How To Fine-tune The Llama 1 Models(GPT3 Alternative)

preview_player
Показать описание
The LLaMA models have impressive performance despite their relatively smaller size, with the 13B model being even better than GPT3!

In this video, I go over how you can make the models even more powerful, by finetuning them on your own dataset!

#ai #chatgpt #docker #gpt3 #machinelearning #nlp #llama #gpt4 #wandb #llm

Timestamps
00:00 - Intro
00:16 - Model Metrics And Explanation
01:24 - Github Repo
01:39 - Finetuning Process Differences
02:36 - Setup Walkthrough
04:23 - Running Docker Image
06:00 - Looking At Run Flags
08:05 - Getting The Model Weights
10:11 - 3090 Server Performance
11:16 - A100 Server Performance
11:40 - WandB Loss Graphs
12:09 - Finetuned Model Inference
13:07 - Outro
Рекомендации по теме
Комментарии
Автор

In this video, I just fine-tune the 7B version. However, given more resources(mainly RAM) there is no reason the larger models couldn't be fine-tuned as well. I suspect that at least the 33B model could be fine-tuned this way, but I wouldn't be suprised if 65B worked as well.

Update: Less than 24 hours after this video release a breaking change has happened with that PR with regards to the tokenizer. Its effectively just a renamed but it breaks the autotokenizer. I will work to update it quickly.

Brillibits
Автор

Everyone is talking about Gpt4, but this is the exciting stuff right here. Thank you for doing this.

jameshughes
Автор

Great to hear that you found the video helpful! I noticed that you've been addressing some important questions on your blog post. Speaking of which, I have a question that I believe you could help me with. I'm curious about the instructions for training the LLaMA model with my own data. Specifically, if I have a library of law cases and want to turn my Alpaca into a robo-lawyer, what would be the process for further training the models based on the existing work? Thank you in advance for your help!

frankvitetta
Автор

Thank you so much for these videos, setting it up now

MachineMinds_AI
Автор

Could you make a video about how to set up (and rent?) a gpu server with llm in mind?

javideas
Автор

Any chance youll cover how to add the stanford Alpaca retrain? I think the 13b version was just released today.

NewMateo
Автор

Thanks for sharing. Very good insights.

deltavthrust
Автор

LlaMa's story remind me of Robin Hood. Thanks continuing to bring rich content to the people🏹

quantumbyte-studios
Автор

Gem of a work '''' 👍👍

muhammadshahzaib
Автор

great videos. we are currently working on build ML box with two Nvidia 4090 RTX. do you think we could do the bigger LLaMA?

mattbuscher
Автор

Thank you for this video; I have a question: can you see the weights of the model?
So you could, for instance, train a new neural network composed of Llama and newly added neurons.
Or is Llama operating as a program for which you do not have access to the NN's source code or structure?
In which case, can you train a NN that interacts with Llama running on your own computer?

bosquillondejenlisarmand
Автор

I could not figure out the lama but it downloaded the world on my machine. For such a small... Model it takes a ton of space. You should make a video on how to lama.

timothymaggenti
Автор

Thank you very much @Brillibits. This is very helpful video and impressive work. I have one question. I like to fine-tune using question answer data set. Is it possible to fine-tune using this Q&A data set? if it is possible can you point out the reference document or video to do it? GOAL: I need add more data(which is in plane text and I'm converting into Q&A data set) to customize the model.

Jena
Автор

Hi! thanks for the great video! I noticed the repository has already changed compared with the video one. Is there any more detailed steps how to finetune with the new files, starting from environment building? I'm not sure when building the docker, which is the first file I need to run build imagesh? and what's the file about update llamash?

sseot
Автор

How do you control your Linux machine from your Mac? If you could give me an idea to look up the rest on the internet. Another question, what version of Linux are you using? Thank you very much.

DataRockShow
Автор

Hi, why can you directly use the path on huggingFace? Is that because of Deepspeed?

yuantian
Автор

how do these llama models perform with foreign language queries? are there any stats on this?

eyemazed
Автор

Is it possible to train the model with, let's say, some documentation ?
So that I can just ask him to help me to resolve a problem, and it can answer fast ?

maxencelaurent
Автор

Would this process work for WizardLM 13b?

spotterinc.engineering
Автор

Do we need to download the weights separately to run this?

Alvee_AI