You're looking at a specific version of this model. Jump to the model overview.

lucataco /internvl3_5-30b:92713bb5

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
top_k
integer
50

Min: 1

Top-k sampling parameter
top_p
number
0.95

Max: 1

Top-p sampling parameter
video
string
Input video file for video understanding (alternative to images)
images
string
Input image(s) - can be a single image or multiple images as a list (for multi-image understanding)
prompt
string
Please describe this image in detail.
Text prompt/question about the image(s) or video
num_beams
integer
1

Min: 1

Max: 5

Number of beams for beam search (1 = no beam search)
max_frames
integer
8

Min: 1

Max: 32

Maximum number of frames to extract from video (evenly spaced)
temperature
number
0.2

Max: 2

Temperature for sampling (higher = more random)
thinking_mode
boolean
False
Enable thinking mode for step-by-step reasoning
max_new_tokens
integer
1024

Min: 1

Max: 8192

Maximum number of tokens to generate
repetition_penalty
number
1

Min: 1

Max: 2

Repetition penalty (1.0 = no penalty)

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'title': 'Output', 'type': 'string'}