openai/parameter-golf

Train language models under 16MB

View on index · View in 3D Map

Related repos

• framework for testing and benchmarking large language models with custom or built-in evaluations
• evaluating large language models across tasks and datasets
• tools for finetuning language models with instruction datasets and preference optimization
• Run open-source or custom language models as OpenAI-style APIs with one command
• Inference of language models on hardware with limited memory
• DeepSeek-V3, a Mixture-of-Experts language model with 671B parameters and 37B active per token, focused on math and coding tasks
• run large language models on any device
• minimal PyTorch code for training your own small language model from scratch
• litgpt: tools to train, finetune, and run large language models from the command line
• Runs large language models locally