jlippp/litesearch
Run autosearch on any NVIDIA GPUs (Works on 2-4GB+ Cards)
This helps AI researchers and hobbyists efficiently train small to medium-sized language models on their personal NVIDIA GPUs. You provide your training data and it automatically adjusts model size and training parameters to fit your GPU's memory. The outcome is a trained language model and a log of experiments, helping you iterate towards a better model faster.
Use this if you want to autonomously experiment with and train custom large language models using an NVIDIA consumer GPU, without needing vast cloud resources.
Not ideal if you need to train models on AMD or Intel GPUs, or if you are working with extremely large models that require enterprise-grade GPU clusters.
Stars
17
Forks
—
Language
Python
License
—
Category
Last pushed
Mar 22, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/jlippp/litesearch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SalesforceAIResearch/enterprise-deep-research
Salesforce Enterprise Deep Research
Technion-Kishony-lab/data-to-paper
data-to-paper: Backward-traceable AI-driven scientific research
Alibaba-NLP/DeepResearch
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Oqura-ai/deepdoc
Deep research tool for local knowledge base.
CopilotKit/open-research-ANA
🤖 An open-source, AI agent-native research canvas application that performs real-time search...