michaelromagne

Michaël Romagné's starred repositories

determined

Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch and TensorFlow.

Language:GoApache-2.0293400

llmware

Unified framework for building enterprise RAG pipelines with small, specialized models

Language:PythonApache-2.0425800

llama_index

LlamaIndex is a data framework for your LLM applications

Language:PythonMIT3371600

label-studio

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Language:JavaScriptApache-2.01752700

trulens

Evaluation and Tracking for LLM Experiments

Language:Jupyter NotebookMIT187300

phoenix

AI Observability & Evaluation

Language:Jupyter NotebookNOASSERTION305500

flyte

Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.

Language:GoApache-2.0522500

langchainrb

Build LLM-powered applications in Ruby

Language:RubyMIT120900

flink

Apache Flink

Language:JavaApache-2.02354700

ydata-synthetic

Synthetic data generators for tabular and time-series data

Language:Jupyter NotebookMIT137700

proton

A streaming SQL engine, a fast and lightweight alternative to ksqlDB and Apache Flink, 🚀 powered by ClickHouse.

Language:C++Apache-2.0138400

milvus

A cloud-native vector database, storage for next generation AI applications

Language:GoApache-2.02837200

fiftyone

The open-source tool for building high-quality datasets and computer vision models

Language:PythonApache-2.0791000

haystack-tutorials

Here you can find all the Tutorials for Haystack 📓

Language:Jupyter NotebookApache-2.023200

:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

Language:PythonApache-2.01468900

ollama

Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.

Language:GoMIT7910200

quivr

Open-source RAG Framework for building GenAI Second Brains 🧠 Build productivity assistant (RAG) ⚡️🤖 Chat with your docs (PDF, CSV, ...) & apps using Langchain, GPT 3.5 / 4 turbo, Private, Anthropic, VertexAI, Ollama, LLMs, Groq that you can share with users ! Efficient retrieval augmented generation framework

Language:PythonNOASSERTION3423800

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Language:PythonApache-2.0192600

ludwig

Low-code framework for building custom LLMs, neural networks, and other AI models

Language:PythonApache-2.01100400

bentoctl

Fast model deployment on any cloud 🚀

Language:PythonNOASSERTION17500

OpenLLM

Run any open-source LLMs, such as Llama 2, Mistral, as OpenAI compatible API endpoint in the cloud.

Language:PythonApache-2.0935000

llm

[Unmaintained, see README] An ecosystem of Rust libraries for working with large language models

Language:RustApache-2.0606100

server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Language:PythonBSD-3-Clause778700

dvc-streamlit-example

Dvc + Streamlit = ❤️

Language:HTMLMIT4000

sicarator

Instant Setup & Best Quality for Data Projects!

Language:JavaScriptApache-2.017600

skypilot

SkyPilot: Run LLMs, AI, and Batch jobs on any cloud. Get maximum savings, highest GPU availability, and managed execution—all with a simple interface.

Language:PythonApache-2.0629400

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

Language:Jupyter NotebookMIT972500

djl-serving

A universal scalable machine learning model deployment solution

Language:JavaApache-2.018300

danswer

Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.

Language:PythonNOASSERTION984700

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Language:PythonApache-2.01508800