Argilla's repositories
distilabel
⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.
distilabel-spin-dibt
Repository containing the SPIN experiments on the DIBT 10k ranked prompts
argilla-llama-index
A public repo that contains integrations for Argilla and LlamaIndex.
argilla-server
A Python native FastAPI server for the Argilla backend.
argilla-python
The Argilla API python SDK
argilla-haystack
A public repo that contains integrations for Argilla and Haystack.
distilabel-workbench
A working repository for experimental pipelines in distilabel
haystack
:mag: Haystack is an open source NLP framework to interact with your data using Transformer models and LLMs (GPT-4, ChatGPT and alike). Haystack offers production-ready tools to quickly build complex decision making, question answering, semantic search, text generation applications, and more.
argilla-workshop
A repo with everything someone might need to give a nice workshop on NLP with Argilla.
awesome-argilla-datasets
The Argilla team periodically creates datasets and loves to share the process and data with the world.
data-is-better-together
Let's build better datasets, together!
dataset_examples
A public repo for holding dataset examples.
dill
serialize all of Python
distilabel-helm-instruct-adaptable-evaluation-criteria
A repo that implements Stanford CRFM their HELM Instruct with adaptable evaluation criteria
genai-stack
Langchain + Docker + Neo4j + Ollama + Argilla
LLM-Blender
[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
orpo
Official repository for ORPO
prompt-collective-dashboard
A Gradio app to monitor a collective effort from the Open Source AI Community to understand and collect good quality and diverse prompts.
trl
Train transformer language models with reinforcement learning.