Explore Gemma SEA-LION v4 4B VL

Provides the visual inputs the model should analyze. The text field should identify the requested task and, with multiple images, clearly distinguish which image each instruction refers to; larger or numerous images consume more processing and context.

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.

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.

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.

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.

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.

Limits sampling at each step to the specified number of most likely next tokens. Smaller values make output more conservative, while larger values preserve more variety; zero commonly means that this filter is disabled.

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.

Changes the scores of tokens that already appeared in the generated text. Values above 1 discourage repeated words and loops, 1 leaves probabilities unchanged, and values below 1 make repetition more likely.

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.

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.

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.

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.

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.