dnotitia / smoothie-qwenLinks
A lightweight adjustment tool for smoothing token probabilities in the Qwen models to encourage balanced multilingual generation.
☆78Updated 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.☆62Updated last year
- ☆20Updated last year
- Official repository for EXAONE 3.5 built by LG AI Research☆200Updated 7 months ago
- ☆12Updated last year
- BERT score for text generation☆12Updated 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…☆112Updated last month
- ☆62Updated 2 weeks ago
- [ACL 2025] DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues☆21Updated 3 weeks ago
- Ko-Arena-Hard-Auto: An automatic LLM benchmark for Korean☆23Updated 3 months ago
- Official repository for KoMT-Bench built by LG AI Research☆66Updated last year
- Make running benchmark simple yet maintainable, again. Now only supports Korean-based cross-encoder.☆20Updated last month
- The Universe of Evaluation. All about the evaluation for LLMs.☆226Updated last year
- LLM 모델의 외국어 토큰 생성을 막는 코드 구현☆77Updated 3 weeks ago
- Efficient fine-tuning for ko-llm models☆182Updated last year
- 구글에서 발표한 Chain-of-Thought Reasoning without Prompting을 코드로 구현한 레포입니다.☆66Updated 10 months ago
- KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models☆25Updated 11 months ago
- 자체 구축한 한국어 평가 데이터셋을 이용한 한국어 모델 평가☆31Updated last year
- Newsletter bot for 🤗 Daily Papers☆126Updated last week
- ☆11Updated 7 months ago
- Sakura-SOLAR-DPO: Merge, SFT, and DPO☆116Updated last year
- An extended project of the LLM Compiler paper, focusing on developing LLM-based Autonomous Agents.☆25Updated 9 months ago
- The most modern LLM evaluation toolkit☆67Updated last week
- evolve llm training instruction, from english instruction to any language.☆118Updated last year
- Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)☆48Updated last year
- ☆68Updated last year
- Official repository for EXAONE Deep built by LG AI Research☆401Updated 2 months ago
- Evaluate gpt-4o on CLIcK (Korean NLP Dataset)☆20Updated last year
- OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca☆19Updated last year
- AutoRAG example about benchmarking Korean embeddings.☆38Updated 10 months ago
- ☆101Updated last week