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。
This tool helps machine learning engineers and researchers fine-tune and experiment with large language models. It takes raw text data, pre-trained large language models (LLMs) like Llama or Qwen, and configuration settings as input. The output is a refined, specialized LLM ready for deployment, or performance metrics from testing. It is designed for those who want to customize existing LLMs for specific tasks.
223 stars. No commits in the last 6 months.
Use this if you need to train or fine-tune large language models for particular applications, evaluate their performance, or predict outputs using a web interface or terminal.
Not ideal if you are a casual user looking for an off-the-shelf chatbot, or if you don't have experience with machine learning model training and infrastructure.
Stars
223
Forks
21
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 08, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/stanleylsx/llms_tool"
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
zjunlp/KnowLM
An Open-sourced Knowledgable Large Language Model Framework.
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...
slp-rl/slamkit
SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for...