Instructions to use peft-internal-testing/tiny-clip-text-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use peft-internal-testing/tiny-clip-text-2 with Transformers:
# Load model directly from transformers import AutoTokenizer, CLIPTextModelWithProjection tokenizer = AutoTokenizer.from_pretrained("peft-internal-testing/tiny-clip-text-2") model = CLIPTextModelWithProjection.from_pretrained("peft-internal-testing/tiny-clip-text-2") - Notebooks
- Google Colab
- Kaggle
LoRA adapters β perfect for mobile personalization
#3
by 3morixd - opened
LoRA adapters are the key to personalized mobile AI. Instead of shipping a full model per user, ship one base model + tiny LoRA per user (5-20MB each).
At Dispatch AI, we're building a mobile LoRA hub β users can download task-specific LoRAs on demand. A 1.5B base model + 50 LoRAs = 50 capabilities in 1.5GB.
- Dispatch AI (FZE), Sharjah UAE