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

lmstudio/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.

LM Studio language model ID format

LM Studio language model IDs follow the format of model names available in LM Studio, such as 'llama-3.2-1b'. Models must be downloaded first before they can be used.

LM Studio language model instantiation

To use a language model with LM Studio, call the provider instance with the model ID as a string argument. Example: const model = lmstudio('llama-3.2-1b');

LM Studio embedding model instantiation

To use an embedding model with LM Studio, call the embeddingModel factory method on the provider instance with the model ID as a string argument. Example: const model = lmstudio.embeddingModel('text-embedding-nomic-embed-text-v1.5');

LM Studio embedding model IDs

LM Studio supports embedding models with IDs such as 'text-embedding-nomic-embed-text-v1.5' and 'text-embedding-bge-small-en-v1.5'.

Give your agent this brain