A lightweight adjustment tool for smoothing token probabilities in the Qwen models to encourage balanced multilingual generation.
☆107Jul 9, 2025Updated last year
Alternatives and similar repositories for smoothie-qwen
Users that are interested in smoothie-qwen are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆64Jul 21, 2025Updated last year
- LLM 모델의 외국어 토큰 생성을 막는 코드 구현☆87Aug 7, 2025Updated last year
- ☆13Apr 17, 2024Updated 2 years ago
- Official code and dataset repository of KoBBQ (TACL 2024)☆22May 13, 2024Updated 2 years ago
- This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the model’s latent reasoning capabil…☆117Jun 25, 2025Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- The unofficial CLI of Amazon S3 Vectors (Preview) in Rust☆17Jul 19, 2025Updated last year
- ☆11Sep 19, 2025Updated 11 months ago
- ☆12Mar 25, 2022Updated 4 years ago
- [ACL 2025] DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues☆26Jul 10, 2025Updated last year
- Ko-Arena-Hard-Auto: An automatic LLM benchmark for Korean☆22Apr 23, 2025Updated last year
- StrategyQA 데이터 세트 번역☆22Apr 12, 2024Updated 2 years ago
- 🎹 Instruct.KR 2025 Summer Meetup: 오픈소스 LLM, vLLM으로 Production까지 🎹☆23Aug 2, 2025Updated last year
- Official repository for KoMT-Bench built by LG AI Research☆74Aug 8, 2024Updated 2 years ago
- Sakura-SOLAR-DPO: Merge, SFT, and DPO☆116Dec 30, 2023Updated 2 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆123Feb 25, 2026Updated 6 months ago
- Code for LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query Inference☆19Oct 19, 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 …☆134Mar 7, 2024Updated 2 years ago
- ☆10Oct 21, 2022Updated 3 years ago
- The Universe of Evaluation. All about the evaluation for LLMs.☆235Jul 9, 2024Updated 2 years ago
- Reward Model을 이용하여 언어모델의 답변을 평가하기☆30Feb 23, 2024Updated 2 years ago
- Model Resonance Imaging — visualize LLM internals like a brain MRI☆15Apr 10, 2026Updated 4 months ago
- bpe based korean t5 model for text-to-text unified framework☆63Apr 17, 2024Updated 2 years ago
- KoTAN: Korean Translation and Augmentation with fine-tuned NLLB☆23Jan 4, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆19Sep 20, 2022Updated 3 years ago
- [KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model☆73Aug 24, 2025Updated last year
- ☆109Aug 27, 2026Updated last week
- ☆40Mar 11, 2025Updated last year
- A hackable, simple, and reseach-friendly GRPO Training Framework with high speed weight synchronization in a multinode environment.☆38Aug 27, 2025Updated last year
- 한국어 언어모델 다분야 사고력 벤치마크☆208Oct 17, 2024Updated last year
- KURE: 고려대학교에서 개발한, 한국어 검색에 특화된 임베딩 모델☆231Updated this week
- Weak Labeling (NER) using ChatGPT☆37Mar 28, 2023Updated 3 years ago
- ☆49Apr 17, 2026Updated 4 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆38Oct 4, 2023Updated 2 years ago
- SKT A.X LLM 4.0☆160Feb 11, 2026Updated 6 months ago
- 1-Click is all you need.☆63Apr 29, 2024Updated 2 years ago
- 🤗 최소한의 세팅으로 LM을 학습하기 위한 샘플코드☆59May 23, 2023Updated 3 years ago
- ☆10Sep 13, 2024Updated last year
- Pipeline for employing a Lightweight deep learning models for LOW-power systems☆11Jan 9, 2023Updated 3 years ago
- Easy Language Model Pretraining leveraging Huggingface's Transformers and Datasets☆130Nov 12, 2022Updated 3 years ago