CLIP-Italian
CLIP Italian is a CLIP-like Model for Italian. The CLIP model (Contrastive Language–Image Pre-training) was developed by researchers at OpenAI and is able to efficiently learn visual concepts from natural language supervision.
We fine-tuned a competitive Italian CLIP model with only ~1.4 million Italian image-text pairs. This model is part of the Flax/Jax Community Week, organized by HuggingFace and TPU usage sponsored by Google.
Training Data
We considered three main sources of data:
Training Procedure
Preprocessing, hardware used, hyperparameters...
Evaluation Performance
Limitations
Usage
Team members
- Federico Bianchi (vinid)
- Raphael Pisoni (4rtemi5)
- Giuseppe Attanasio (g8a9)
- Silvia Terragni (silviatti)
- Dario Balestri (D3Reo)
- Gabriele Sarti (gsarti)
- Sri Lakshmi (srisweet)
Useful links
- Downloads last month
- 9