dnotitia / smoothie-qwenLinks
A lightweight adjustment tool for smoothing token probabilities in the Qwen models to encourage balanced multilingual generation.
☆73Updated last month
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
- ☆62Updated last month
- Ko-Arena-Hard-Auto: An automatic LLM benchmark for Korean☆23Updated 2 months ago
- ☆20Updated 11 months ago
- Make running benchmark simple yet maintainable, again. Now only supports Korean-based cross-encoder.☆18Updated this week
- Sakura-SOLAR-DPO: Merge, SFT, and DPO☆116Updated last year
- ☆12Updated last year
- BERT score for text generation☆12Updated 5 months ago
- Official repository for KoMT-Bench built by LG AI Research☆63Updated 10 months ago
- huggingface에 있는 한국어 데이터 세트☆28Updated 8 months ago
- ☆11Updated 6 months ago
- Official repository for EXAONE 3.5 built by LG AI Research☆190Updated 6 months ago
- This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the model’s latent reasoning capabil…☆109Updated this week
- 구글에서 발표한 Chain-of-Thought Reasoning without Prompting을 코드로 구현한 레포입니다.☆66Updated 8 months ago
- ☆31Updated 6 months ago
- KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models☆25Updated 10 months ago
- 자체 구축한 한국어 평가 데이터셋을 이용한 한국어 모델 평가☆31Updated last year
- LLM 모델의 외국어 토큰 생성을 막는 코드 구현☆74Updated 3 months ago
- OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca☆19Updated last year
- Efficient fine-tuning for ko-llm models☆182Updated last year
- Build complex LLM Applications with Python Dictionary☆40Updated 8 months ago
- evolve llm training instruction, from english instruction to any language.☆118Updated last year
- An extended project of the LLM Compiler paper, focusing on developing LLM-based Autonomous Agents.☆24Updated 8 months ago
- hwpxlib 패키지 python에서 쉽게 사용 할수 있게 만든 github repo 입니다.☆34Updated 2 months ago
- 한국어 벤치마크 평가 코드 통합본(?)☆17Updated 7 months ago
- ☆70Updated last week
- Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)☆47Updated last year
- Reward Model을 이용하여 언어모델의 답변을 평가하기☆29Updated last year
- ☆94Updated 6 months ago
- The most modern LLM evaluation toolkit☆60Updated this week