Exploring LLMs | Data scientist with a curious engineering mind
Bengaluru, India
Joined April 2013
- Tweets122
- Following698
- Followers129
- Likes129
Pinned Tweet
My recent blog with @hasgeek - “Decoding Llama3” is out.
It’s a deep dive into the Llama3 model code released in April this year. This is a fun blog with a code-first approach.
hasgeek.com/simrathanspal/th…

simrat hanspal retweeted
1. Diffusion Language Models
Language models do not always have to generate text one token at a time. Diffusion language models start with a masked sentence, predict many words in parallel, and refine them over multiple rounds. Models like LLaDA and Mercury are exploring a new path for text generation.
courses.vizuara.ai
🫣 Softmax is unstable with very large and very small numbers.
🤓 Here is a simple illustration of how (x-max) makes softmax stable for use.
What does it mean to have dropout in Attention computation?
Dropouts are used to prevent overfitting.
In case of attention, we drop some attention scores, which means that if the model learnt to attend to some token, it now has to focus on other related tokens.
#LLM #Attention
The tokeniser lies about how many tokens it holds ;)
What the tokeniser returns is the size of the base vocabulary that it learnt during training. Everything after that are special tokens.
Special tokens are like metadata and help structure context.
Trivial but worth a reminder use np.matmul for dot product instead of np. dot.
np. dot is meant to be a flexible function that will adjust according to the input shape, instead of raising an error.
Example np. dot(np.array([[1, 2], [3, 4]]), 10)
Budding entrepreneur 🥹
I purchased more than I planned.
And also assisting madame in coordinating logistics and order shipping the day after #fifthel
@jackerhack @_waabi_saabi_
Looking forward to it.
Tech x society enthusiasts, show up for The Fifth Elephant Annual Conference on 13th July!
I'll be hosting the session on Deploying AI in Key Sectors: Robust Risk Mitigation Strategies with @jnkhyati, @bargava, @simsimsandy & @fooobar
@fifthel @hasgeek @anthillin @zainabbawa
simrat hanspal retweeted
First, @simsimsandy walked us through GPU architecture, optimizations, CUDA, and the challenges of running large ML models on GPUs, with a special look at the attention mechanism, KV-Cache optimizations, and PagedAttention!
Thank you for the shoutout @TheOtherRaghav. It was a lovely event. xitter.cf/theotherraghav/status/…
If you are into GenAI, @hasgeek is organizing a call today to build a community on #ResponsibleAI. Join for cross-learning.
🔗 Meeting Link: Register here to confirm your participation - lnkd.in/gFSt8bYc
🕰Time: 7 PM IST Friday, 28 June (tonight)
simrat hanspal retweeted
🚀Join us in Chennai next week for our hands-on workshop: "Building AI Agents with RAG and Functions" 🤖✨
Limited seats available, so hurry and secure your spot! 🏃♂️💨
🔗 Register now: lu.ma/6lrnyo1b
#AIWorkshop #ChennaiEvents #llm #genai
Thank you for the call out @zainabbawa :)
Best wishes to all the speakers at FifthEl 2024, looking forward to networking in person.
.@simsimsandy introduced Bhumika Makwana @GalaxEyeSpace who will speak about multimodal fusion as the new game changer.
Reach out to Simrat for review and feedback on #nlp work, and for simplifying complex AI concepts. 3/5
Really fun video on the basics - dot prd and inner prd.
Also, potentially a great resource on Quantum Mechanics #QuantumSense YT channel.
youtube.com/watch?v=3N2vN76E…
Inner product is an important concept for Rotary Positional Embedding, which is used by #LLM like #Llama3 (#Llama).
simrat hanspal retweeted
Surprised how Twitter Influencers have got more insider informations and conclusions than anyone else!
Also, because Apple uses OpenAI means it couldn't make it on its own 🤦🏽
Concise end-to-end #RAG tutorial by @jasonzhou1993
youtu.be/u5Vcrwpzoz8?si=kPwf…
This YouTube channel is a Gem with a lot of use case-based tutorials.
Check it out :)
#LLM #GenAI #AI
I discovered fairscale today, PyTorch extension by Meta that helps you with distributed model training. Looks like #Llama3 used it.
github.com/facebookresearch/…
I am definitely going to be reading more about it.
Please drop in your thoughts if you have used it or read something.
