Rajendra Chola
Well-known member
- Messages
- 309
- Reactions
- Nation of residence
-
- Nation of origin
-
Indian AI lab Sarvam on Tuesday unveiled a new generation of large language models, as it bets that smaller, efficient open source AI models will be able to grab some market share away from more expensive systems offered by its much larger U.S. and Chinese rivals.
The launch, announced at the India AI Impact Summit in New Delhi, aligns with New Delhi’s push to reduce reliance on foreign AI platforms and tailor models to local languages and use cases.
Sarvam said the new lineup includes 30-billion- and 105-billion-parameter models; a text-to-speech model; a speech-to-text model; and a vision model to parse documents. These mark a sharp upgrade from the company’s 2-billion-parameter Sarvam 1 model that it released in October 2024.
The 30-billion- and 105-billion-parameter models use a mixture-of-experts architecture, which activates only a fraction of their total parameters at a time, significantly reducing computing costs, Sarvam said. The 30B model supports a 32,000-token context window aimed at real-time conversational use, while the larger model offers a 128,000-token window for more complex, multi-step reasoning tasks.
SARVAM’S 30B MODEL IS PLACED AGAINST GOOGLE’S GEMMA 27B AND OPENAI’S GPT-OSS-20B, AMONG OTHER MODELS.IMAGE CREDITS:SARVAM
Sarvam said the new AI models were trained from scratch rather than fine-tuned on existing open source systems. The 30B model was pre-trained on about 16 trillion tokens of text, while the 105B model was trained on trillions of tokens spanning multiple Indian languages, it said.
The models are designed to support real-time applications, the startup said, including voice-based assistants and chat systems in Indian languages.
SARVAM’S 105B IS TOUTED TO COMPETE AGAINST OPENAI’S GPT-OSS-120B AND ALIBABA’S QWEN-3-NEXT-80B.IMAGE CREDITS:SARVAM
The startup said the models were trained using computing resources provided under India’s government-backed IndiaAI Mission, with infrastructure support from data center operator Yotta and technical support from Nvidia.
techcrunch.com
The launch, announced at the India AI Impact Summit in New Delhi, aligns with New Delhi’s push to reduce reliance on foreign AI platforms and tailor models to local languages and use cases.
Sarvam said the new lineup includes 30-billion- and 105-billion-parameter models; a text-to-speech model; a speech-to-text model; and a vision model to parse documents. These mark a sharp upgrade from the company’s 2-billion-parameter Sarvam 1 model that it released in October 2024.
The 30-billion- and 105-billion-parameter models use a mixture-of-experts architecture, which activates only a fraction of their total parameters at a time, significantly reducing computing costs, Sarvam said. The 30B model supports a 32,000-token context window aimed at real-time conversational use, while the larger model offers a 128,000-token window for more complex, multi-step reasoning tasks.
Sarvam said the new AI models were trained from scratch rather than fine-tuned on existing open source systems. The 30B model was pre-trained on about 16 trillion tokens of text, while the 105B model was trained on trillions of tokens spanning multiple Indian languages, it said.
The models are designed to support real-time applications, the startup said, including voice-based assistants and chat systems in Indian languages.
The startup said the models were trained using computing resources provided under India’s government-backed IndiaAI Mission, with infrastructure support from data center operator Yotta and technical support from Nvidia.
Indian AI lab Sarvam's new models are a major bet on the viability of open source AI | TechCrunch
The new lineup includes 30-billion- and 105-billion-parameter models; a text-to-speech model; a speech-to-text model; and a vision model to parse documents.
techcrunch.com
