Get the latest tech news

Sarvam 105B, the first competitive Indian open source LLM


We're releasing Sarvam 30B and Sarvam 105B as open-source models. Both are reasoning models trained from scratch on large-scale, high-quality datasets curated in-house across every stage of training: pre-training, supervised fine-tuning, and reinforcement learning.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of LLM

LLM

Photo of Indian

Indian

Photo of Sarvam 105B

Sarvam 105B

Related news:

News photo

LLMs work best when the user defines their acceptance criteria first

News photo

New KV cache compaction technique cuts LLM memory 50x without accuracy loss

News photo

Google PM open-sources Always On Memory Agent, ditching vector databases for LLM-driven persistent memory