new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

ollama/models

4 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Creating language models with Ollama

Create models that call the Ollama Chat Completion API using the provider instance. The first argument is the model id, such as 'phi3'. Example: const model = ollama('phi3');

Ollama models are on the Ollama Library

More Ollama models can be found on the Ollama Library homepage at https://ollama.com/library.

Ollama embedding models

Create models that call the Ollama embeddings API using the .embeddingModel() factory method. Example: const model = ollama.embeddingModel('nomic-embed-text');

Using Ollama embedding models with embedMany

Use Ollama embedding models with the embedMany function to generate embeddings. Example: const { embeddings } = await embedMany({ model: model, values: ['sunny day at the beach', 'rainy afternoon in the city'] });

Give your agent this brain