isaacus-dev/terge
An easy-to-use Python library for merging PyTorch models.
This tool helps machine learning engineers combine multiple PyTorch models into a single, more capable model. You provide a list of existing PyTorch models, and it merges their learned parameters. The output is a new, unified PyTorch model, allowing you to leverage knowledge from various sources.
No commits in the last 6 months.
Use this if you need to consolidate the capabilities of several PyTorch models, potentially with different architectures, into one high-performing model for tasks like transfer learning or ensemble creation.
Not ideal if your models do not share any common parameter names or shapes, as there would be no parameters to merge.
Stars
12
Forks
1
Language
Python
License
MIT
Category
Last pushed
Jun 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/isaacus-dev/terge"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
meta-llama/llama-cookbook
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started...
arcee-ai/mergekit
Tools for merging pretrained large language models.
changyeyu/LLM-RL-Visualized
๐100+ ๅๅ LLM / RL ๅ็ๅพ๐๏ผใๅคงๆจกๅ็ฎๆณใไฝ่ ๅทจ็ฎ๏ผ๐ฅ๏ผ100+ LLM/RL Algorithm Maps ๏ผ
mindspore-lab/step_into_llm
MindSpore online courses: Step into LLM