IAAR-Shanghai/Grimoire
Grimoire is All You Need for Enhancing Large Language Models
This project helps improve how well smaller, less powerful language models can learn from examples. It takes examples from a strong language model and distills the key learning into a 'grimoire' which is then used by a weaker language model to perform tasks. This is for AI/ML researchers and engineers working with language models who need to get better performance out of smaller models on specific tasks.
117 stars. No commits in the last 6 months.
Use this if you need to boost the in-context learning capabilities of smaller language models to achieve performance levels similar to or even exceeding much larger models on specific tasks.
Not ideal if you are working exclusively with the largest, most powerful language models and don't need to transfer learning to smaller models.
Stars
117
Forks
14
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/IAAR-Shanghai/Grimoire"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shibing624/MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline....
lyogavin/airllm
AirLLM 70B inference with single 4GB GPU
GradientHQ/parallax
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
CrazyBoyM/llama3-Chinese-chat
Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。
CLUEbenchmark/CLUE
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained...