dnotitia / smoothie-qwen
A lightweight adjustment tool for smoothing token probabilities in the Qwen models to encourage balanced multilingual generation.
☆36Updated last week
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.☆61Updated last year
- Ko-Arena-Hard-Auto: An automatic LLM benchmark for Korean☆23Updated 2 weeks ago
- BERT score for text generation☆11Updated 3 months ago
- 구글에서 발표한 Chain-of-Thought Reasoning without Prompting을 코드로 구현한 레포입니다.☆65Updated 7 months ago
- ☆12Updated last year
- Make running benchmark simple yet maintainable, again. Now only supports Korean-based cross-encoder.☆18Updated 2 weeks ago
- ☆60Updated last week
- This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the model’s latent reasoning capabil…☆100Updated 2 weeks ago
- hwpxlib 패키지 python에서 쉽게 사용 할수 있게 만든 github repo 입니다.☆33Updated last month
- Build complex LLM Applications with Python Dictionary☆40Updated 7 months ago
- Newsletter bot for 🤗 Daily Papers☆120Updated this week
- It shows a problem solver based on agentic workflow.☆16Updated 2 months ago
- An extended project of the LLM Compiler paper, focusing on developing LLM-based Autonomous Agents.☆23Updated 6 months ago
- Official repository for KoMT-Bench built by LG AI Research☆61Updated 9 months ago
- ☆19Updated 9 months ago
- KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models☆25Updated 8 months ago
- generate synthetic data for LLM fine-tuning in arbitrary situations within systematic way☆21Updated last year
- OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca☆19Updated last year
- huggingface에 있는 한국어 데이터 세트☆28Updated 7 months ago
- ☆31Updated 5 months ago
- ☆36Updated 2 months ago
- evolve llm training instruction, from english instruction to any language.☆117Updated last year
- LLM 모델의 외국어 토큰 생성을 막는 코드 구현☆72Updated last month
- ☆11Updated 4 months ago
- 자체 구축한 한국어 평가 데이터셋을 이용한 한국어 모델 평가☆31Updated 11 months ago
- Toy O☆16Updated 7 months ago
- ☆68Updated last year
- AutoRAG example about benchmarking Korean embeddings.☆38Updated 7 months ago
- Official repository for EXAONE 3.5 built by LG AI Research☆188Updated 4 months ago
- ☆10Updated last year