Tensordroid
Tensordroid
  • Видео 195
  • Просмотров 82 335
Hands On LLM by Jay Alammar Book Review
👇🏻 Looking for some help and mentoring? 👇🏻
--------------
👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm
Book Link:
ShroffPublisher: www.shroffpublishers.com/books/9789355425522/?sef_rewrite=1
Amazon: amzn.in/d/b0V8E3V
My Links 🔗
👉🏻 Subscribe: youtube.com/@Tensordroid
👉🏻 Twitter: vishesh_t27
👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
Просмотров: 76

Видео

My Advice to Beginner Students to a become ML Engineer in 2025
Просмотров 58614 дней назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
Text Classification in 2025 !!
Просмотров 14621 день назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm Google Colab notebook: colab.research.google.com/drive/1EtkoVcxixnI1iQbFuNST6Y6AgQ7_f_mi?usp=sharing My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
The only resume you need for your next Machine Learning Interviews
Просмотров 9621 день назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm Overleaf Resume: www.overleaf.com/read/rpvqcxkcqbkf#e2a5cc My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
Machine Learning Jobs and Internships in India
Просмотров 19828 дней назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref... AI Startup Sheet Link: docs.google.com/spreadsheets/d/13x3SS5W_6HaALfGo_Gi5TYJcFJ5GMMnr2muzsMW5ATA/edit?usp=sharing My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
How to read Machine Learning Research papers
Просмотров 355Месяц назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm HuggingFace Papers: huggingface.co/papers The AI-Timeline: x.com/TheAITimeline Elvis: x.com/omarsar0 My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
But what is HTMLRAG ?
Просмотров 79Месяц назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm Paper Link: arxiv.org/abs/2411.02959 My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
A HitchHiker's Guide to Scaling Law Estimation
Просмотров 172 месяца назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm Research Paper: arxiv.org/abs/2410.11840 My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
Not all Attention is Needed in Transformers ?!
Просмотров 942 месяца назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm Paper Link: arxiv.org/abs/2406.15786 My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
Understanding Cross Entropy and Perplexity
Просмотров 762 месяца назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
But what is Differential Transformer ?
Просмотров 1382 месяца назад
Paper Link: arxiv.org/abs/2410.02703 My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
But what is selective Attention ?
Просмотров 442 месяца назад
Hey guys, sorry for the horizontal view, was trying something and realised it during final editing. Paper link: arxiv.org/abs/2410.02703 My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
Google presents Astute RAG !!
Просмотров 2032 месяца назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm Paper Link: arxiv.org/abs/2410.07176 My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
ColPali: Indexing Documents in RAG made easy using Vision Language Models !!
Просмотров 3883 месяца назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm Paper Link: arxiv.org/abs/2407.01449 Blog: huggingface.co/blog/manu/colpali My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordroid 👉🏻 Twitter: vishesh_t27 👉🏻 LinkedIn: www.linkedin.com/in/vishesh-tripathi/
Best Paper for Retrieval Augmented Generation Pain Points !!
Просмотров 1743 месяца назад
👇🏻 Looking for some help and mentoring? 👇🏻 👉🏻 Book a one-on-one call: unstop.com/mentor/vishesh?ref=kzVULcm Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely: arxiv.org/pdf/2409.14924 Searching for Best Practices in Retrieval-Augmented Generation: arxiv.org/pdf/2407.01219 My Links 🔗 👉🏻 Subscribe: youtube.com/@Tensordro...
But OpenAI o1 is here !!
Просмотров 2603 месяца назад
But OpenAI o1 is here !!
Smart India Hackathon Guide 2024
Просмотров 2464 месяца назад
Smart India Hackathon Guide 2024
But what is DeepSpeed ? DeepSpeed vs VLLM
Просмотров 2654 месяца назад
But what is DeepSpeed ? DeepSpeed vs VLLM
Preparing for Machine Learning Interviews in 2024
Просмотров 825 месяцев назад
Preparing for Machine Learning Interviews in 2024
But GPT-4o-mini is here !!
Просмотров 375 месяцев назад
But GPT-4o-mini is here !!
Weekly ML News Episode - 8
Просмотров 466 месяцев назад
Weekly ML News Episode - 8
Are Large Language Models really learning something or Not ?
Просмотров 666 месяцев назад
Are Large Language Models really learning something or Not ?
But Google's Gemma-2 is here !!
Просмотров 496 месяцев назад
But Google's Gemma-2 is here !!
Weekly ML News Episode -7
Просмотров 466 месяцев назад
Weekly ML News Episode -7
Table Extraction for RAG !!
Просмотров 9106 месяцев назад
Table Extraction for RAG !!
Training and adding new tokens in a Pre-trained Tokenizer !!
Просмотров 3496 месяцев назад
Training and adding new tokens in a Pre-trained Tokenizer !!
Weekly ML News Episode - 6
Просмотров 447 месяцев назад
Weekly ML News Episode - 6
But Mistral-AI's Codestral is here !!
Просмотров 657 месяцев назад
But Mistral-AI's Codestral is here !!
But Meta's Chameleon is here !!!
Просмотров 2247 месяцев назад
But Meta's Chameleon is here !!!
But what is Paged Attention !!
Просмотров 8807 месяцев назад
But what is Paged Attention !!

