Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
-
Updated
Dec 22, 2024 - Python
#
rlaif
Here are 9 public repositories matching this topic...
code for paper Query-Dependent Prompt Evaluation and Optimization with Offline Inverse Reinforcement Learning
inverse-reinforcement-learning irl offline-rl large-language-models llm prompt-engineering rlhf rlaif offline-irl
-
Updated
Mar 20, 2024 - Python
ZYN: Zero-Shot Reward Models with Yes-No Questions
-
Updated
Aug 15, 2023 - Python
Framework for building synthetic datasets with AI feedback
python ai evaluation synthetic-data finetuning dpo huggingface synthetic-data-generation llm rlhf rlaif llm-evaluation ai-feedback
-
Updated
Dec 21, 2024 - Python
Code and data for "Timo: Towards Better Temporal Reasoning for Language Models" (COLM 2024)
temporal-reasoning sota-model llms rlhf rlaif llm-as-a-judge llm-as-evaluator self-critic-framework colm2024
-
Updated
Oct 23, 2024 - Python
Official Implementation of VideoDPO
-
Updated
Dec 20, 2024 - Python
distilled Self-Critique refines the outputs of a LLM with only synthetic data
-
Updated
Apr 11, 2024 - Jupyter Notebook
Improve this page
Add a description, image, and links to the rlaif topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the rlaif topic, visit your repo's landing page and select "manage topics."