MakazhanAlpamys/Soup

Fine-tunes 8B language models on a 4 GB laptop GPU using layer streaming and relies on a single YAML configuration.

View on index · View in 3D Map

Related repos

• Run large language models in a browser
• Runs large language models on iOS and macOS
• Runs large language models locally without internet or GPUs
• Runs large language models in the browser with WebGPU acceleration
• toolkit for finetuning large language models like Llama and Mistral on your own machine
• run large language models on any device
• Fine-tuning notebooks for language models
• Runs large language models locally
• large language model tutorials and training basics from scratch
• Web interface for local language models