llava-gemma-2b
llava-gemma-2b is a large multimodal model (LMM) trained using the LLaVA-v1.5 framework with the 2-billion parameter google/gemma-2b-it model as language backbone and the CLIP-based vision encoder.
text + image → text · made by Intel
Sold by
Nobody in the catalogue publishes a price for this yet.
About
llava-gemma-2b — a text model from Intel.
It takes text and images and returns text. It was published in March 2024. The catalogue files it under chat.
Every current figure
- Maker
- Intel
- Register
- model
- Takes
- text + image
- Returns
- text
- Published
- March 2024
- Parameters
- 2.8 billion · read from its own weights
Known as 1 name
Intel/llava-gemma-2b