nlpconnect/vit-gpt2-image-captioning
Data and Resources
This dataset has no data
Additional Info
| Field | Value |
|---|---|
| Last Updated | June 16, 2026, 06:40 (UTC) |
| Created | June 16, 2026, 06:40 (UTC) |
| algorithm | Transformer (ViT), GPT-2. |
| authors | [{"id":"7977e0b3-6ee7-442f-82f6-80086d33df0e","role":"principal","type":"user"}] |
| framework | pytorch |
| library_requirements | transformers, torch, Pillow |
| marketplace_author_id | 7977e0b3-6ee7-442f-82f6-80086d33df0e |
| marketplace_id | 3de8c611-6729-47b8-8b74-2f32fe7bd4e0 |
| resource_type | model |
| short_description | Modelo de subtitulación con codificador ViT y decodificador GPT-2: una referencia sencilla y muy utilizada. |
| task_type | other |