1475963

Marc Benzahra's starred repositories

snowflake-cli

Snowflake CLI is an open-source command-line tool explicitly designed for developer-centric workloads in addition to SQL operations.

Language:PythonApache-2.016300

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Language:PythonApache-2.02906400

Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, with more integrations coming..

Language:RustApache-2.0355700

swirl-search

SWIRL AI Connect: AI infrastructure software that powers your Search & Retrieval Augmented Generation (RAG) applications. Simplify and enhance your AI pipelines with seamless integration of large language models (LLMs) and data sources.

Language:PythonApache-2.0161400

pyright

Static Type Checker for Python

Language:PythonNOASSERTION1243700

arroyo

Distributed stream processing engine in Rust

Language:RustApache-2.0344500

polars

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

Language:RustNOASSERTION2782500

buf

The best way of working with Protocol Buffers.

Language:GoApache-2.0850000

fm_data_tasks

Foundation Models for Data Tasks

Language:Python9400

self-rag

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

Language:PythonMIT160600

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Language:PythonMIT1911000

attention_sinks

Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

Language:PythonApache-2.064800

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Language:PythonMIT635400

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Language:Jupyter NotebookApache-2.0200600

picard

PICARD - Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models. PICARD is a ServiceNow Research project that was started at Element AI.

Language:HaskellApache-2.032500

outlines

Structured Text Generation

Language:PythonApache-2.0699000

Awesome-LLMOps

An awesome & curated list of best LLMOps tools for developers

Language:ShellCC0-1.0338800

dataherald

Interact with your SQL database, Natural Language to SQL using LLMs

Language:PythonApache-2.0321000

guidance

A guidance language for controlling large language models.

Language:Jupyter NotebookMIT1814300

NeMo-Guardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Language:PythonNOASSERTION373000

prompt2model

prompt2model - Generate Deployable Models from Natural Language Instructions

Language:PythonApache-2.0192700

scratch

Personal scratch code

Language:CUnlicense35600

ChatDev

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

Language:ShellApache-2.02437500

plot

A concise API for exploratory data visualization implementing a layered grammar of graphics

Language:HTMLISC409400

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Language:PythonMIT1939900

chroma

the AI-native open-source embedding database

Language:RustApache-2.01347700

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Language:PythonMIT16365800

python-socketio

Python Socket.IO server and client

Language:PythonMIT385900

Flask-SocketIO

Socket.IO integration for Flask applications.

Language:PythonMIT531000

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Language:PythonMIT3448000