Enhanced multi-needle retrieval testing framework for evaluating LLM long-context understanding capabilities
☆12Oct 8, 2025Updated last year
Alternatives and similar repositories for dnotitia-NIAH
Users that are interested in dnotitia-NIAH are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Codex, Claude Code 스킬: 한글 파일(.hwpx) 자동 분석 및 작성 도구☆17Sep 30, 2026Updated last month
- Experimental validation of the Bayesian BM25 paper☆10Feb 16, 2026Updated 8 months ago
- Azure OpenAI 프롬프톤☆11Sep 23, 2024Updated 2 years ago
- Korean MTEB Retrieval Evaluators for SPLADE, Dense, and Reranking models☆14Jul 21, 2026Updated 3 months ago
- A lightweight adjustment tool for smoothing token probabilities in the Qwen models to encourage balanced multilingual generation.☆110Jul 9, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Efficient Finetuning for OpenAI GPT-OSS☆24Oct 2, 2025Updated last year
- A local-LLM based Graph RAG agent using FalkorDB☆21Dec 24, 2025Updated 10 months ago
- LLM-as-a-judge using G-eval Scratch☆15Oct 12, 2025Updated last year
- A framework for benchmarking embedding models in hybrid search scenarios (BM25 + vector search) using Weaviate.☆40Oct 31, 2026Updated last week
- This is a DQN-based recommendation system for item-list recommendation and it finally achieved second place in the competition of RL-base…☆11Oct 8, 2021Updated 5 years ago
- Generate workflows (for flowcharts or low code) via LLM. Also describe workflow given in DOT.☆19Nov 2, 2023Updated 3 years ago
- Reading comprehension based question-answering model for news articles.☆11Jun 22, 2022Updated 4 years ago
- Generate fixed dimensional embeddings for multi-dimensional vectors in python based on Muvera from Google.☆21Jun 28, 2025Updated last year
- Qwen3 MoE Router Statistics | 큐웬3 MoE☆11May 16, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- HSEB: Hybrid Search Engine Benchmark☆21Oct 5, 2025Updated last year
- The training codes of Jasper-Token-Compression-600M☆22Nov 19, 2025Updated 11 months ago
- Re-ranking task using MS MARCO dataset and Hugging Face library☆15Jun 7, 2020Updated 6 years ago
- Open-source RL Framework with Online Teacher-Student Distillation☆23Mar 5, 2026Updated 8 months ago
- ☆15Dec 17, 2025Updated 10 months ago
- An implementation of online data mixing for the Pile dataset, based on the GPT-NeoX library.☆15Jan 9, 2024Updated 2 years ago
- Visualization of raw KITTI dataset, using rerun-io☆10Mar 15, 2024Updated 2 years ago
- 🎹 Instruct.KR 2025 Summer Meetup: 오픈소스 LLM, vLLM으로 Production까지 🎹☆23Aug 2, 2025Updated last year
- AutoRAG example about benchmarking Korean embeddings.☆46Oct 2, 2024Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- The Python Implementation of CRISP: Clustering Multi-Vector Representations for Denoising and Pruning☆27Jul 27, 2025Updated last year
- Performs benchmarking on two Korean datasets with minimal time and effort.☆49Aug 6, 2026Updated 3 months ago
- Unofficial PyTorch Implementation of "Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential".☆13Oct 8, 2025Updated last year
- KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval☆16Aug 8, 2026Updated 3 months ago
- AskUp Search ChatGPT Plugin☆20May 27, 2023Updated 3 years ago
- Example project to take a shot at nginx unit☆11Dec 11, 2018Updated 7 years ago
- Evaluate gpt-4o on CLIcK (Korean NLP Dataset)☆20May 18, 2024Updated 2 years ago
- No code tool for finetuning embedding models☆35Nov 2, 2026Updated last week
- 각종 프로그램이 설치하는 루트 인증 기관(Root CA) 인증서 목록☆13Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆83Feb 16, 2022Updated 4 years ago
- This repository forked from parlAI. Korean Wizard of Wikipedia task was added to this repo. This repository is going to be moved after EM…☆16Dec 9, 2022Updated 3 years ago
- A Unified Framework for Document Parsing Tasks (Including Document Layout Analysis, OCR, Formula Recognition, and Table Recognition)☆15Jul 1, 2025Updated last year
- Official datasets and pytorch implementation repository of SQuARe and KoSBi (ACL 2023)☆256Jun 29, 2023Updated 3 years ago
- Generate paper-curation reviews for Zotero items via original paper-curation functions (Anthropic / OpenAI / Gemini)☆15Nov 4, 2026Updated last week
- ☆11Apr 19, 2021Updated 5 years ago
- SpectraFuse: an independent implementation inspired by SpectRAG (arXiv:2610.36991). Official SpectRAG: github.com/SightAndCite/SpectRAG☆26Nov 4, 2026Updated last week
Are these results useful?