Search Results for "artificial intelligence algorithm" - Page 5
Sort By:
Showing 215 open source projects for "artificial intelligence algorithm"
View related business solutions-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
Crowdtesting That Delivers | TesteumTesteum connects your software, app, or website to a worldwide network of testers, delivering detailed feedback in under 48 hours. Ensure functionality and refine UX on real devices, all at a fraction of traditional costs. Trusted by startups and enterprises alike, our platform streamlines quality assurance with actionable insights. Click to perfect your product now.
-
1
distilgpt2
DistilGPT2: Lightweight, distilled GPT-2 for faster text generation
DistilGPT2 is a smaller, faster, and lighter version of OpenAI’s GPT-2, distilled by Hugging Face using knowledge distillation techniques. With 82 million parameters, it retains most of GPT-2’s performance while significantly reducing size and computational requirements. It was trained on OpenWebText, a replication of OpenAI’s WebText dataset, using the same byte-level BPE tokenizer. The model excels in general-purpose English text generation and is well-suited for applications like... -
2
Qwen2.5-VL-3B-Instruct
Qwen2.5-VL-3B-Instruct: Multimodal model for chat, vision & video
Qwen2.5-VL-3B-Instruct is a 3.75 billion parameter multimodal model by Qwen, designed to handle complex vision-language tasks in both image and video formats. As part of the Qwen2.5 series, it supports image-text-to-text generation with capabilities like chart reading, object localization, and structured data extraction. The model can serve as an intelligent visual agent capable of interacting with digital interfaces and understanding long-form videos by dynamically sampling resolution and... -
3
Llama-3.2-1B
Llama 3.2–1B: Multilingual, instruction-tuned model for mobile AI
meta-llama/Llama-3.2-1B is a lightweight, instruction-tuned generative language model developed by Meta, optimized for multilingual dialogue, summarization, and retrieval tasks. With 1.23 billion parameters, it offers strong performance in constrained environments like mobile devices, without sacrificing versatility or multilingual support. It is part of the Llama 3.2 family, trained on up to 9 trillion tokens and aligned using supervised fine-tuning, preference optimization, and safety... -
4
siglip-so400m-patch14-384
SigLIP: Zero-shot image-text model with shape-optimized ViT
google/siglip-so400m-patch14-384 is a powerful zero-shot image classification model based on the SigLIP framework developed by Google. SigLIP introduces a new sigmoid contrastive loss, improving scalability and performance compared to traditional CLIP models. This specific variant uses a SoViT-400M architecture, a shape-optimized Vision Transformer trained on the large-scale WebLI dataset at 384×384 resolution. Unlike CLIP’s softmax-based loss, SigLIP’s sigmoid loss enables pairwise training... -
Sales CRM and Pipeline Management Software | PipedrivePipedrive’s simple interface empowers salespeople to streamline workflows and unite sales tasks in one workspace. Unlock instant sales insights with Pipedrive’s visual sales pipeline and fine-tune your strategy with robust reporting features and a personalized AI Sales Assistant.
-
5
bart-large-cnn
Summarization model fine-tuned on CNN/DailyMail articles
facebook/bart-large-cnn is a large-scale sequence-to-sequence transformer model developed by Meta AI and fine-tuned specifically for abstractive text summarization. It uses the BART architecture, which combines a bidirectional encoder (like BERT) with an autoregressive decoder (like GPT). Pre-trained on corrupted text reconstruction, the model was further trained on the CNN/DailyMail dataset—a collection of news articles paired with human-written summaries. It performs particularly well in... -
6
mms-300m-1130-forced-aligner
CTC-based forced aligner for audio-text in 158 languages
mms-300m-1130-forced-aligner is a multilingual forced alignment model based on Meta’s MMS-300M wav2vec2 checkpoint, adapted for Hugging Face’s Transformers library. It supports forced alignment between audio and corresponding text across 158 languages, offering broad multilingual coverage. The model enables accurate word- or phoneme-level timestamping using Connectionist Temporal Classification (CTC) emissions. Unlike other tools, it provides significant memory efficiency compared to the... -
7
vit-base-patch16-224-in21k
Base Vision Transformer pretrained on ImageNet-21k at 224x224
vit-base-patch16-224-in21k is a base-sized Vision Transformer (ViT) model pretrained by Google on the large-scale ImageNet-21k dataset, comprising 14 million images across over 21,000 classes. It was introduced in the paper "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale." This model uses 16x16 image patches and absolute positional embeddings, turning image classification into a token-based sequence modeling task akin to NLP transformers. While it lacks... -
8
yolo-world-mirror
Mirror of Ultralytics YOLO-World model weights for object detection
yolo-world-mirror is a hosted mirror of the model weights for YOLO-World, a variation of the YOLO (You Only Look Once) object detection architecture, designed and maintained by Ultralytics. This Hugging Face repository by Bingsu provides easy access to the pre-trained weights used in YOLO-World, supporting a range of visual tasks. YOLO-World expands the object detection framework to handle open-vocabulary detection, where the model can detect novel object classes based on textual input... -
9
esm2_t36_3B_UR50D
3B parameter ESM-2 model for protein sequence understanding
esm2_t36_3B_UR50D is a large-scale protein language model from Meta AI’s ESM-2 family, trained using a masked language modeling objective on protein sequences. It features 36 transformer layers and 3 billion parameters, offering high accuracy for protein-related downstream tasks such as structure prediction, mutation effect modeling, or function classification. The model is part of Meta’s ESM-2 series, which improves over previous versions with better performance and scalability. It takes... -
Secure remote access solution to your private network, in the cloud or on-prem.OpenVPN is here to bring simple, flexible, and cost-effective secure remote access to companies of all sizes, regardless of where their resources are located.
