David Berenstein

dspydantic. DSPydantic: Auto-Optimize Your Prompts and Pydantic Models with DSPy

concise-concepts. This repository contains an easy and intuitive approach to few-shot NER using most similar expansion over spaCy embeddings. Now with entity scoring.

classy-classification. This repository contains an easy and intuitive approach to few-shot classification using sentence-transformers or spaCy models, or zero-shot classification with Huggingface.

fast-sentence-transformers. Simply, faster, sentence-transformers

crosslingual-coreference. A multi-lingual approach to AllenNLP CoReference Resolution along with a wrapper for spaCy.

spacy-setfit. This repository contains an easy and intuitive approach to use SetFit in combination with spaCy.

dataset-viber. Dataset Viber is your chill repo for data collection, annotation and vibe checks.

whisper-jax-asr-webservice. OpenAI Whisper-JAX ASR Webservice API

paper-prowler. A versatile tool that aggregates and organizes web content like RSS feeds, arXiv papers to streamline your research and information management.

cleaners. Your lightweight library for dataset cleaning

memory-palace. The open-source neural privacy friendly neural-search engine for your data.

davidberenstein1957. 👨🏽‍🍳 Cooking, 👨🏽‍💻 Coding, 🏆 Committing

llm-course. Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

political-statement-evaluator. Work for De Groene Amsterdammer, a Dutch opinion newspaper, to investigate political statements made during talkshows.

blog. Public repo for HF blog posts

structured-generation-extraction-from-documents. Python

goose. an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

spacy-fastfit. This repository contains an easy and intuitive approach to use FastFit in combination with spaCy.

model2vec-setfit. Model2Vec: Distill a Small Fast Model from any Sentence Transformer

vicinity. Lightweight Nearest Neighbors with Flexible Backends

LocalAIVoiceChat. Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.