This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the model’s latent reasoning capability without additional training by leveraging Test-Time Scaling techniques.
☆116Jun 25, 2025Updated last year
Alternatives and similar repositories for COT_steering
Users that are interested in COT_steering are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 1-Click is all you need.☆63Apr 29, 2024Updated 2 years ago
- 🎹 Instruct.KR 2025 Summer Meetup: 오픈소스 LLM, vLLM으로 Production까지 🎹☆23Aug 2, 2025Updated 11 months ago
- 구글에서 발표한 Chain-of-Thought Reasoning without Prompting을 코드로 구현한 레포입니다.☆65Sep 28, 2024Updated last year
- Ko-Arena-Hard-Auto: An automatic LLM benchmark for Korean☆22Apr 23, 2025Updated last year
- ☆64Jul 21, 2025Updated 11 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆67Mar 21, 2024Updated 2 years ago
- A lightweight adjustment tool for smoothing token probabilities in the Qwen models to encourage balanced multilingual generation.☆106Jul 9, 2025Updated last year
- 한국어 언어모델 다분야 사고력 벤치마크☆209Oct 17, 2024Updated last year
- KoLLaVA: Korean Large Language-and-Vision Assistant (feat.LLaVA)☆295Sep 20, 2024Updated last year
- [KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model☆73Aug 24, 2025Updated 10 months ago
- Forked repo from https://github.com/EleutherAI/lm-evaluation-harness/commit/1f66adc☆81Feb 28, 2024Updated 2 years ago
- ☆19Sep 3, 2024Updated last year
- SKT A.X LLM 4.0☆157Feb 11, 2026Updated 4 months ago
- Make running benchmark simple yet maintainable, again. Now only supports Korean-based cross-encoder.☆35Dec 2, 2025Updated 7 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Korean SAT leader board☆168Nov 20, 2025Updated 7 months ago
- Evaluate gpt-4o on CLIcK (Korean NLP Dataset)☆20May 18, 2024Updated 2 years ago
- nanoRLHF: from-scratch journey into how LLMs and RLHF really work.☆192Jul 2, 2026Updated last week
- LLM 모델의 외국어 토큰 생성을 막는 코드 구현☆87Aug 7, 2025Updated 11 months ago
- Extension of Langchain for RAG. Easy benchmarking, multiple retrievals, reranker, time-aware RAG, and so on...☆283Jan 9, 2024Updated 2 years ago
- ☆36Oct 4, 2023Updated 2 years ago
- Easy Instruction for DPO training☆24Oct 9, 2024Updated last year
- BERT score for text generation☆12Jan 15, 2025Updated last year
- KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models☆25Aug 24, 2024Updated 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.
- 한국어 벤치마크 평가 코드 통합본(?)☆21Nov 15, 2024Updated last year
- Gunmo-emo-classification: 한국어 감정 다중 분류 모델 제작법☆28Dec 12, 2023Updated 2 years ago
- High-performance vector search engine with no loss of accuracy through GPU and dynamic placement☆32Jul 12, 2025Updated 11 months ago
- Open Source + Multilingual MLLM + Fine-tuning + Distillation + More efficient models and learning + ?☆19Jan 31, 2025Updated last year
- Korean Sentence Embedding Model Performance Benchmark for RAG☆50Jan 27, 2025Updated last year
- ☆40Mar 11, 2025Updated last year
- 42dot LLM consists of a pre-trained language model, 42dot LLM-PLM, and a fine-tuned model, 42dot LLM-SFT, which is trained to respond to …☆133Mar 7, 2024Updated 2 years ago
- ☆25Jul 24, 2024Updated last year
- 언어모델을 학습하기 위한 공개 한국어 instruction dataset들을 모아두었습니다.☆467Apr 13, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆12Dec 20, 2024Updated last year
- KURE: 고려대학교에서 개발한, 한국어 검색에 특화된 임베딩 모델☆222Apr 14, 2026Updated 2 months ago
- Coord: A Unified Interface for All Models☆18Jun 19, 2026Updated 2 weeks ago
- ☆33Aug 30, 2023Updated 2 years ago
- Korean Multi-task Instruction Tuning☆156Dec 20, 2023Updated 2 years ago
- Efficient fine-tuning for ko-llm models☆183Mar 18, 2024Updated 2 years ago
- KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding☆312Jul 9, 2023Updated 3 years ago