Saquib Khan

My take is that the training process performs a kind of negative sampling to filter out samples that have low information, hence improving training efficiency.

4

3 Comments

Interesting to read actual evidence of what one could expect as an inevitability of scale!

21

3 Comments

The liger-kernel blog post is finally live 🎉 The project has gained massive attention and is being widely used since it's release. The blog post gives a nice overview of the motivation and design that went into building these kernels. For all the nitty-gritty details, checkout our technical report: https://lnkd.in/gEGwDNjP

9

📢 Starting a thread on Fine-tuning Large Language Models (LLMs) 📢 1/n ● Large Language Models (LLMs) have revolutionised computational systems' ability to understand and generate human language. Building upon traditional language models, LLMs address limitations in handling rare words, overfitting, and capturing intricate linguistic patterns. ● Fine-tuning is a crucial process that adapts pre-trained LLMs to specific tasks or domains. This involves further training the model on a smaller, targeted dataset, refining its pre-existing knowledge and enhancing performance on specific tasks with reduced data and computational requirements. ● The fine-tuning process typically involves a seven-stage pipeline: dataset preparation, model initialisation, training environment setup, fine-tuning, evaluation and validation, deployment, and monitoring and maintenance. Each stage is essential for tailoring the LLM to meet specific requirements and ensuring optimal performance. ● There are different types of fine-tuning: unsupervised fine-tuning, supervised fine-tuning (SFT), and instruction fine-tuning via prompt engineering. The choice of method depends on the availability of labeled data and the specific task requirements. ● Parameter-Efficient Fine-Tuning (PEFT) techniques have emerged to address the computational challenges associated with fine-tuning large models. PEFT methods, such as LoRA, QLoRA, and adapters, allow for efficient fine-tuning with fewer parameters, reducing computational costs and mitigating overfitting. ● Evaluation and validation are critical for assessing the performance of fine-tuned LLMs. Metrics such as cross-entropy, perplexity, and accuracy are used to measure the model's ability to generalize and perform the target task effectively. ● Deployment of fine-tuned LLMs involves making them operational and accessible for specific applications. This includes setting up the necessary infrastructure, developing APIs, and optimizing model performance for inference. ● Monitoring and maintenance are essential to ensure the ongoing performance and reliability of deployed models. Continuous monitoring of metrics, retraining on updated data, and addressing potential biases or security vulnerabilities are crucial for maintaining model effectiveness and ethical considerations. ● Various platforms and frameworks facilitate LLM fine-tuning, such as Hugging Face, OpenAI, Google, and NVIDIA. These platforms provide tools for data preparation, model selection, hyperparameter tuning, and deployment, streamlining the fine-tuning process. ● Fine-tuning LLMs raises ethical considerations regarding bias, fairness, accountability, and transparency. Addressing these concerns is vital for responsible AI development, ensuring that models are deployed ethically and their outputs are trustworthy. Stay tuned for upcoming posts 📬 where I go through these in detail 📤 .

7

Do LLMs have any immediate applications in the field of Robotics? The above question was loosely based on a query asked by a startup founder in an event, based on my colleague’s work on a recent LLMs integration. (Siddharth) Come to think of it, robotics about 10 years ago wouldn’t have been able to accommodate such computational expenses. Imagine running a LLM model on a Raspberry Pi zero and not expecting it to blow up! :) While implementing a LLMs could be a fun side project, what question warrants a deeper insight would be whether it is of absolute necessity? With Nvidia doubling down on the highly powerful Jetson devices, and Blackwell chips, the hardware is expansive and available, but it still begs to ask the same question again and again - is it necessary? Like every other industrial trend, once must deeply analyse where a novel idea would fit in, and calculate against its effort and yield. Let’s explore a few options wherein it could be absolute importance to use LLMs in context of Robotics: 1. Support agents - Social robotics has a huge potential of closing down on the weary technical support based on an exhaustive list of solved and interpreted problems. Distilling technical documents and datasheets into a message parsing model is an important win to do effective knowledge transfer. 2. Assistive bots - In the field of soft robotics and prosthetic arms/exoskeleton, a voice controlled NLP agent would be great help in helping administer orchestrated actions for differently abled individuals who have clear motive/task list. 3. Surveillance/Monitoring bots - Given the nature of preordained message intents, it is a perfect candidate for having a lightweight message-action model for surveying specific sites. Looking at the magnanimity of the manufacturing plants, this would be a great boom. 4. Surgical bots - Expert assisted robotic surgeries are a natural extension for aligning non-conventional anomalies that are very unique to the nature of the surgery. Since precision and targeted algorithms are of utmost importance, one cannot make actions based on learning based approaches effectively from general archetypes. Are there more applications that cross your mind marrying LLMs and Robotics?

