Tarka-Embedding-350M-V1 is a text embedding model with 350 million parameters, capable of generating 1024-dimensional dense text representations. This model is optimized for downstream applications such as semantic similarity, search, and retrieval-augmented generation (RAG), supports multiple languages, and has the ability to handle long contexts.

Natural Language ProcessingSentence-transformers

Tarka-Embedding-150M-V1 is an embedding model with 150 million parameters, capable of generating 768-dimensional dense text representations. It is optimized for various downstream applications such as semantic similarity, search, and retrieval-augmented generation (RAG), focusing on capturing deep contextual semantics to support general text understanding across different domains.

Natural Language ProcessingSentence-transformers

Vi-Qwen2-7B-RAG is a large language model customized for retrieval-augmented generation (RAG) tasks. It is fine-tuned on a Vietnamese dataset based on Qwen2-7B-Instruct, significantly improving the Vietnamese processing ability and the execution efficiency of RAG tasks.

Natural Language ProcessingTransformersOther

Vietnamese Retrieval-Augmented Generation (RAG) specialized large model fine-tuned based on Qwen2.5-7B-Instruct, trained using GRPO optimization method

Natural Language ProcessingTransformersOther

Qwen-2.5-7B-base-RAG-RL is a large language model with 7B parameters trained from scratch on an unknown dataset, incorporating Retrieval-Augmented Generation (RAG) and Reinforcement Learning (RL) technologies.

Natural Language ProcessingTransformers

ReaRAG-9B is an enhanced model trained on glm-4-9b, capable of generating knowledge-guided reasoning chains and supporting iterative retrieval-augmented generation.

Natural Language ProcessingPytorchMultiple Languages

Pleias-RAG-1B is a 1.2B-parameter compact reasoning model specifically designed for retrieval-augmented generation (RAG), search, and document summarization tasks. It excels in multilingual RAG tasks and supports structured citation generation.

Natural Language ProcessingTransformersMultiple Languages

Pleias-RAG-350M is a 350-million-parameter compact reasoning model specifically trained for retrieval-augmented generation (RAG), search, and source summarization tasks.

Natural Language ProcessingTransformersMultiple Languages

A Korean large language model fine-tuned based on Qwen2.5-14B, specializing in RAG (Retrieval-Augmented Generation) tasks, capable of generating structured responses with source citations.

Natural Language ProcessingSafetensorsKorean

The first retriever specifically designed for financial time series forecasting, based on the Retrieval-Augmented Generation (RAG) framework

Natural Language ProcessingTransformersEnglish

FinSeer StockLLM is an open-source 1-billion-parameter large language model specifically designed for financial time series forecasting, utilizing a Retrieval-Augmented Generation (RAG) framework.

Natural Language ProcessingTransformersEnglish

Provence is a lightweight context pruning model optimized for retrieval-augmented generation, especially suitable for Q&A scenarios.

Natural Language ProcessingSafetensorsEnglish

A finance-domain retrieval-augmented generation model optimized based on the stella_en_400M_v5 architecture, supporting semantic retrieval and paragraph matching for financial documents

Natural Language ProcessingSafetensorsOther

VisRAG is a retrieval-augmented generation (RAG) system based on vision-language models (VLM) that can directly embed documents as images, avoiding information loss caused by traditional text parsing.

MultimodalSafetensorsEnglish

Mistral-NeMo-Minitron-8B-Instruct is a text generation model developed by NVIDIA, supporting various tasks such as role-playing, retrieval-augmented generation, and function calls, with the characteristics of high efficiency and accuracy.

Natural Language ProcessingTransformers

Nemotron-Mini-4B-Instruct is a response generation model developed by NVIDIA, optimized for role-playing, retrieval-augmented generation, and function calling. It is fine-tuned based on Minitron-4B-Base and supports a context length of 4096 tokens.

Natural Language ProcessingTransformersEnglish

Command R+ 08-2024 is a 104 billion parameter multilingual large language model that supports Retrieval-Augmented Generation (RAG) and tool usage, suitable for automating complex tasks.

Natural Language ProcessingTransformersMultiple Languages

Cohere Lab's Command R 08-2024 is a high-performance 32-billion parameter generative model supporting multilingual generation and Retrieval-Augmented Generation (RAG) capabilities.

Natural Language ProcessingTransformersMultiple Languages

Marsilia-Embeddings-FR-Base is a French embedding model specifically designed for financial domain tasks, demonstrating the importance of task-specific fine-tuning for embedding models in Retrieval-Augmented Generation (RAG) applications.

Natural Language ProcessingTransformersFrench

Vietnamese text embedding model focused on RAG (Retrieval-Augmented Generation) and productivity, fine-tuned based on intfloat/multilingual-e5-base

Natural Language ProcessingSafetensorsMultiple Languages