yorickvp/llava-v1.6-vicuna-13b

LLaVA v1.6: Large Language and Vision Assistant (Vicuna-13B)

Capabilities

Reference Images Max Tokens Top-P

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`prompt` *	string	Prompt to use for text generation	`—`	—
`history`	array	List of earlier chat messages, alternating roles, starting with user input. Include <image> to specify which message to attach the image to.	`—`	—
`image`	string (uri)	Input image	`—`	—
`max_tokens`	integer	Maximum number of tokens to generate. A word is generally 2-3 tokens	`1024`	min: 0
`temperature`	number	Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic	`0.2`	min: 0
`top_p`	number	When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens	`1`	min: 0, max: 1

prompt required string

Prompt to use for text generation

history array

List of earlier chat messages, alternating roles, starting with user input. Include <image> to specify which message to attach the image to.

image string

Input image

max_tokens integer

Maximum number of tokens to generate. A word is generally 2-3 tokens

Default: 1024 min: 0

temperature number

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic

Default: 0.2 min: 0

top_p number

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens

Default: 1 min: 0, max: 1

Version: 0603dec59608 Updated: 2/26/2026 3.8M runs