems book (Chip Huyen, O'Reilly 2022)
TranslatedOffline translation model server with low resource consumption, fast speed, and private deployment capability.
A fast inference library for running LLMs locally on modern consumer-class GPUs
Model summary in PyTorch similar to `model.summary()` in Keras
Module for automatic summarization of text documents and HTML pages.
Transcribe and summarize videos and podcasts using AI. Open-source, multi-platform, and supports multiple languages.
View model summaries in PyTorch!
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
文本挖掘和预处理工具(文本清洗、新词发现、情感分析、实体识别链接、关键词抽取、知识抽取、句法分析等),无监督或弱监督方法
Run Mixtral-8x7B models in Colab or consumer desktops
Python implementation of TextRank algorithms ("textgraphs") for phrase extraction
Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"
Use supervised learning to illuminate the latent space of GAN for controlled generation and edit
TextTeaser is an automatic summarization algorithm.
An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization.
Code for paper Fine-tune BERT for Extractive Summarization
Easy to use extractive text summarization with BERT