Tinker - Thinking Machines Lab
thinkingmachines.ai · 1,795 words · saved by 3 readers
Tinker is a training API for researchers and developers.
Tinker is a training API for researchers Control every aspect of model training and fine-tuning while we handle the infrastructure. Your ideas in four functions forward_backward Perform a forward pass and a backward pass, accumulating the gradient. optim_step Update weights based on the accumulated gradient. sample Generate tokens for interaction, evaluation, or RL actions. save_state Save training progress for resumption. How teams use Tinker Supported models QWEN Dense MoE Dense Dense Dense Dense MoE MoE Dense Explore more Tinker uses LoRA LoRA fine-tunes models by…
saved by
related reading
- Anatomy of a Modern Finetuning APIbenanderson.work
- GitHub - NVIDIA-NeMo/Automodel: 🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face supportgithub.com
- Goodfire AIgoodfire.ai
- Compare AI Models: Pricing, Context & Benchmarks | OpenRouteropenrouter.ai
- Inkling: Our Open-Weights Model - Thinking Machines Labthinkingmachines.ai
- Together AI | The AI Native Cloudtogether.ai
- Parsed | Custom, interpretable AI systems that continuously learnparsed.com
- Hugging Face – The AI community building the future.huggingface.co
- Tinker: Call for Community Projects - Thinking Machines Labthinkingmachines.ai
- Model optimization | OpenAI APIplatform.openai.com
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- Datacurve | The data engine for frontier AIdatacurve.ai