A lightweight adjustment tool for smoothing token probabilities in the Qwen models to encourage balanced multilingual generation.
☆104Jul 9, 2025Updated 8 months ago
Alternatives and similar repositories for smoothie-qwen
Users that are interested in smoothie-qwen are comparing it to the libraries listed below
Sorting:
- LLM 모델의 외국어 토큰 생성을 막는 코드 구현☆84Aug 7, 2025Updated 7 months ago
- ☆64Jul 21, 2025Updated 7 months ago
- [ACL 2025] DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues☆26Jul 10, 2025Updated 7 months ago
- Official code and dataset repository of KoBBQ (TACL 2024)☆19May 13, 2024Updated last year
- ☆12Apr 17, 2024Updated last year
- This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the model’s latent reasoning capabil…☆115Jun 25, 2025Updated 8 months ago
- ☆11Sep 19, 2025Updated 5 months ago
- StrategyQA 데이터 세트 번역☆23Apr 12, 2024Updated last year
- ☆12Mar 25, 2022Updated 3 years ago
- Official repository for KoMT-Bench built by LG AI Research☆71Aug 8, 2024Updated last year
- [KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model☆73Aug 24, 2025Updated 6 months ago
- ☆116Feb 25, 2026Updated last week
- Reward Model을 이용하여 언어모델의 답변을 평가하기☆29Feb 23, 2024Updated 2 years ago
- 금융 도메인에 특화된 한국어 임베딩 모델☆23Aug 8, 2024Updated last year
- Sakura-SOLAR-DPO: Merge, SFT, and DPO☆116Dec 30, 2023Updated 2 years ago
- ☆102Apr 11, 2025Updated 10 months ago
- 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 …☆132Mar 7, 2024Updated 2 years ago
- ☆15May 20, 2023Updated 2 years ago
- Liner LLM Meetup archive☆71Mar 27, 2024Updated last year
- The Universe of Evaluation. All about the evaluation for LLMs.☆232Jul 9, 2024Updated last year
- Weak Labeling (NER) using ChatGPT☆37Mar 28, 2023Updated 2 years ago
- ☆36Oct 4, 2023Updated 2 years ago
- The unofficial CLI of Amazon S3 Vectors (Preview) in Rust☆15Jul 19, 2025Updated 7 months ago
- 🤗 최소한의 세팅으로 LM을 학습하기 위한 샘플코드☆59May 23, 2023Updated 2 years ago
- KURE: 고려대학교에서 개발한, 한국어 검색에 특화된 임베딩 모델☆205Feb 26, 2026Updated last week
- ☆19Sep 20, 2022Updated 3 years ago
- 한국어 언어모델 다분야 사고력 벤치마크☆201Oct 17, 2024Updated last year
- ☆39Mar 11, 2025Updated 11 months ago
- 1-Click is all you need.☆63Apr 29, 2024Updated last year
- OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca☆18Nov 1, 2023Updated 2 years ago
- bpe based korean t5 model for text-to-text unified framework☆63Apr 17, 2024Updated last year
- Korean Multi-task Instruction Tuning☆156Dec 20, 2023Updated 2 years ago
- The most modern LLM evaluation toolkit☆70Nov 9, 2025Updated 4 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 10 months ago
- 🎹 Instruct.KR 2025 Summer Meetup: 오픈소스 LLM, vLLM으로 Production까지 🎹☆23Aug 2, 2025Updated 7 months ago
- Performs benchmarking on two Korean datasets with minimal time and effort.☆46Jan 22, 2026Updated last month
- Quick access to any large language model from your browser.☆10Feb 16, 2026Updated 3 weeks ago
- Yet another frontend for LLM, written using .NET and WinUI 3☆10Sep 14, 2025Updated 5 months ago