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

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

Input
Configure the inputs for the AI model.

Input image

0
1

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

Prompt to use for text generation

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

0
100

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

0
100

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

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.