# Zero-shot learning

A zero-shot classification model based on the Transformers architecture that can classify text without fine-tuning

This is an automatically generated transformers model card, and specific information is to be supplemented.

This is a transformers model published on Hub. The specific functions and detailed information are to be supplemented.

This is a transformers model that has been pushed to the Hub. The specific functions and uses are to be supplemented.

YingLong is a pretrained model for time series forecasting, which has been pretrained on 78 billion time points and provides strong support for time series forecasting tasks.

GPT-2 is an open-source language model developed by OpenAI, based on the Transformer architecture, capable of generating coherent text.

A multilingual text classification model fine-tuned based on xlm-roberta-large, supporting English and Danish, focusing on political agenda and media content classification tasks.

A feature extraction model fine-tuned based on openai/clip-vit-large-patch14, optimizing the image and text encoders

A vision model based on the Vision Transformer architecture, trained using SigLIP (Sigmoid Loss for Language-Image Pretraining), suitable for image understanding tasks.

An 8B-parameter large language model fused via MergeKit from multiple high-quality models, optimized for reasoning, dialogue, and creative generation

Granite Vision 3.2 2B is a vision-language model developed by IBM, focusing on image-to-text tasks.

YOLOE is an efficient, unified, and open model for object detection and segmentation, supporting various prompting mechanisms including text, visual inputs, and prompt-free paradigms, achieving real-time universal visual perception.

A 72B-parameter multimodal foundation model released by ByteDance Research, specializing in image-text-to-text tasks

Whisper large-v3-turbo is an automatic speech recognition and speech translation model proposed by OpenAI, trained with large-scale weak supervision and supporting multiple languages.

Lamarckvergence-14B is a pre-trained language model merged via mergekit, combining Lamarck-14B-v0.7 and Qwenvergence-14B-v12-Prose-DS. It ranks first among models with fewer than 15B parameters on the Open LLM Leaderboard.

DepthMaster is a refined single-step diffusion model that customizes generative features from diffusion models for discriminative depth estimation tasks.

This model is a text generation model capable of producing coherent text content based on input prompts.

ResNet101 image encoder based on CLIP framework, extracting image features through Global Average Pooling (GAP)

This is a model checkpoint provided for the Any-to-Any subnet collaboration between OMEGA Labs and Bittensor, aiming to achieve general artificial intelligence tasks.

The Any-to-Any Subnet Model jointly developed by OMEGA Labs and Bittensor, focusing on general artificial intelligence tasks.

Florence-2 is an advanced visual foundation model developed by Microsoft, employing a prompt-based architecture to unify various vision and vision-language tasks

A compact pre-trained model for multivariate time series forecasting open-sourced by IBM Research, with parameter scales starting from 1 million, pioneering the concept of 'tiny' pre-trained time series forecasting models.

Show-o is a PyTorch-based any-to-any conversion model focused on multimodal task processing.

Show-o is an any-to-any conversion model based on PyTorch, supporting input and output conversion across multiple modalities.

This is a monolingual Czech SpeechT5 base model, pre-trained on 120,000 hours of Czech audio and a 17.5 billion-word text corpus, designed as a starting point for Czech TTS fine-tuning.

A sparse retrieval model based on distillation technology, optimized for OpenSearch, supporting inference-free document encoding with improved search relevance and efficiency over V1

All-round image generation and editing control network, supporting 12 control conditions and 5 advanced editing functions

BitNet b1.58 is a large language model with 1.58-bit quantization. It reduces the computational resource requirements by lowering the weight precision while maintaining performance close to that of a full-precision model.

Florence-2 is an advanced vision foundation model developed by Microsoft, employing a prompt-based approach to handle various vision and vision-language tasks.

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, offering finer details and stronger robustness.

Badger is a Llama3 8B instruction model generated through recursive maximum pairwise disjoint normalized denoising Fourier interpolation method, incorporating features from multiple high-quality models.

MobileCLIP-S2 is an efficient image-text model that achieves rapid inference through multimodal reinforcement training, delivering outstanding zero-shot performance while maintaining a compact size.

Compare2Score is a model for image quality assessment that provides a quality score for images through a specific algorithm.

This model is released under the MIT license, specific details are currently unknown.

An Italian large language model optimized based on Meta-Llama-3-8B, supporting English and Italian text generation tasks

This is an open-source model using the Apache-2.0 license; specific details need to be supplemented

StrangeMerges_53-7B-model_stock is the result of merging multiple 7B-parameter models using LazyMergekit, possessing powerful text generation capabilities.

BitNet b1.58 is a 1-bit large language model with 3 billion parameters, trained on the RedPajama dataset for 100 billion tokens.

BitNet b1.58 3B is a 1-bit quantized large language model trained on 100 billion tokens from the RedPajama dataset, significantly reducing computational resource requirements while maintaining performance.