Explore Kanana 1.5 V 3B Instruct

Explains how the model should use the supplied image or video, such as describing a scene, extracting text, comparing items, or answering a question. Refer to relevant regions or frames explicitly when a precise visual answer is needed.

Limits how long the pipeline waits while downloading an image or other remote media source. Increase it for large files or slow hosts, and lower it when the application should fail quickly instead of holding a request open.

Controls whether each result contains the original prompt followed by the completion or only the newly generated portion. Disable it when you need a clean completion without repeating the submitted input.

Returns numeric generated token IDs as tensors rather than ordinary readable text. This is useful for downstream model processing or custom decoding, but most applications should leave it off.

Applies the tokenizer’s cleanup rules after decoding, such as removing spaces that were introduced around punctuation. Disable it when exact spacing or a lossless view of token decoding is more important than polished text.

Removes internal tokens such as beginning-of-sequence, end-of-sequence, padding, and chat-control markers from readable output. Keep it enabled for user-facing text; disable it only when inspecting the model’s exact token sequence.

Treats the last chat message as an unfinished response that the model should continue. Use it to prefill the beginning or structure of an assistant answer; leave it off for a normal new reply to the conversation.

Ends generation as soon as the decoded output contains this exact sequence. The match is literal, so capitalization and spacing matter; choose a distinctive delimiter to avoid stopping on normal prose by accident.

Provides advanced keyword arguments to the processor that prepares text, images, or video for the model. Use it for supported preprocessing options not exposed elsewhere, and avoid conflicting values because they can change resizing, tokenization, or media handling.

Caps how many tokens the model can add after the input. The model may stop earlier naturally, but a limit that is too low can cut off an answer; input tokens are not counted in this value.

Adjusts how strongly the model favors its most likely next token. Lower values produce more focused and repeatable output, while higher values allow less-likely choices and increase variety; it only has an effect when sampling is enabled.

Limits sampling to the smallest set of likely tokens whose probabilities add up to this value. Lower settings make output more focused, while a value near 1 keeps more alternatives available; it only affects sampled generation.

Sets how many candidate continuations the model explores in parallel at each generation step. A value of 1 uses ordinary generation, while larger values can find a better overall sequence at the cost of additional time and memory.

Chooses whether the next token is sampled from a probability distribution or selected deterministically. Enable it for more varied responses that are affected by temperature and Top P; disable it when repeatability matters or when using beam search.

Provides advanced keyword arguments directly to the model’s generation method. Use it for supported controls that are not shown separately in the form, and avoid duplicating named settings because these values may override or conflict with them.