2 6 50

Sunil Kumar Yadav

sukuya

sukuya

AI & ML interests

Machine Translation, Large Language Models

Recent Activity

updated a dataset 12 days ago

Rakuten/JGLUE

liked a model 14 days ago

meituan/DeepSeek-R1-Channel-INT8

liked a model 21 days ago

facebook/KernelLLM

View all activity

Organizations

sukuya's activity

updated a dataset 12 days ago

Rakuten/JGLUE

Updated 12 days ago • 272 • 3

liked a model 14 days ago

meituan/DeepSeek-R1-Channel-INT8

Text Generation • Updated Feb 27 • 7.29k • 28

liked a model 21 days ago

facebook/KernelLLM

Text Generation • Updated 18 days ago • 13.3k • 153

liked 2 models about 2 months ago

sand-ai/MAGI-1

Image-to-Video • Updated 11 days ago • 580

nari-labs/Dia-1.6B

Text-to-Speech • Updated 13 days ago • 185k • • 2.53k

liked a Space about 2 months ago

8.02k

DeepSite

🐳

Generate any application with DeepSeek

liked a dataset about 2 months ago

zwhe99/DeepMath-103K

Viewer • Updated 16 days ago • 103k • 7.04k • 196

reacted to jasoncorkill's post with 👀 3 months ago

Post

3823

At Rapidata, we compared DeepL with LLMs like DeepSeek-R1, Llama, and Mixtral for translation quality using feedback from over 51,000 native speakers. Despite the costs, the performance makes it a valuable investment, especially in critical applications where translation quality is paramount. Now we can say that Europe is more than imposing regulations.

Our dataset, based on these comparisons, is now available on Hugging Face. This might be useful for anyone working on AI translation or language model evaluation.

Rapidata/Translation-deepseek-llama-mixtral-v-deepl