Комментарии

  • @adityadhukia9382
    @adityadhukia9382 4 дня назад

    Hi, I came across one more book named as "Build a Large Language Model ( From Scratch)" by - Author (Sebastian Raschka). Can you suggest which book should I read from these two books in order to get a deeper knowledge for the architecture of the LLM's and how fine-tuning is done.

  • @Motivationalvideousa
    @Motivationalvideousa 8 дней назад

    Hi there! I adore your videos, and I’m sure your audience wants more of them too. If time’s tight, I can help! I’m a pro at editing and designing thumbnails. You provide the videos and channel info, and I’ll handle the rest. Can we chat tomorrow?

    • @Tensordroid
      @Tensordroid 7 дней назад

      Heyy I am a bit busy in January, let's connect first week of February ? You can mail me "hi" in my mail Id: vishesht27@gmail.com

  • @siddharthmanumusic
    @siddharthmanumusic 15 дней назад

    Thanks for wrapping this up with formulas and diagrams within 15 minutes!

  • @debankumarsahu8603
    @debankumarsahu8603 18 дней назад

    Can't we just learn Deep Learning and basic mathematics if we going to choose NLP or ComputerVision instead of learning ML and Deep Learning both

    • @NavdeepVarshney-ep4ck
      @NavdeepVarshney-ep4ck 17 дней назад

      Mathematics is essential if you want to better learn mathematics, develop intuition, take small example illustration how the things are working. Then you will have a upper hand on it.

  • @Ranjith_Kumar.P
    @Ranjith_Kumar.P 19 дней назад

    bro , in my opinion , you should increase the screen recording resolution, because it is kind of blurred and not clearly visible...Or-else try uploading in higher quality..........ur content is good by the way 👍

    • @Tensordroid
      @Tensordroid 19 дней назад

      Sure dude Thanks for the suggestion, will work on this

  • @AnA-xx1vx
    @AnA-xx1vx 26 дней назад

    Use Mendeley I guess.

    • @Tensordroid
      @Tensordroid 25 дней назад

      I agree, but I’ve noticed that juniors/beginners finding difficult to use tools, they can usually start with basic methods and gradually upgrade.

  • @vikramjeetsingh4627
    @vikramjeetsingh4627 28 дней назад

    Knowledgeable ✨

  • @nandanisharma9300
    @nandanisharma9300 Месяц назад

    The Video is a great help can, kind request to how to choose the target_modules in LORA configuration

  • @NWS189
    @NWS189 2 месяца назад

    Thank you for this video

  • @advaychandratre2220
    @advaychandratre2220 2 месяца назад

    Hi, Great video, i am trying to build a model that will do OCR for driving license and rc book using PALI, how do you think i should approach this model

  • @PraffulPawar-c9t
    @PraffulPawar-c9t 2 месяца назад

    You are basically reading from the slides, it could have been much better if you could have refreshed/brushed upon the concept of paging and then explained how paged attention works

  • @siddharthmanumusic
    @siddharthmanumusic 2 месяца назад

    Straight to the point and insightful

  • @subhamlaha8232
    @subhamlaha8232 2 месяца назад

    please provide link for transformers video

  • @tomzhang9186
    @tomzhang9186 3 месяца назад

    where is paper published to?

