Uploaded model
- Developed by: marvin-brt
- License: apache-2.0
- Finetuned from model : unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit
This llava_next model was trained 2x faster with Unsloth and Huggingface's TRL library.
instruction = "Rate the aesthetic appeal of this water bottle image on a scale from 1 to 7, where 1 represents the lowest aesthetic appeal and 7 represents the highest aesthetic appeal. The answer should be formated as Aesthetic rating: X"
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for marvin-brt/Llava1.6-aesthetic_predictor_LoRA_1
Base model
llava-hf/llava-v1.6-mistral-7b-hf