Built on Llama‑3.1, the open‑weight model targets India’s 60‑crore Hindi speakers with a Hindi‑centric tokenizer and training ...

Were you aware that more than 425 million people speak Hindi as their first language, and about 120 million use it as a ...

Senior Congress leader P Chidambaram slammed the Union government "increasing practice" of using Hindi words, written in ...

Congress leader P. Chidambaram criticised the government’s practice of using Hindi words in the titles of Bills, calling it ...

Successive governments have reiterated the promise that English will remain an Associate Official Language. I fear that ...

P Chidambaram said the non-Hindi speaking people cannot identify the titles of Bill/Act that are Hindi words written in English letters.

Built upon Llama-3.1 70B, NANDA 87B has been trained on a curated Hindi-English dataset with over 65 billion Hindi tokens. A custom Hindi-centric tokenizer boosts efficiency, reducing both training ...

Developed by MBZUAI in collaboration with Inception and Cerebras, the 87-billion-parameter model brings new scale and fluency ...

Chhattisgarh's initiative to offer MBBS education in Hindi medium faces setbacks as no students enrolled for 202526, citing ...

The government has proposed a new legislation titled Viksit Bharat – Guarantee for Rozgar and Ajeevika Mission (Gramin) Bill, 2025.

The All India OBC Students Association on Wednesday urged the Centre to conduct CUET-PG in all Scheduled Languages, instead of limiting it to English and Hindi.

Abu Dhabi-based AI group G42 on Tuesday announced the release of NANDA 87B, an open-source Hindi-English large language model with 87 billion parameters, an upgrade to its earlier NANDA model.