Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
The fastest way to build and start training your own LLM. CLI tool that scaffolds production-ready PyTorch training projects in seconds. Like create-next-app but for language models.
| Date | Stars |
|---|---|
| 2026-07-24 | 356 |
| 2026-07-25 | 356 |
| 2026-07-28 | 356 |
| 2026-07-30 | 356 |
| 2026-07-31 | 357 |
| 2026-08-06 | 357 |
Today
— stars today
This week
+1 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.28%/day
# create-llm
```
_ _ _
___ _ __ ___ __ _ | |_ ___ | || | _ __ ___
/ __|| '__| / _ \ / _` || __| / _ \ _____ | || || '_ ` _ \
| (__ | | | __/| (_| || |_ | __/ |_____|| || || | | | | |
\___||_| \___| \__,_| \__| \___| |_||_||_| |_| |_|
```
**CLI tool for scaffolding LLM Creation and training **
Create production-ready LLM training projects in seconds. Similar to create-next-app but for training custom language models.
[](https://www.npmjs.com/package/@theanikrtgiri/create-llm)
[](https://www.npmjs.com/package/@theanikrtgiri/create-llm)
[](https://github.com/theaniketgiri/create-llm/stargazers)
[](https://opensource.org/licenses/MIT)
[npm Package](https://www.npmjs.com/package/@theanikrtgiri/create-llm) • [Documentation](#documentation) • [Report Bug](https://github.com/theaniketgiri/create-llm/issues) • [Request Feature](https://github.com/theaniketgiri/create-llm/issues)
```bash
npx create-llm my-awesome-llm
cd my-awesome-llm
pip install -r requirements.txt
python training/train.py
```
---
## Why create-llm?
Training a language model from scratch requires:
- Model architecture (GPT, BERT, T5...)
- Data preprocessing pipeline
- Tokenizer training
- Training loop with callbacks
- Checkpoint management
- Evaluation metrics
- Text generation
- Deployment tools
**create-llm provides all of this in one command.**
---
## Features
### Right-Sized Templates
Choose from 4 templates optimized for different use cases:
- **NANO** (1M params) - Learn in 2 minutes on any laptop
- **TINY** (6M params) - Prototype in 15 minutes on CPU
- **SMALL** (100M params) - Production models in hours
- **BASE** (1B params) - Research-grade in days
### Complete Toolkit
Everything you need out of the box:
- PyTorch training infrastructure
- Data preprocessing pipeline
- Tokenizer training (BPE, WordPiece, Unigram)
- Checkpoint management with auto-save
- TensorBoard integration for real-time monitoring
- Interactive chat interface
- Model comparison tools
- Deployment scripts
### Smart Defaults
Intelligent configuration that:
- Auto-detects vocab size from tokenizer
- Automatically handles sequence length mismatches
- Warns about model/data size mismatches
- Detects overfitting during training
- Suggests optimal hyperparameters
- Handles cross-platform paths
- Provides detailed diagnostic messages for errors
### Plugin System
Optional integrations:
- **WandB** - Experiment tracking
- **HuggingFace** - Model sharing
---
## Quick Start
### One-Command Setup
```bash
# Using npx (recommended - no installation needed)
npx create-llm my-llm
# Or install globally
npm install -g create-llm
create-llm my-llm
```
### Interactive Setup
```bash
npx create-llm
```
You'll be prompted for:
- Project name
- Template (NANO, TINY, SMALL, BASE)
- Tokenizer type (BPE, WordPiece, Unigram)
- Optional plugins (WandB, HuggingFace)
### Quick Mode
```bash
# Specify everything upfront
npx create-llm my-llm --template tiny --tokenizer bpe --skip-install
```
---
## 🐳 Docker Support
**Run create-llm without installing Node.js or Python locally!**
### Quick Docker Setup
```bash
# Build the Docker image
git clone https://github.com/theaniketgiri/create-llm.git
cd create-llm
docker build -t create-llm .
# Create a new project
mkdir my-projects && cd my-projects
docker run -it -v $(pwd):/workspace create-llm scaffold my-llm --template tiny
# Train your model
cd my-llm
docker run --gpus all -v $(pwd):/workspace create-llm train
# Start chat interface
docker run -p 7860:7860 -v $(pwd):/workspace create-llmExcerpt of 14,657 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4b2ab5ee87a2e916, topic:llm, topic:transformer, topic:gpt
matched fp:4b2ab5ee87a2e916, topic:deep-learning, topic:pytorch, topic:training