zjunlp/KnowLM
An Open-sourced Knowledgable Large Language Model Framework.
This framework helps data scientists and AI researchers build and customize Large Language Models (LLMs) that are 'knowledgeable.' It allows you to process raw text, train or fine-tune models using specific datasets, and then utilize them for various tasks. You input training data and configuration settings, and you get out a ready-to-use, specialized LLM or a component for an existing one.
1,376 stars. No commits in the last 6 months.
Use this if you are developing new Large Language Models and need a robust framework to manage data processing, model training, fine-tuning, and knowledge integration, or if you want to deploy pre-built specialized models.
Not ideal if you are solely looking for a simple tool for information extraction; for that, refer to the DeepKE project.
Stars
1,376
Forks
133
Language
Python
License
MIT
Category
Last pushed
Jan 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/zjunlp/KnowLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TsinghuaC3I/MARTI
A Framework for LLM-based Multi-Agent Reinforced Training and Inference
cli99/llm-analysis
Latency and Memory Analysis of Transformer Models for Training and Inference
tanyuqian/redco
NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to...
stanleylsx/llms_tool
一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。
slp-rl/slamkit
SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for...