🌸🌸राधा साध्यम साधनं यस्य राधा, मंत्रो राधा मन्त्र दात्री च राधा। सर्वं राधा जीवनम् यस्य राधा, राधा राधा वाचि किम तस्य शेषम।।🌸🌸🎉🎉
आप सभी को हमारी प्यारी किशोरी जू के प्राकट्योत्सव की #विश्व_शांति_सेवा_समिति_प्रयागराज की ओर से हार्दिक शुभकामनाएं।।
#radharadha#radhaashtami
Today we introduce Sarvam-M, a 24B open-weights hybrid model built on top of Mistral Small.
Sarvam-M achieves a new benchmark across a range of Indian languages, math, and programming tasks, for a model of its size.
Here is a detailed technical blog on how we customize fine-tuning and reinforcement learning recipes, and optimize deployment - https://t.co/HfxIlGjSGt
Sarvam-M is built for versatility and designed to support a wide range of applications, including conversational agents, translation, educational tools, and so much more.
You can now try Sarvam-M on the Sarvam API - https://t.co/MGDxscK4Ws
This is the first in a series of contributions as we help build out the Sovereign AI Ecosystem in India.
Stay tuned for more updates in the coming weeks.
How to Teach LLMs to Follow Instructions
I just shared a new tutorial video as part of the Build a Large Language Model From Scratch series!
In this one, we take a pre-trained decoder-only model and turn it into a small personal assistant that can handle free-form instruction-following tasks like answering questions, rewriting text, or generating short responses.
From my experience working with teams building LLM applications, I’ve noticed that many people still think instruction fine-tuning is complicated. But as you’ll see, we reuse the same loss function (and even the same training loop) as during pre-training. The only real difference? How we format the data.
In this video, I walk through:
1. What instruction fine-tuning actually is
2. How to format data into prompt/response pairs using common templates
3. A lightweight dataset to demonstrate the process
4. Practical tips like dynamic padding, loss masking, and clean end-of-text handling
The model we train here is not a ChatGPT competitor, but it is small and fast, which is ideal for educational use, and great way to understand the principles behind instruction-following LLMs.
The full walkthrough is available here: https://t.co/Lk0gQcVhGQ