perone / feste
Feste is a free and open-source framework allowing scalable composition of NLP tasks using a graph execution model that is optimized and executed by specialized schedulers.
☆41Updated 2 years ago
Alternatives and similar repositories for feste:
Users that are interested in feste are comparing it to the libraries listed below
- A sample pattern for running CI tests on Modal☆17Updated 3 weeks ago
- a pipeline for using api calls to agnostically convert unstructured data into structured training data☆30Updated 7 months ago
- ☆24Updated last year
- Creating Generative AI Apps which work☆17Updated 3 weeks ago
- Writing Blog Posts with Generative Feedback Loops!☆47Updated last year
- Check for data drift between two OpenAI multi-turn chat jsonl files.☆37Updated last year
- Chat Markup Language conversation library☆55Updated last year
- ☆22Updated last year
- Using modal.com to process FineWeb-edu data☆20Updated last month
- Mixtral finetuning☆19Updated last year
- Cortex-compatible model server for Python and TensorFlow☆17Updated 2 years ago
- NLP with Rust for Python 🦀🐍☆62Updated 11 months ago
- Run LLMs on Replicate with vLLM☆18Updated 6 months ago
- This repository contains code for cleaning your training data of benchmark data to help combat data snooping.☆25Updated 2 years ago
- Explore the use of DSPy for extracting features from PDFs 🔎☆39Updated last year
- ☆20Updated this week
- ☆34Updated 2 weeks ago
- Embedding Recycling for Language models☆38Updated last year
- A library for squeakily cleaning and filtering language datasets.☆47Updated last year
- This repository implements DSPy programs to tasks in Indian Languages☆13Updated last year
- ☆18Updated 7 months ago
- PyTorch implementation for MRL☆18Updated last year
- Python tools☆12Updated last year
- ☆20Updated last year
- Binary vector search example using Unum's USearch engine and pre-computed Wikipedia embeddings from Co:here and MixedBread☆18Updated last year
- An unofficial Python client library for Lambda Lab's Cloud Computing Platform☆12Updated 2 years ago
- Vector Database with support for late interaction and token level embeddings.☆54Updated 7 months ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated last year
- 🤝 Trade any tensors over the network☆30Updated last year
- Tokenization across languages. Useful as preprocessing for subword tokenization.☆22Updated 2 years ago