Prompting dei modelli Vision Language (VLM)

Nei prossimi due esercizi userai un modello multi-modale per analizzare il sentiment di un articolo di news e della sua immagine di copertina corrispondente dal dataset BBC News su Hugging Face:

BBC News dataset card

Per iniziare, preparerai un chat template per il modello che includa sia l'immagine sia l'articolo. Il dataset (dataset) e l'immagine di copertina (image) sono già stati caricati.

Questo esercizio fa parte del corso

Modelli multi-modali con Hugging Face

Visualizza il corso

Istruzioni dell'esercizio

Carica il contenuto dell'articolo di news (content) dal datapoint all'indice 6 in dataset.
Completa la query di testo per inserire content in text_query usando le f-string.
Aggiungi image e text_query al chat template, specificando il tipo di contenuto di text_query come "text".

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

# Load the news article content from datapoint 6
content = ____

# Complete the text query
text_query = f"Does the news article have a positive, negative, or neutral impact on championship winning chances: {____}. Provide reasoning."

# Add the text query dictionary to the chat template
chat_template = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": ____,
            },
            ____
        ],
    }
]

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Modelli multi-modali con Hugging Face

IntermediárioNível de habilidade

4.8+

Inizia il corso gratis

Navigate the Hugging Face model hub, transform raw text, audio, and visual data into AI-friendly formats. Learn how to find the latest most popular models for tasks such as text generation and harness the power of pre-built pipelines.

Exercise 1: Hugging Face model navigation Exercise 2: How many models!?Exercise 3: Finding the most popular text-to-image model Exercise 4: Preprocessing different modalities Exercise 5: Text tokenizing Exercise 6: Image preprocessing Exercise 7: Audio preprocessing Exercise 8: Pipeline tasks and evaluations Exercise 9: Pipeline caption generation Exercise 10: Passing keyword arguments Exercise 11: Model evaluation on a custom dataset

Learn to master individual modalities with state-of-the-art models. Dive into computer vision for image classification and segmentation, explore speech recognition and text-to-speech synthesis, and learn effective fine-tuning techniques. Build practical skills with pre-trained models from Hugging Face's transformers library.

Exercise 1: Computer vision Exercise 2: Image classification Exercise 3: Object detection Exercise 4: Image background removal Exercise 5: Fine-tuning computer vision models Exercise 6: CV fine-tuning: dataset prep Exercise 7: CV fine-tuning: model classes Exercise 8: CV fine-tuning: trainer configuration Exercise 9: Speech recognition and audio generation Exercise 10: Automatic speech recognition Exercise 11: Creating speech embeddings Exercise 12: Audio denoising Exercise 13: Fine-tuning text-to-speech models Exercise 14: Fine-tuning a text-to-speech model Exercise 15: Generating new speech

Learn to fuse visual, textual, and audio information for richer AI applications. Master techniques like CLIP for zero-shot classification, build sentiment analyzers that see and read, and create emotion detectors that combine facial expressions with voice. Take your AI models beyond single-modality thinking.

Exercise 1: Classificazione di immagini zero-shot Exercise 2: Zero-shot learning con CLIP Exercise 3: Valutazione automatica della qualità delle didascalie Exercise 4: Analisi del sentiment multimodale Exercise 5: Prompting dei modelli Vision Language (VLM)

Esercizio in corso

Exercise 6: Classificazione multimodale del sentiment con Qwen Exercise 7: Classificazione video zero-shot Exercise 8: Separare audio e video Exercise 9: Analisi del sentiment dei video con CLIP CLAP

Transform ideas into reality! Master cutting-edge AI techniques to generate and manipulate visual content using text prompts. Create stunning images, edit photos intelligently, and build powerful question-answering systems for images and documents. Turn your creative vision into digital reality with multi-modal AI.

Exercise 1: Visual question-answering (VQA)Exercise 2: VQA with Vision Language Transformers (ViLTs)Exercise 3: Document VQA with LayoutLM Exercise 4: Image editing with diffusion models Exercise 5: Custom image editing Exercise 6: Image inpainting Exercise 7: Video generation Exercise 8: Build a video!Exercise 9: Assessing video generation performance Exercise 10: Congratulations!