  • @siddhantsingh8999
    @siddhantsingh8999 3 месяца назад

    This was informative 💯

  • @S.Ahmed730
    @S.Ahmed730 4 месяца назад

    great achievement thank you

  • @himanshuseditography8224
    @himanshuseditography8224 4 месяца назад

    Hey Bro Is there any Chance of increase in No. of Submission(Right Now It's only 2)

  • @pranilpatil4109
    @pranilpatil4109 4 месяца назад

    I did the same for 22 Indian languages. But when I searched a kannada language character in the tokens for a test purpose, it was not showing anything. Also, tokenizer separates punctuation as well. Your method of splitting is not optimal.

  • @veritaz753
    @veritaz753 4 месяца назад

    whats the minimum spec to run this??

  • @rbrowne4255
    @rbrowne4255 4 месяца назад

    thanks for the video, from an inferencing hardware point of view, it would be good to see basic results comparing performance on a Multi-GPU system with NVLINK and without, meaning the GPUs using the PCIe bus on the host system

  • @IlllIlllIlllIlll
    @IlllIlllIlllIlll 4 месяца назад

    Is kv cache in every LLM? How about the small models

  • @tharunbhaskar6795
    @tharunbhaskar6795 4 месяца назад

    Some quality content here. So the new tokens just get appended to the current tokenizer right?

  • @sajjadrahman256
    @sajjadrahman256 5 месяцев назад

    awesome presentation and make sense .❤

  • @priteshtadvi4946
    @priteshtadvi4946 5 месяцев назад

    Very well explained !!! Good work 👍 Keep it up 🤝

  • @SufiyanSiddique
    @SufiyanSiddique 5 месяцев назад

    from systemxpert???

  • @Keep_going_no_matter_what
    @Keep_going_no_matter_what 6 месяцев назад

    Can I learn java for ML ?

    • @Tensordroid
      @Tensordroid 6 месяцев назад

      Java is good for DSA, but for ML, you need to learn ML

  • @littleglitch5853
    @littleglitch5853 6 месяцев назад

    can you give the ppt is shown in the video please?

    • @Tensordroid
      @Tensordroid 4 месяца назад

      here you go: docs.google.com/presentation/d/1hfK_k0jotCNwZWMDuHsbeL3R4r5q7hCwQXsJWbE3o6k/edit?usp=sharing

  • @karthikb547
    @karthikb547 6 месяцев назад

    Thanks for sharing:)

  • @priteshtadvi4946
    @priteshtadvi4946 6 месяцев назад

    Very good research and well explained 🙌

    • @Tensordroid
      @Tensordroid 6 месяцев назад

      Thank you so much !!

  • @yatinshekhar787
    @yatinshekhar787 6 месяцев назад

    dsa in python or java. Coz I saw your leetcode and majority of the problems are solved using java

    • @Tensordroid
      @Tensordroid 6 месяцев назад

      it's a choice, I did in java, because DSA is always better in C++ or Java. but python also works, as I have shifted to work in python full time, I am going to do DSA in python only

  • @akarsh-tripathi
    @akarsh-tripathi 6 месяцев назад

    Nice one, Vishesh

  • @CantBeSubh
    @CantBeSubh 7 месяцев назад

    good shit bro

  • @CantBeSubh
    @CantBeSubh 7 месяцев назад

    thanks g, you the best.

  • @akarsh-tripathi
    @akarsh-tripathi 7 месяцев назад

    👏👏

  • @travellingbytes
    @travellingbytes 7 месяцев назад

    🎉

  • @rishabhkumar-h8q
    @rishabhkumar-h8q 7 месяцев назад

    What about cp and can we do dsa in python or it is modatory to do in cpp or java

  • @JesúsLópezLópez-u6q
    @JesúsLópezLópez-u6q 7 месяцев назад

    always a goddamn indian

  • @sh1w5z
    @sh1w5z 8 месяцев назад

    Volume is abit low

    • @Tensordroid
      @Tensordroid 7 месяцев назад

      Sorry, some mic issue

  • @anantagarwal8279
    @anantagarwal8279 8 месяцев назад

    do you earn enough to pay back the loan for vit? im not being condescending , im okay and happy with a very little disposable income but if u earn really good that is just cherry on top

    • @Tensordroid
      @Tensordroid 8 месяцев назад

      I actually did not take any loan, my income I would say is descent, I am able to afford stuff I want rn

    • @anantagarwal8279
      @anantagarwal8279 7 месяцев назад

      @@Tensordroid but its fees is so high ?

