Trendyol LLM v4.1.0 is a generative model based on Trendyol LLM base v4.0 (a Qwen2.5 7B version further pre-trained on 13 billion tokens), specializing in e-commerce and Turkish language understanding.

Natural Language ProcessingSafetensorsOther

A conversational embedding model optimized for e-commerce search, fine-tuned based on Stella Embed 400M v5, excelling at understanding natural language queries and matching relevant products

Natural Language ProcessingTransformersMultiple Languages

This is a fine-tuned model based on the DistilBERT architecture, specifically designed for product classification tasks in the e-commerce domain.

Natural Language ProcessingOnnxEnglish

COLD2 is a PyTorch-based fill-mask model specifically designed to address missing words in e-commerce search queries.

Natural Language ProcessingTransformersOther

A sentence similarity model optimized for Russian e-commerce search queries, specifically designed for differentiating product search queries

Natural Language ProcessingSafetensorsOther

This model is an e-commerce domain chatbot model fine-tuned based on meta-llama/Llama-3.2-3B-Instruct, focusing on the interaction needs in the e-commerce scenario.

Natural Language ProcessingTransformersEnglish

LoRA diffusion model based on the FLUX framework, designed specifically for virtual try-on and fashion e-commerce scenarios of Ray-Ban Meta smart glasses

Computer VisionDiffusers

A model for providing relevance scores between e-commerce search queries and products, usable as a retriever/ranker

Natural Language ProcessingTransformers

A text-to-image diffusion model optimized for e-commerce scenarios, developed based on Stable Diffusion XL, with instance mask fine-tuning to prevent foreground overflow.

Computer VisionDiffusersEnglish

EcomXL is a text-to-image diffusion model optimized for e-commerce scenarios, developed based on Stable Diffusion XL, with excellent generation capabilities for both general and e-commerce applications.

Computer VisionDiffusersEnglish

eCeLLM-M is a large language model for the e-commerce domain, obtained through instruction fine-tuning based on the Mistral-7B Instruct-v0.2 foundation model, aiming to enhance language understanding and generation capabilities in e-commerce scenarios.

Natural Language ProcessingTransformers

This is a model based on sentence-transformers that can map sentences and paragraphs into a 768-dimensional dense vector space, suitable for text similarity calculation and semantic search tasks in the e-commerce domain.

Natural Language ProcessingTransformersMultiple Languages

This model is specifically designed for extracting keywords and core opinions from e-commerce comments, trained on 5,000 Taobao reviews.

Natural Language ProcessingTransformersChinese

YODA is a named entity recognition model optimized for Google Feed products, focusing on feature extraction from e-commerce product metadata

Natural Language ProcessingTensorboardSpanish

A post-trained BERT model based on review corpora, focusing on understanding sentiment, options, and various e-commerce-related dimensions

Natural Language ProcessingJax

A post-trained model based on BERT-base-uncased, optimized for understanding sentiments and options in e-commerce reviews

Natural Language ProcessingJax

BERT model post-trained on laptop review corpus, specializing in understanding sentiment orientation and e-commerce domain features

Natural Language ProcessingJax

BERT model post-trained on Yelp restaurant review data, specializing in sentiment analysis and multi-dimensional understanding of e-commerce reviews

Natural Language ProcessingJax