📌 Hugging Face API

Number of APIs: 10

Prerequisites

• Qodex
• Hugging Face Account: https://huggingface.co/

Usage

1. Create a fork
2. Update collection variables
3. Send requests (on 503 due to model loading, wait and retry)

Documentation

• API: https://huggingface.co/docs/api-inference/index
• Models: https://huggingface.co/models

Models

1,000,000+ open models (open-source, open-data, and/or open-weight), including Gemma (by Google, open-weight), Llama (by Meta AI, open-weight), and Mixtral (by Mistral AI, open-weight).

Models can be deployed via one or more of the following options:

• Serverless Inference REST API
• Transformer Python SDK
• Dedicated Inference Endpoint (AWS, Azure, GCP)
• Amazon SageMaker
• Azure ML
• Google Vertex AI
• Hugging Face Space

About Hugging Face

The AI community building the future.

1. 🚀 Get Started - Text Generation (google/gemma-7b-it) POST {{baseUrl}}/models/:model

2. Text Generation - mistralai/Mixtral-8x7B-Instruct-v0.1 POST {{baseUrl}}/models/:model

3. Text-to-Speech - facebook/fastspeech2-en-ljspeech POST {{baseUrl}}/models/:model

4. Speech-to-Text - openai/whisper-large-v3 POST {{baseUrl}}/models/:model

5. Text-to-Image - stabilityai/stable-diffusion-xl-base-1.0 POST {{baseUrl}}/models/:model

6. Image-to-Text - Salesforce/blip-image-captioning-large POST {{baseUrl}}/models/:model

7. Text-to-Audio - facebook/musicgen-stereo-large POST {{baseUrl}}/models/:model

8. Object Detection - facebook/detr-resnet-50 POST {{baseUrl}}/models/:model

9. Summarization - facebook/bart-large-cnn POST {{baseUrl}}/models/:model

10. Table Question Answering - microsoft/tapex-large-finetuned-wtq POST {{baseUrl}}/models/:model