# Low Resource Consumption

A 15-billion-parameter efficient inference model launched by ServiceNow, with memory usage only half that of comparable advanced models

HiDream-I1-Fast is a GGUF-quantized text-to-image generation model designed for fast image generation tasks.

LTX-Video is a model based on text-to-video generation technology, capable of generating corresponding video content based on input text descriptions.

OuteTTS-0.3-500M is a multilingual text-to-speech model supporting English, Chinese, Japanese, Korean, French, and German.

Fast speech recognition model based on OpenAI Whisper, optimized for inference speed using CTranslate2

Distilled version of Whisper Large v3 for efficient automatic speech recognition (ASR)

A news summarization model fine-tuned based on BART-large, using StableBeluga-7B as the teacher model to provide efficient and high-quality news summaries

A lightweight text summarization model fine-tuned on the xsum dataset based on t5-small, featuring fast generation speed and low resource usage

This is a binary classification model trained using AutoTrain, specifically designed for wasp image classification tasks.

This is an audio source separation model based on the RE-SepFormer architecture, implemented by SpeechBrain and trained on the WSJ0-2Mix dataset.

This is an entity recognition model trained via AutoTrain, featuring high accuracy and F1 score.

This model is a Named Entity Recognition (NER) model fine-tuned on the few_nerd dataset based on distilbert-base-uncased, achieving an F1 score of 0.7621 on the evaluation set.

A question-answering model fine-tuned on the Squad V2 dataset based on the Mobile-Bert architecture, suitable for resource-limited devices

A lightweight dialogue summarization model fine-tuned on the SAMSum dataset, trained using Amazon SageMaker and Hugging Face containers