  • @micalopez3707
    @micalopez3707 8 месяцев назад

    Sorry for asking, at 1 year of distance. But if I want to detect something outside the YAMnet labels, like creating a new label, then YAMnet is not whorty any more right? Or is it whorty anyway for the power of the whole dataset, and training it with new audio to create new label would be a good idea? And then how to do it in a proper way?

    • @Tensordroid
      @Tensordroid 8 месяцев назад

      No problem ! ummm, if you want to detect something outside YAMNet's existing labels, you can still use YAMNet for its powerful pre-trained features. So actually you can use transfer learning: extract features from your new audio data using YAMNet, then train a new model on these features with your custom labels. this approach will help you from YAMNet's dataset while adapting it to your specific needs.

  • @rishavagrawal9070
    @rishavagrawal9070 8 месяцев назад

    Can you share more respurces for maths

    • @Tensordroid
      @Tensordroid 8 месяцев назад

      You can also study from khan-academy Rest Ig these 2 are more than enough for ML

  • @Prathamos
    @Prathamos 8 месяцев назад

    Skarparised you bro ❤ 6:56

  • @_Future_IITian
    @_Future_IITian 8 месяцев назад

    Hi bhaiya I am going to join lnct bhopal btech ai ml this year . Please can you help me I am really really confused abt my clg but as much as I researched it is the only decent clg I am getting according to my rank in jee mains (89.35 %ile,1.59lk ). Q1. The doubt in my mind is will the faculties be good ? Q2. Will I get any good job ? (my goal is to learn ml ,neural networking, how to teach mechine through data ,how to build networks ,etc stuff in detail) Q3. Will I need to do mtech? From where? For Which exam I have to prepare for? Q4. What skill should I start learning ? (I know little bit of python like class 12th level I had created a billing program as my cs boards practical project using python and mysql In it you can login ,create productl ist,quantity, edit quantity , add ,remove(only admin can other staff can create bill only) , add user info , add his list,he will get discount on basis of his visit frequency ,it also provide demo data for user to examin software ) Q5. Should I start learning c++ or first complete python? Q6.What skills should I start learning? Q7. From where should I learn skills like coding, communication skills (I am horrible at it,also lnct clg do not have much activity ), etc? Q8. is possible to improve skill while maintaining 75% attendance ?(I do not participate in much events,trips I can spare time from it) . Q9. How helpful are clg lectures? And much more advice from you please help.

    • @_Future_IITian
      @_Future_IITian 8 месяцев назад

      Hey brother please reply i need help

  • @akarsh-tripathi
    @akarsh-tripathi 8 месяцев назад

    Nice Video, I'll start folliwing this 🌟

  • @kwanhk6161
    @kwanhk6161 8 месяцев назад

    the volume is very low, can’t hear clearly

    • @Tensordroid
      @Tensordroid 8 месяцев назад

      Sorry, there was some mic issue

  • @vipuljaiswal4357
    @vipuljaiswal4357 8 месяцев назад

    Insightful

  • @tanmaysharma7285
    @tanmaysharma7285 8 месяцев назад

    🙌

  • @vipuljaiswal4357
    @vipuljaiswal4357 8 месяцев назад

    Amazing

  • @novmikvis
    @novmikvis 8 месяцев назад

    What hardware do you need to run this locally?

    • @Tensordroid
      @Tensordroid 8 месяцев назад

      You will need at-least 32 GB space, it you use torch.bfloat16, then 16 GB is required

    • @novmikvis
      @novmikvis 8 месяцев назад

      @@Tensordroid Is this is System RAM or GPU VRAM?

    • @Tensordroid
      @Tensordroid 8 месяцев назад

      @@novmikvis So you can set it right, on which you want to se using torch device, else device_map="auto", but the speed you are going to get at GPU is no where close to System RAM, you can use VLLM also for inferencing faster if you have multiple GPUs

    • @novmikvis
      @novmikvis 8 месяцев назад

      @@Tensordroid Great! Thanks for clarifying that.

  • @vipuljaiswal4357
    @vipuljaiswal4357 9 месяцев назад

    Amazing ❤