38

6 Comments

You don’t normally see LLM researchers and engineers talking about their day-to-day work. Big shoutout to this YouTube video from the Anthropic LLM Interpretability team, the team behind the Golden Gate Claude. It’s amazing to see that most of the team members have worked for the team for only one year, and yet they have made such a big breakthrough in interpretability research. Another thing I want to highlight is the unique challenges facing the team and how they approach these challenges, that is, through fast trial-and-error iterations and constant evaluation of what may work and what to prioritize next. #artificialintelligence #machinelearning #deeplearning https://lnkd.in/eUaPAYch

98

1 Comment

🔍 Exploring Sparse Distributed Memory (SDM) I'm excited to share my latest blog post on Sparse Distributed Memory (SDM), an innovative model inspired by human memory! 🚀 In this detailed walkthrough, I break down the SDM script I made, providing rich mathematical and scientific insights to help you understand and implement this robust and scalable memory storage and retrieval system. If you're curious about how SDM can serve as a fascinating alternative to traditional neural networks, enhancing your machine learning projects, check out the full article here. #MachineLearning #ArtificialIntelligence #SparseDistributedMemory #SDM #DataScience #NeuralNetworks #MemoryModels #TechInnovation #Coding #AIResearch

4

While Gen AI engineers in India are rightly concerned about #hallucination in LLMs, yet most would rarely appreciate that genius folks in our own country evolved extraordinary measures to arrest hallucination thousands of years ago, which included sophisticated #guardrails which were to be 'assimilated' in the brain itself, impacting the way it perceived reality and 'generated' content (Isn't the brain one of the most hallucinating natural 'LLMs' after all ?). This was not just to ensure that facts were rendered correctly. The attempt was to prevent disasters of another kind and of a much more serious nature. After all, language in India was considered an important vehicle for connecting to the divine, and not merely for communicating with one another. And we often fail to realize this #opensource framework, so to say, was built upon by different intellectuals in different parts of the country, and India ended up having several wonderful languages in different regions, languages which look different, but have a lot in common. Did you not realize that no matter where in India we are from, names of most of us can be traced to this one language? https://lnkd.in/g4Njx4mG #llms #nlp #generativeai

16

3 Comments

🎯 How teams are cutting Machine Learning Engineer hiring time from 90+ days to 28 days: 1. Role-specific technical assessments that mirror real projects • Real-world problem-solving instead of whiteboard exercises • Actual code reviews from your codebase • System design challenges based on your architecture • Practical ML model optimization tasks 2. Direct access to tech leads in first interview • No HR screening delays • Technical discussion from day one • Immediate architecture alignment • Quick technical fit assessment 3. 48-hour feedback commitment from all parties • Same-day interview feedback • Next-steps within 24 hours • Offer decisions in 48 hours • Clear communication timeline 4. Streamlined technical evaluation process • One comprehensive technical round • Parallel evaluations when possible • Combined culture/technical assessments • Quick technical team consensus Teams implementing even one of these cut hiring time by 40%. "Especially effective for fast-growing startups and scale-ups" #TechHiring #MLEngineering #TechRecruitment