-
10
resnet18.a1_in1k
Lightweight ResNet-18 model trained on ImageNet with A1 recipe
resnet18.a1_in1k is a lightweight convolutional neural network from the timm library, implementing a ResNet-B variant trained on ImageNet-1K using the improved "ResNet Strikes Back" A1 training recipe. It features ReLU activations, a single 7x7 convolution with pooling, and 1x1 convolutional shortcuts for downsampling. With only 11.7 million parameters, it's designed to be efficient while maintaining strong baseline performance for image classification tasks. The model was optimized using... -
11
fashion-clip
CLIP model fine-tuned for zero-shot fashion product classification
FashionCLIP is a domain-adapted CLIP model fine-tuned specifically for the fashion industry, enabling zero-shot classification and retrieval of fashion products. Developed by Patrick John Chia and collaborators, it builds on the CLIP ViT-B/32 architecture and was trained on over 800K image-text pairs from the Farfetch dataset. The model learns to align product images and descriptive text using contrastive learning, enabling it to perform well across various fashion-related tasks without... -
12
distilbert-base-uncased-finetuned-sst-2
Sentiment analysis model fine-tuned on SST-2 with DistilBERT
distilbert-base-uncased-finetuned-sst-2-english is a lightweight sentiment classification model fine-tuned from DistilBERT on the SST-2 dataset. Developed by Hugging Face, it performs binary sentiment analysis (positive/negative) with high accuracy, achieving 91.3% on the dev set. It offers a smaller and faster alternative to BERT while retaining competitive performance (BERT scores ~92.7%). The model uses an uncased vocabulary and supports PyTorch, TensorFlow, ONNX, and Rust for broad... -
13
jina-embeddings-v3
Multilingual task-adaptive embeddings for 94 languages and NLP tasks
jina-embeddings-v3 is a multilingual, multi-task text embedding model developed by Jina AI, designed to generate highly adaptable representations across a wide range of natural language processing tasks. Built on a modified XLM-RoBERTa architecture with Rotary Position Embeddings (RoPE), it supports long inputs up to 8192 tokens. The model includes five task-specific LoRA adapters—covering retrieval, classification, clustering, and text matching—that allow users to optimize embeddings for... -
14
deberta-v3-base
Improved DeBERTa model with ELECTRA-style pretraining
DeBERTa-v3-base is an enhanced version of Microsoft’s DeBERTa model, integrating ELECTRA-style pretraining and Gradient-Disentangled Embedding Sharing for improved performance. It builds upon the original DeBERTa's disentangled attention mechanism and enhanced mask decoder, enabling more effective representation learning than BERT or RoBERTa. The base version includes 12 layers, a hidden size of 768, and 86 million backbone parameters, with a 128K-token vocabulary contributing to 98M... -
15
paraphrase-multilingual-mpnet-base-v2
Multilingual sentence embeddings for search and similarity tasks
paraphrase-multilingual-mpnet-base-v2 is a sentence-transformers model designed to generate dense vector representations of sentences and paragraphs in 50 languages. Developed by the Sentence Transformers team, it is particularly well-suited for tasks like semantic search, clustering, and paraphrase detection. The model maps input text to a 768-dimensional vector space, making it easy to compare the semantic meaning of different sentences. Based on the XLM-RoBERTa architecture and trained... -
16
Qwen2.5-VL-7B-Instruct
Multimodal 7B model for image, video, and text understanding tasks
Qwen2.5-VL-7B-Instruct is a multimodal vision-language model developed by the Qwen team, designed to handle text, images, and long videos with high precision. Fine-tuned from Qwen2.5-VL, this 7-billion-parameter model can interpret visual content such as charts, documents, and user interfaces, as well as recognize common objects. It supports complex tasks like visual question answering, localization with bounding boxes, and structured output generation from documents. The model is also... -
17
vit-base-patch16-224
Transformer model for image classification with patch-based input.
