davidkim205 / noxLinks
Efficient fine-tuning for ko-llm models
☆185Updated last year
Alternatives and similar repositories for nox
Users that are interested in nox are comparing it to the libraries listed below
Sorting:
- 1-Click is all you need.☆63Updated last year
- The Universe of Evaluation. All about the evaluation for LLMs.☆231Updated last year
- Sakura-SOLAR-DPO: Merge, SFT, and DPO☆116Updated 2 years ago
- A lightweight adjustment tool for smoothing token probabilities in the Qwen models to encourage balanced multilingual generation.☆103Updated 6 months ago
- Extension of Langchain for RAG. Easy benchmarking, multiple retrievals, reranker, time-aware RAG, and so on...☆284Updated 2 years ago
- evolve llm training instruction, from english instruction to any language.☆119Updated 2 years ago
- ☆12Updated last year
- manage histories of LLM applied applications☆91Updated 2 years ago
- Newsletter bot for 🤗 Daily Papers☆133Updated 2 weeks ago
- [KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model☆73Updated 5 months ago
- OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca☆18Updated 2 years ago
- 자체 구축한 한국어 평가 데이터셋을 이용한 한국어 모델 평가☆31Updated last year
- Official repository for EXAONE 3.5 built by LG AI Research☆202Updated last year
- ☆15Updated 2 years ago
- ☆20Updated last year
- Make running benchmark simple yet maintainable, again. Now only supports Korean-based cross-encoder.☆28Updated 2 months ago
- ☆69Updated last year
- This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the model’s latent reasoning capabil…☆114Updated 7 months ago
- 구글에서 발표한 Chain-of-Thought Reasoning without Prompting을 코드로 구현한 레포입니다.☆65Updated last year
- LLM 모델의 외국어 토큰 생성을 막는 코드 구현☆83Updated 5 months ago
- nanoRLHF: from-scratch journey into how LLMs and RLHF really work.☆146Updated last week
- generate synthetic data for LLM fine-tuning in arbitrary situations within systematic way☆22Updated last year
- Here's how to use Lama3 for beginners and what services are being used.☆77Updated last year
- Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)☆48Updated last year
- ☆64Updated 6 months ago
- [ACL'25] Official Code for LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs☆314Updated 6 months ago
- ☆115Updated 6 months ago
- Official repository for KoMT-Bench built by LG AI Research☆71Updated last year
- Korean Multi-task Instruction Tuning☆156Updated 2 years ago
- Ko-Arena-Hard-Auto: An automatic LLM benchmark for Korean☆22Updated 9 months ago