3

Deep Dive into Large Language Model (LLM) Agents UC Berkeley’s Fall 2024 course on LLM Agents provided an exceptional exploration of how these technologies are shaping the future of AI. Here's a glimpse into the key topics covered by industry-leading speakers: LLM Reasoning: Denny Zhou (Google DeepMind) explained the capabilities and limitations of LLMs in logical reasoning. Agentic AI Frameworks: Chi Wang (AutoGen-AI) and Jerry Liu (LlamaIndex) discussed tools and strategies for designing intelligent agents. Multi-Agent Collaboration: Shunyu Yao (OpenAI) explored how agents can interact effectively. Enterprise Trends: Burak Gokturk (Google) highlighted generative AI applications in business. Neural and Symbolic Decision Making: Yuandong Tian (Meta AI) proposed frameworks for integrating neural and symbolic reasoning. Robotics and Generalist Agents: Jim Fan (NVIDIA) introduced the vision for robotics powered by LLM agents. Ethics and Safety: Dawn Song (UC Berkeley) shared approaches to building trustworthy and responsible AI systems. This course bridged theory and real-world applications, covering industries such as robotics, web automation, and scientific discovery, with hands-on labs to empower learners. LLM Agents are unlocking new frontiers in AI—from enabling multi-agent collaboration to addressing real-world challenges in enterprise and beyond. Exploring their capabilities is essential for shaping the next wave of innovation. https://lnkd.in/ezPGZs8C #LLMAgents #ArtificialIntelligence #MultiAgentSystems #AI #Automation

37

recently been tinkering with running hand rolled neural nets on FPGAs for audio generation. ( it's crazy being able to run inference almost 200,000 inferences / second e.g. https://lnkd.in/gqepf6Cy ) stumbled today onto a cool idea called LUTnet ( https://lnkd.in/gi9GiH2Y ) where binary neural nets can be expressed as 2-LUTs ( generalisable to N-LUTs ). what a great idea! has anyone worked with these kinds of architectures? am particularly interested in how i can use the same ideas with my power-of-two quantisation networks (where "multiplies" are just left/right shifts )

26

The paper reveals "the Transformer’s limitation in learning only the observed reachability matrix, without deducing the complete reachability matrix," which supports the claim that LLMs are all about (approximate) retrieval. Link to the paper: https://lnkd.in/eGZN6Wrd #artificialintelligence #machinelearning #deeplearning

21

5 Comments

Sharing my thoughts on How Waymo (formerly known as the Google Self-Driving Car Project) is Pioneering Autonomous Driving with AI. Waymo has become a trailblazer in self-driving technology, and at the core of it all is AI. Leveraging advanced machine learning and deep neural networks, Waymo’s AI-powered system continuously improves through real-world data, making autonomous vehicles smarter, safer, and more reliable. Perception: AI allows Waymo’s cars to "see" and understand their surroundings by processing data from sensors like cameras, LIDAR, and radar. This helps detect pedestrians, other vehicles, and objects in real time. Prediction: The AI system predicts the behavior of everyone around the vehicle—whether it’s cars changing lanes or pedestrians crossing the street—ensuring smooth and safe driving decisions. Planning & Control: AI makes split-second decisions about accelerating, braking, and steering based on the analysis of complex traffic patterns, enabling Waymo vehicles to safely navigate roads. With millions of autonomous miles driven, Waymo’s AI is constantly learning and improving, helping create the future of safer and smarter transportation. The road ahead is AI-driven! www.rxsmeta.com #AI #AutonomousVehicles #Waymo #SelfDrivingCars #MachineLearning #SmartMobility #TransportationTech #FutureOfTransport #AIinAction #Innovation