vit-base-patch16-224 is a Vision Transformer (ViT) model developed by Google for image classification tasks. It was pretrained on ImageNet-21k (14 million images, 21,843 classes) and fine-tuned on ImageNet-1k (1 million images, 1,000 classes), both using 224x224 resolution. The model treats images as sequences of 16x16 pixel patches, which are linearly embedded and processed using a transformer encoder. A special [CLS] token is used to summarize the image for classification. ViT learns... -
18
Hunyuan-A13B-Instruct
Efficient 13B MoE language model with long context and reasoning modes
Hunyuan-A13B-Instruct is a powerful instruction-tuned large language model developed by Tencent using a fine-grained Mixture-of-Experts (MoE) architecture. While the total model includes 80 billion parameters, only 13 billion are active per forward pass, making it highly efficient while maintaining strong performance across benchmarks. It supports up to 256K context tokens, advanced reasoning (CoT) abilities, and agent-based workflows with tool parsing. The model offers both fast and slow... -
19
paraphrase-MiniLM-L6-v2
Lightweight sentence embedding model for semantic search
paraphrase-MiniLM-L6-v2 is a sentence-transformers model that encodes sentences and paragraphs into 384-dimensional dense vectors. It is specifically optimized for semantic similarity tasks such as paraphrase mining, clustering, and semantic search. The model is built on a lightweight MiniLM architecture, making it both fast and efficient for large-scale inference. It supports integration via both the sentence-transformers and transformers libraries, with built-in pooling strategies like... -
20
voice-activity-detection
Detects speech activity in audio using pyannote.audio 2.1 pipeline
The voice-activity-detection model by pyannote is a neural pipeline for detecting when speech occurs in audio recordings. Built on pyannote.audio 2.1, it identifies segments of active speech within any audio file, making it valuable for preprocessing tasks like transcription, diarization, or voice-controlled systems. The model was trained using datasets such as AMI, DIHARD, and VoxConverse, and it requires users to authenticate via Hugging Face for access. To use the model, users must accept... -
21
wav2vec2-large-xlsr-53-portuguese
Portuguese ASR model fine-tuned on XLSR-53 for 16kHz audio input
wav2vec2-large-xlsr-53-portuguese is an automatic speech recognition (ASR) model fine-tuned on Portuguese using the Common Voice 6.1 dataset. It is based on Facebook’s wav2vec2-large-xlsr-53, a multilingual self-supervised learning model, and is optimized to transcribe Portuguese speech sampled at 16kHz. The model performs well without a language model, though adding one can improve word error rate (WER) and character error rate (CER). It achieves a WER of 11.3% (or 9.01% with LM) on Common... -
22
bge-base-en-v1.5
Efficient English embedding model for semantic search and retrieval
bge-base-en-v1.5 is an English sentence embedding model from BAAI optimized for dense retrieval tasks, part of the BGE (BAAI General Embedding) family. It is a fine-tuned BERT-based model designed to produce high-quality, semantically meaningful embeddings for tasks like semantic similarity, information retrieval, classification, and clustering. This version (v1.5) improves retrieval performance and stabilizes similarity score distribution without requiring instruction-based prompts. With... -
23
ms-marco-MiniLM-L6-v2
Efficient cross-encoder for MS MARCO passage re-ranking tasks
ms-marco-MiniLM-L6-v2 is a lightweight cross-encoder fine-tuned on the MS MARCO Passage Ranking dataset to deliver strong retrieval and reranking performance. It is based on a 6-layer MiniLM model and trained to directly score the relevance between query-passage pairs. The model outputs a single relevance score per pair and is used in re-ranking pipelines after an initial candidate set is retrieved (e.g., with BM25). Despite its compact 22.7M parameter size, it achieves an MRR@10 of 39.01 on... -
24
multilingual-e5-large
High-performance multilingual embedding model for 94 languages
multilingual-e5-large is a powerful sentence embedding model trained on a diverse set of multilingual datasets and fine-tuned for both symmetric and asymmetric text retrieval tasks. Based on xlm-roberta-large, the model generates 1024-dimensional embeddings across 94 languages, optimized for semantic search, clustering, bitext mining, and cross-lingual retrieval. It uses the "query:" and "passage:" prefix convention for improved performance and supports batch encoding through both Hugging... -
25
answerai-colbert-small-v1
Compact multi-vector retriever with state-of-the-art ranking accuracy
answerai-colbert-small-v1 is a 33M parameter multi-vector retrieval model developed by Answer.AI, using the JaColBERTv2.5 training recipe. Despite its small size (MiniLM scale), it surpasses many larger models—including e5-large-v2 and bge-base-en-v1.5—on standard information retrieval benchmarks. It is optimized for retrieval-augmented generation (RAG), reranking, and vector search, compatible with ColBERT, RAGatouille, and Rerankers libraries. The model achieves top performance in tasks...
