lucky verma

ML Engineer. Building production agentic AI for defense supply chain. LangGraph, DSPy, knowledge graphs.

[lucky verma @luckieverma]

Code/artifacts: https://t.co/W2497OpUjG

[lucky verma @luckieverma]

arXiv preprint:
When does removing LayerNorm help?

Main finding: DyT is not uniformly helpful; it behaves like a regime-dependent implicit regularizer.

Paper: https://t.co/bRz1CYmX3c

[comma @comma_ai]

New rack up!

Sell comma 3X to buy GPUs to train better models to sell more comma 3X to buy more GPU to sell more comma 3X

[lucky verma @luckieverma]

Pacman dominance ＼⍩⃝／: Fun to play around with KGs built with LMs

[lucky verma @luckieverma]

terminal is good

[lucky verma @luckieverma]

@thisistheray @METAPCs Maryland!

[AK @_akhaliq]

KAN

Kolmogorov-Arnold Networks

Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have fixed activation functions on nodes ("neurons"),

[WIZZ🥷 ( beware scammers ) @CryptoWizardd]

Anyone else needs this ?

[lucky verma @luckieverma]

@ChaniNattan Why do you need sikh hashtag at that time? Do you want to dig up old feuds?

[lucky verma @luckieverma]

@AGONbyAOC GPU

[lucky verma @luckieverma]

@BhaktSanatani_ @historyinmemes How much do they pay?

[Elon Musk @elonmusk]

Fixed it

[elvis @omarsar0]

Knowledge Fusion of LLMs

Is it possible to merge existing models into a more potent model?

We have already seen a few ways that show the potential to effectively do this using approaches like weight merging and ensembling of models.

This work proposes FuseLLM with the core idea of externalizing knowledge from multiple LLMs and transferring their capabilities to a target LLM.

It leverages the generative distributions of source LLMs to externalize both their collective knowledge and individual strengths and transfer them to the target LLM through continual training.

To put it simply, the idea is to benefit from the strengths of all the LLMs and combine them into one integrated model.

Finds that the FuseLLM can improve the performance of the target model across a range of capabilities such as reasoning, common sense, and code generation.

By the way, you can also perform the fusion among fine-tuned LLMs that specialize in specific tasks.

This continues to be an interesting research area so hoping to document more on any new ideas and findings I come across.

[lucky verma @luckieverma]

@WallStreetSilv Taxation

[lucky verma @luckieverma]

@zerochills Headshot!

[lucky verma @luckieverma]

I found a #cloud #torrent that's awesome ;) @seedrcoil it's free just give it a try! https://t.co/59QZA2YFv7

[lucky verma @luckieverma]

@X0GALE @AGONbyAOC Nice refresh rate ?

[lucky verma @luckieverma]

@AGONbyAOC 144hz

[lucky verma @luckieverma]

Github's new feature
#Github #Skyline @github

https://t.co/DbhzEcOv00

[lucky verma @luckieverma]

@aryan_eth 👋

Interviewed and got screwed. #DSAisImportant