instruction-tuned model

A language modellanguage model, n.: A system that has learned how likely different sequences of words are, so it can predict the next word in a text and, by doing that repeatedly, write text of its own. that, after pretrainingpretraining, n.: The first and usually the most expensive stage of building a modern AI model, in which it learns general patterns from enormous amounts of raw text, images or code before being specialized for particular uses., has been fine-tunedfine-tuning, n.: Taking an AI model that has already learned a lot and training it a little more on a smaller, focused set of examples so it gets better at one job or behaves a certain way. on instructions or task descriptions paired with desired outputs (instruction tuninginstruction tuning, n.: Training a language model on many tasks written as plain instructions with correct answers, so it learns to do what a request asks instead of just continuing the text.), usually followed by preference optimization such as reinforcement learning from human feedbackreinforcement learning from human feedback, n.: A way of training AI using people's judgments: humans compare pairs of answers, a scoring model learns their preferences, and the AI is then trained to produce answers that score well. or direct preference optimizationdirect preference optimization, n.: A simpler way to teach an AI people's preferences: instead of building a separate scoring model, it trains directly on pairs of better and worse answers, making the better ones more likely.. Compared with its base modelbase model, n.: A language model fresh from its first broad training on text, before being taught to follow instructions or chat. It continues whatever text it is given instead of answering., it answers directly, respects constraints on format and length, generalizes to unseen tasks described in plain language (zero-shotzero-shot learning, n.: Doing a task without being shown a single example of it — say, an AI sorting reviews into positive and negative just from being told to, or recognizing an animal it never saw in training.) and is more predictable and safer, at some cost in output diversity. Open-weight releases mark such checkpoints with suffixes such as '-Instruct' or '-it'. Most instruction-tuned models are also chat modelschat model, n.: A language model trained to hold a back-and-forth conversation, keeping track of who said what and replying as a helpful assistant. It is the engine inside chat apps. and the terms are often used interchangeably, although single-turn instruction models preceded multi-turn chat formats.

Use the instruct checkpoint for the extraction pipeline; the base model ignores the output format.