2

Fine Tuning LLMs: 6/n Stage 2: Initializing LLMs ● This post outlines the steps involved and highlights the tools, libraries, and potential challenges associated with this crucial stage ● The first step is to establish the necessary environment. This includes setting up the computing environment and installing any required dependencies. Then, import the libraries needed for working with LLMs, which often include specialized tools for handling large datasets and complex model architectures. ● Next, select a pre-trained LLM from a repository, taking into account the specific requirements of the task. This choice is critical, as the pre-trained model's capabilities should align with the intended application. Download the selected model from a repository like Hugging Face's Model Hub. ● Once downloaded, load the model into memory, which initializes its weights and prepares it for either inference (using the model for predictions) or further fine-tuning (adapting the model to a specific task). ● Python offers a variety of tools and libraries for initializing LLMs, providing access to both open-source and proprietary models. Hugging Face's Transformers library is a popular choice, offering a broad selection of pre-trained LLMs, including models like Phi-3 mini and Llama-3 70B. ● The Transformers library supports several features, such as loading fine-tuned models, working with 4-bit quantized models for efficiency, and a "pipeline" function that simplifies the application of pre-trained models to various tasks. Other commonly used libraries for LLM initialization include TensorFlow, PyTorch, and FastAI. ● Model initialization, however, is not without its challenges. Developers must carefully consider several factors to ensure the model's effectiveness and responsible deployment. One primary concern is aligning the capabilities of the pre-trained model with the specific tasks it will perform. ● Another challenge is understanding the chosen model's architecture and ensuring its compatibility with the available hardware and software resources. Deploying large, complex models on systems with limited resources can pose significant difficulties. ● Additional challenges include addressing data privacy concerns, managing the costs associated with training and deploying LLMs, ensuring ongoing maintenance and updates, handling the large size of these models, effectively utilizing quantization techniques, and being aware of potential biases present in the training data. ● Careful consideration of these challenges during the model initialization stage is essential for successfully deploying and utilizing LLMs for various applications. Addressing these challenges upfront helps mitigate risks and ensures the model's effectiveness, reliability, and responsible application.

2

Controversial take 🚀 Large Language Models (LLMs) are akin to monoliths similar to OS packaging in early days where core OS and applications were all bundled together. A lot of such application packages were never used. Just like unused OS applications and packages, a lot of knowledge in todays model may not be useful for many specialized use-cases particularly in B2B, which is also evident in need for fine-tuning or ICL. In the applications world, as containerization took center stage, it became flexible to add or remove packages needed for a system. Docker emerged as the go-to for this purpose, allowing engineers to build enterprise systems by excluding unnecessary packages besides using a relevant starting point, further adding their own packages. For example, users can begin with a base OS container and customize it by adding or removing packages. Over the last year, with LoRA Adapters(and similar variants) have been goto methods for bringing in your knowledge bits to create customized models. Other techniques such as modelmerge help merge multiple models into a single one. These are interesting directionally, however it needs to become even simpler similar to layers in containers, where knowledge bits can be added/excluded seemlessly. Looking ahead, the future of LLM seems like would mirror containers. Starting with a pre-trained base model tailored to your use-case, you can then add layers your knowledge bits on top. "Language Model as a container" offers the simplicity of packaging your custom knowledge bits. #LLM #huggingface #SLM

16

6 Comments

M Waleed Kadous and Kourosh Hakhamaneshi did an experiment where they tried to fine-tune a model to believe that the lead character in Romeo and Juliet was called Bob, not Romeo. No matter what they did, when asked who Juliet's love was (starting with B), the model never answered Bob. Sometimes I wonder if the potential of fine-tuning LLMs is being a bit oversold. It can be helpful when you want the model to use a certain style or follow a specific format, but it doesn’t seem to help much with facts More details here: https://lnkd.in/g6p2eU-n

8

Responsible engineers should avoid copying code directly from online sources, including LLMs or platforms like Stack Overflow, without fully reviewing, understanding, and adapting it for safe integration into their codebase. Thoughtful assessment is essential to ensure code behaves as expected and meets project requirements. That said, I believe LLMs can be a fantastic resource to accelerate learning and deepen understanding across a range of topics—as long as they’re used with careful consideration. #LLM #engineering #ChatGPT

10

1 Comment

Excited to dive deeper into LangChain! Just explored key concepts like LLM chains, memory, loaders, retrievers, and splitters. Building more robust and context-aware applications with LLMs is now within reach. #LangChain #LLMs #AI #MachineLearning

4