dnotitia / smoothie-qwenLinks
A lightweight adjustment tool for smoothing token probabilities in the Qwen models to encourage balanced multilingual generation.
☆88Updated 3 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:
- 1-Click is all you need.☆62Updated last year
- Official repository for EXAONE 3.5 built by LG AI Research☆200Updated 9 months ago
- ☆12Updated last year
- ☆20Updated last year
- ☆63Updated 2 months ago
- Ko-Arena-Hard-Auto: An automatic LLM benchmark for Korean☆23Updated 5 months ago
- This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the model’s latent reasoning capabil…☆113Updated 3 months ago
- Official repository for KoMT-Bench built by LG AI Research☆69Updated last year
- LLM 모델의 외국어 토큰 생성을 막는 코드 구현☆80Updated 2 months ago
- BERT score for text generation☆12Updated 8 months ago
- ☆12Updated 9 months ago
- Efficient fine-tuning for ko-llm models☆182Updated last year
- [ACL 2025] DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues☆25Updated 3 months ago
- 구글에서 발표한 Chain-of-Thought Reasoning without Prompting을 코드로 구현한 레포입니다.☆67Updated last year
- ☆32Updated 10 months ago
- Make running benchmark simple yet maintainable, again. Now only supports Korean-based cross-encoder.☆21Updated last week
- KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models☆25Updated last year
- A server application designed on top of MCP to interact with Cursor and MySQL.☆28Updated 6 months ago
- The Universe of Evaluation. All about the evaluation for LLMs.☆226Updated last year
- A hackable, simple, and reseach-friendly GRPO Training Framework with high speed weight synchronization in a multinode environment.☆31Updated last month
- Newsletter bot for 🤗 Daily Papers☆127Updated last week
- Official repository for EXAONE 4.0 built by LG AI Research☆84Updated 2 months ago
- Official repository for EXAONE Deep built by LG AI Research☆401Updated 4 months ago
- ☆68Updated last year
- The most modern LLM evaluation toolkit☆70Updated 2 weeks ago
- huggingface에 있는 한국어 데이터 세트☆30Updated last year
- OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca☆19Updated last year
- [KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model☆75Updated last month
- AutoRAG example about benchmarking Korean embeddings.☆40Updated last year
- Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)☆48Updated last year