전체 검색

AI 모델 84999

• KURE-v1↗

  nlpai-lab

  Introducing Korea University Retrieval Embedding model, KURE-v1 It has shown remarkable performance in Korean text retrieval, speficially overwhelming most multilingual embedding models. To our knowledge, It is one of the best publicly opened Korean retrieval models. This is the model card of a 🤗 transformers model that has been pushed on the Hub. - **Developed by:** NLP&AI Lab - **Language(s) (NLP):** Korean, English - **License:** MIT - **Finetuned from model:** BAAI/bge-m3

• amdchess-v9↗

  nlpguy

• CUDA-Autocomplete↗

  NVIDIA

• GPT-5.6 Luna (Xhigh)↗

  OpenAI

• InternVideo2-Stage1-1B-224p-f8↗

  OpenGVLab

• NightyGurps-14b-v1.1-GGUF↗

  QuantFactory

• Qwen3.8-Flash-Next-4bit↗

  rapid-mlx

• GPT2-ChineseDevBench↗

  Recor2d

• ParasiticRogue_-_Merged-RP-Stew-V2-34B-gguf↗

  RichardErkhov

• sarvam-105b↗

  sarvamai

  1. Introduction 2. Architecture 3. Benchmarks - Knowledge & Coding - Reasoning & Math - Agentic 4. Inference - Hugging Face - vLLM - SGLang 5. Footnote 6. Citation **Sarvam-105B** is an advanced Mixture-of-Experts (MoE) model with 10.3B active parameters, designed for superior performance across a wide range of complex tasks. It is highly optimized for complex reasoning, with particular strength in agentic tasks, mathematics, and coding. Sarvam-105B is a top-tier performer, consistently matching or surpassing several major closed-source models and staying within a narrow margin of frontier models across diverse reasoning and agentic benchmarks. It demonstrates exceptional agentic and reasoning capabilities in real-world applications such as web search and technical troubleshooting.