Part 2-LoRA,QLoRA Indepth Mathematical Intuition- Finetuning LLM Models

Показать описание

In this video we will be dicussing about amazing finetuning technqiues which is called as LoRA and QLoRA technqiues, low order rank adaptation, quantized Lora.
----------------------------------------------------------------------------------------------------
Support me by joining membership so that I can upload these kind of videos
-----------------------------------------------------------------------------------

►Data Science Projects:

►Learn In One Tutorials

End To End RAG LLM APP Using LlamaIndex And OpenAI- Indexing And Querying Multiple Pdf's

►Learn In a Week Playlist

---------------------------------------------------------------------------------------------------
My Recording Gear

Рекомендации по теме

Комментарии

Sir please make a RAG and Langchain playlist only using OPEN SOURCE model locally....not via api calls and strictly not using OPENAI.... because this is the current use case every one is looking for

copilotcoder

a quick and clear explaination of the terms ive heard but never fully defined!

IdPreferNot

Thank you Krish sir for the Indepth Explaination

rishuraushan

Excellent video on Fine Tuning and the approach as well. Keep it up

bilalmohammed

Very helpful video sir following you for a long time now, every time I want to learn something new I come here and learn lots of stuff... Thank You Sir🙌🙌

dhairyasaatoliya

Thank you Krish, very helpful video. Please keep them coming. Appreciate your efforts!

dppcwjr

Hi Krish, One of the key components in the interviewing process is the coding interview. While there are many coding interview practice sites for developers, very less such resources for data scientists. Would you consider creating a video series for this?

trevorwills

fantastic series man! It will be nice to see a tutorial with pdf locally...

fabsync

We want more videos recording fine tuning the model

velugucharan

can you create a video giving a idea about mostly used finetuning methods. like a intro to different algorithms for fine tuning.

DIYANAMUHAMMED-mn

Hey krish, thank you so much for the video. Can you make a video to explain about how to preprocess data from different sources like pdf, databases and api's to fintune the llm model.

aravindraamasamy

Thanks Krish plz explain the generative AI framework its advance study

sudhirkhadke

Which device do you use for note taking?

rahatrezasulemani

Hi Krish, An interview question being asked in gen ai interview repeatedly is that how do you compare llm models. Or how did you reach to conclusions that this llm is best for you (considering there are so many)?

Krish or anyone please feel free to comment on this.

RahulKumar-lvyz

But how based on the rank the parameter is increasing here ? How does correlate to each others ?

mahikhan

what application do you use for writing notes?

Juicysalad

which whiteboard do you use? Please suggest

ShivamPatel-ygkd

Part 2-LoRA,QLoRA Indepth Mathematical Intuition- Finetuning LLM Models

Part 2-LoRA,QLoRA Indepth Mathematical Intuition- Finetuning LLM Models

Part 1-Road To Learn Finetuning LLM With Custom Data-Quantization,LoRA,QLoRA Indepth Intuition

LoRA & QLoRA Fine-tuning Explained In-Depth

LoRA explained (and a bit about precision and quantization)

Fine Tuning LLM Models – Generative AI Course

Finetuning LLM- LoRA And QLoRA Techniques- Krish Naik Hindi

LLaMA explained: KV-Cache, Rotary Positional Embedding, RMS Norm, Grouped Query Attention, SwiGLU

QLoRA: Efficient Finetuning of Quantized Large Language Models (Tim Dettmers)

LoRA: Low-Rank Adaptation of Large Language Models Paper Reading

Fine Tuning Phi 1_5 with PEFT and QLoRA | Large Language Model with PyTorch

Language Models for Protein Data - Evolutionary Scale Modeling: Amelie Schreiber | Munich NLP 024

LLM Optimization - Techniques and Insights

Spectrum: Training Domain-Adapted SLMs

Single-Step Language Model Alignment & Smaller-Scale Large Multimodal Models | Multimodal Weekly...

EMNLP 2022 Tutorial - 'Modular and Parameter-Efficient Fine-Tuning for NLP Models'

Future of Decentralization, AI, and Computing Summit

ArXiv Paper ThinK: Thinner Key Cache by Query-Driven Pruning By Yuhui Xu, Zhanming Jie, Hanze Dong

Are 1-Bit Weights The Future of Matrix Multiplication?!?!!?

Tutorial on Generative AI | New Tech for LLMs

Eight Things to Know about Large Language Models

Fine-Tuning Mistral 7B with Mistral-finetune

Large Language Models (in 2023)

Session 5: Building a Production-Grade Open-Source RAG System with Llama 2, FastAPI, and Chainlit