Instructions to use Freepik/F-Lite-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Freepik/F-Lite-7B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Freepik/F-Lite-7B", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
How much GPU memory does the 7B parameter model use?
#1
by SOT1k - opened
Hi team,
Thanks for releasing F Lite 7B, it looks like a very promising lightweight model!
I’d like to get a better idea of its hardware requirements. Could you share details on:
The approximate GPU memory usage when running inference (e.g. batch size 1)
Memory usage during training or fine-tuning, if applicable
Any optimizations (e.g., quantization, reduced precision) that affect memory footprint
This information would really help in planning deployments and evaluating compatibility with various hardware setups.
Thanks in advance!