sionic-ai / Llama4-Token-Editor
☆52Updated last week
Alternatives and similar repositories for Llama4-Token-Editor:
Users that are interested in Llama4-Token-Editor are comparing it to the libraries listed below
- This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the model’s latent reasoning capabil…☆88Updated 3 weeks ago
- ☆34Updated last month
- ☆41Updated last year
- 한국어 심리 상담 데이터셋☆77Updated last year
- LLM 모델의 외국어 토큰 생성을 막는 코드 구현☆67Updated 3 weeks ago
- [KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model☆75Updated last year
- Korean SAT leader board☆165Updated last month
- Gugugo: 한국어 오픈소스 번역 모델 프로젝트☆78Updated last year
- Unofficial API for CLOVA X☆37Updated last year
- 구글에서 발표한 Chain-of-Thought Reasoning without Prompting을 코드로 구현한 레포입니다.☆64Updated 6 months ago
- ☆25Updated 8 months ago
- Kor-IR: Korean Information Retrieval Benchmark☆84Updated 9 months ago
- Make running benchmark simple yet maintainable, again. Now only supports Korean-based cross-encoder.☆14Updated 2 weeks ago
- A tool for manual conversion of BGE-M3 models with preserved trainable variables and direct control over model outputs.☆40Updated 2 months ago
- ☆46Updated 9 months ago
- 한국어 언어모델 오픈소스☆82Updated last year
- Kiwi 형태소 분석기를 활용한 딥러닝 언어 모델 실험실☆52Updated last year
- hwplib 패키지 python에서 쉽게 사용 할수 있게 만든 github repo 입니다.☆34Updated 2 weeks ago
- ☆124Updated last year
- ☆67Updated last year
- IA3방식으로 KoAlpaca를 fine tuning한 한국어 LLM모델☆68Updated last year
- OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca☆19Updated last year
- A loader that lets you try running LLMs built for WebGPU.☆29Updated last year
- KoTAN: Korean Translation and Augmentation with fine-tuned NLLB☆23Updated last year
- ☆17Updated 7 months ago
- 한국어 언어모델 다분야 사고력 벤치마크☆189Updated 6 months ago
- KURE: 고려대학교에서 개발한, 한국어 검색에 특화된 임베딩 모델☆158Updated last month
- 한국어 의료 분야 특화 챗봇 프로젝트☆30Updated 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 …☆130Updated last year
- Official repository for KoMT-Bench built by LG AI Research☆62Updated 8 months ago