HKUNLP/icl-ceil
[ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.
This project helps machine learning engineers and researchers improve the performance of large language models (LLMs) for specific tasks by carefully selecting example inputs and outputs (called 'in-context examples'). It takes a dataset of tasks and their solutions, then outputs an optimized set of examples that, when fed to an LLM alongside a new problem, leads to more accurate results. This is for professionals who work with LLMs and want to fine-tune their behavior without retraining the entire model.
103 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking to enhance the accuracy of a frozen large language model on specific tasks by providing it with optimal in-context examples.
Not ideal if you are a non-technical user or if you need to perform full model fine-tuning or training rather than just example selection for in-context learning.
Stars
103
Forks
11
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HKUNLP/icl-ceil"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.