Finetuning Open-Source LLMs

preview_player
Показать описание

This video offers a quick dive into the world of finetuning Large Language Models (LLMs). This video covers

- common usage scenarios for pretrained LLMs
- parameter-efficient finetuning
- a hands-on guide to using the 'lit-GPT' open-source repository for LLM finetuning

#FineTuning #LargeLanguageModels #LLMs #OpenAI #DeepLearning

Useful links to resources discussed in this video:

---

---

  1. Sebastian Raschka
  2. deep learning
  3. LLMs
  4. large language models
  5. Mistral
  6. Pytorch
Рекомендации по теме
Finetuning Open-Source LLMs 0:20:05

Finetuning Open-Source LLMs

Steps By Step 0:26:45

Steps By Step Tutorial To Fine Tune LLAMA 2 With Custom Dataset Using LoRA And QLoRA Techniques

Fine Tuning LLM 2:37:05

Fine Tuning LLM Models – Generative AI Course

Should You Use 0:06:40

Should You Use Open Source Large Language Models?

OpenLLM: Fine-tune, Serve, 0:10:31

OpenLLM: Fine-tune, Serve, Deploy, ANY LLMs with ease.

Fine-tuning Large Language 0:28:18

Fine-tuning Large Language Models (LLMs) | w/ Example Code

Prepare Fine-tuning Datasets 0:15:22

Prepare Fine-tuning Datasets with Open Source LLMs

'okay, but I 0:24:20

'okay, but I want Llama 3 for my specific use case' - Here's how

Fine Tune LLaMA 0:09:44

Fine Tune LLaMA 2 In FIVE MINUTES! - 'Perform 10x Better For My Use Case'

Fine-tuning ANY Open 0:06:02

Fine-tuning ANY Open Source Model like a Pro

Generative AI Fine 2:36:50

Generative AI Fine Tuning LLM Models Crash Course

LLM Fine Tuning 1:21:01

LLM Fine Tuning Crash Course: 1 Hour End-to-End Guide

Finetuning Open-Source LLMs 0:29:04

Finetuning Open-Source LLMs // Sebastian Raschka // LLMs in Production Conference 3 Keynote 1

Fine-tuning Open Source 1:07:15

Fine-tuning Open Source LLMs with Mistral | Tokenization & Model Performance

LLAMA-3.1 🦙: EASIET 0:15:08

LLAMA-3.1 🦙: EASIET WAY To FINE-TUNE ON YOUR DATA 🙌

QLoRA—How to Fine-tune 0:36:58

QLoRA—How to Fine-tune an LLM on a Single GPU (w/ Python Code)

Fine-tuning Llama 2 0:18:28

Fine-tuning Llama 2 on Your Own Dataset | Train an LLM for Your Use Case with QLoRA on a Single GPU

Finetune Open Source 0:30:18

Finetune Open Source LLMs for Function Calling with Unsloth | Dataset, Training and Inference

Create fine-tuned models 0:21:52

Create fine-tuned models with NO-CODE for Ollama & LMStudio!

LLAMA-3 🦙: EASIET 0:15:17

LLAMA-3 🦙: EASIET WAY To FINE-TUNE ON YOUR DATA 🙌

Fine-Tuning LLMs: Best 0:53:48

Fine-Tuning LLMs: Best Practices and When to Go Small // Mark Kim-Huang // MLOps Meetup #124

Developing an LLM: 0:58:46

Developing an LLM: Building, Training, Finetuning

How Fine-tuning Open 0:58:13

How Fine-tuning Open Source LLMs Solves GenAI Productionization - Piero Molino | Stanford MLSys #94

'I want Llama3 0:24:02

'I want Llama3 to perform 10x with my private knowledge' - Local Agentic RAG w/ llama3

Комментарии
Автор

Thanks for sharing, especially about Lit-GPT (I'm always interested in more tutorials as my journey with fine-tuning and LLMs needs all the help it can get). Thanks again.

kenchang
Автор

Very much appreciate this video, fine-tuning seemed like a somewhat amorphous concept to me for sometime, but the diagrams you showed really made it easier to understand how people finetune.

Dom-zyqy
Автор

I recently listened to your latest videos. And now this one was recommended by perplexity for my specific use-case ;-) coincidence?

mulderbm
Автор

One of the approaches I have experimented with, which is both manual labor, time and compute expensive but more reliable, is as follows:
- Use a LLM to query for outputs. Use RAG and prompt engineering to get the best possible results.
- Generate chat logs for each query. The log should include everything - the prompt, the retrieved info if any and the model output. Any special symbol such as to denote the system prompt or anything else should also be left in. This is because LLMs are text generation models with no concept of chat.
- Manually update the model outputs to better reflect the expected output. This is a data creation task.
- Fine tune a copy of the same LLM using PEFT using the updated chat logs.

This can also be done iteratively as long the chat logs are generated initially by a model which hasn't been fine-tuned yet. Like a sort of A/B experiment. Some use cases are served the original model that generates the data for fine-tuning while the other are served the fine-tune model whose outputs are not used for any further fine-tuning.
Expensive but over time, your model would work better for realistic inputs.

MayurGarg
Автор

Thanks for the video, very helpful for me to understand different kinds of finetunning. BTW, what kind of finetunnig is huggingface belong to?

zjffdu
Автор

Time saw you here on YT! Hope you remember me.!

muhammadanas
Автор

I really wish people would stop putting their x link and start sharing something like mastadon or threads, as a free user, x is where u go to feel second class citizen.

PtYt