227 23 43

Longxu Dou PRO

dreamerdeo

https://longxudou.github.io/

AI & ML interests

Natural Language Processing

Recent Activity

reacted to their post with ➕ 4 days ago

🚀 Excited to share our technical report on the Southeast Asian multilingual model Sailor2 and its latest updates! Our 49-page report details Sailor2's development journey, including multilingual data cleaning, small model data mixture simulations, multi-stage continual pre-training, multi-stage post-training, and multi-cultural multi-lingual evaluations. Sailor2 aims to streamline the multilingual model pre-training process efficiently for the community. 🧭 We highlight Sailor2's impressive performance in low-resource language translation scenarios and its cultural understanding advantages in Southeast Asia, promoting practical applications for regional languages. Model updates include: 💡 More precise outputs: Reduced redundancy in model outputs through refined post-training data and optimization techniques. 🌈 Handling longer texts: Expanded to handle up to 128K context length in Southeast Asian languages through long-text training. ⚡️ Faster inference: Achieved 2.5x faster inference speed with speculative decoding. 🌪️ More model sizes: Introduced new sizes of 3B and 14B through model pruning. 🌟 All models are Apache-licensed for commercial use; development tools (code, resources) are open-source. 📚 Technical report: https://huggingface.co/papers/2502.12982 🤖️ Models: https://huggingface.co/collections/sail/sailor2-language-models-674d7c9e6b4dbbd9a869906b 💬 Demo: https://huggingface.co/spaces/sail/Sailor2-20B-Chat 📣 Sailor2 community: https://huggingface.co/sailor2

updated a Space 4 days ago

sailor2/README

new activity 4 days ago

sail/Sailor2-8B-Chat:Fix formatting

View all activity

Organizations

dreamerdeo's activity

liked a model 5 days ago

sail/Sailor2-20B-Chat

Text Generation • Updated 4 days ago • 401 • 4

liked a dataset about 1 month ago

opencsg/chinese-fineweb-edu

Viewer • Updated Jan 20 • 84.6M • 31.3k • 89

liked 6 models 3 months ago

liked a Space 3 months ago

README

💻

liked 2 datasets 3 months ago

VTSNLP/vietnamese_curated_dataset

Viewer • Updated Nov 24, 2024 • 12.2M • 493 • 50

sailor2/Vietnamese_RAG

Viewer • Updated Jul 16, 2024 • 8.41k • 308 • 7

liked a model 3 months ago

liuhaotian/llava-v1.6-34b

Image-Text-to-Text • Updated May 9, 2024 • 14.1k • 347

liked a dataset 3 months ago

neulab/MultiUI

Viewer • Updated Nov 22, 2024 • 7.29M • 2.47k • 41

liked a dataset 4 months ago

C4AI-Community/multilingual-reward-bench

Viewer • Updated Nov 4, 2024 • 66.8k • 1.54k • 26

liked a dataset 7 months ago

m-a-p/neo_sft_phase2

Viewer • Updated Jun 12, 2024 • 109k • 82 • 52

liked a dataset 8 months ago

nvidia/HelpSteer

Viewer • Updated Dec 18, 2024 • 37.1k • 1.93k • 233

liked a Space 9 months ago

LLM Leaderboard for SEA

🥇

Browse leaderboard of language models

liked a dataset 9 months ago

TIGER-Lab/MMLU-Pro

Viewer • Updated Nov 27, 2024 • 12.1k • 41k • 322

liked 2 models 9 months ago

sail/Sailor-14B-Chat-gguf

Updated Dec 21, 2024 • 227 • 5

sail/Sailor-14B-Chat

Text Generation • Updated Dec 21, 2024 • 60 • 11