but i guess here's one: finetuning qwen2.5-32b on various ai related github prjs that are written in python, with a focus on agentic workflows, maybe individual finetunes for each agent python lib / framework, such as autogen, langchain / langgraph, ...
Sadly this may be the first time I disagree with that sentiment. Haha. I loved it but was looking for a course link at the end because it was too much too fast ;)
@@OilersFlash Yea bro (actually uncle, cuz I'm 15 and your dp shows...), I realized that the viewer will need some pre knowledge of LLMs and its workings and also some pre basic knowledge of fine-tuning! But yea the video was good actually!
This is exactly how we are tuning our open source LLMs, the use of unsloth+LORA is key. Validation of the learning is an adventure. We did this over the same tech stack mentioned here. Very good video, of course, lots of details behind each step that cannot be explained in a short video. Great use of lighting and your pace is excellent. Looking forward to more vids.
it depends, this is useful, just if you already know how to do it and you just need a refresh on the steps. In other words, you want to watch it just if you do not need it
I was already taken by the clear content but the KEY highlight of simply mentioning Conda shows the high quality of your informations. Subscribed and thanks for the tuto.
Great video straight to the point, but could you please elaborate more on feeding custom dataset to the script? What are the steps? You wrote it right on the script or did you load it from a different file? Or did you upload to hugginface and use the token from there? Im confused
Every how-to I've found so far glazes over the training datasets. Like here she goes from here is 100k sql dataset, then here are is how the model expects the prompt, but then doesn't show the format of how the dataset is loaded into the model. What does the sql_context look like, what does the sql_prompt look like, what is the sql, and sql_explaination? Fine tuning is one thing but people also need to know how to build and integrate datasets for training.
Great tutorial! Thanks. Really like the definitions and explanations rather than just glossing over the code.. would love to see a full tutorial series 😮 I'd like to try to code it myself, but it would be good if you could share the code too.
Thank you for your informative tutorial. I’ve installed Ollama on Windows 10 and currently only use it for interactive conversations through CMD. However, I asked a friend, and they mentioned that Ollama cannot be used for fine-tuning. Why is that? Additionally, Unsloth offers convenient online fine-tuning, but if the training data requires privacy and fine-tuning needs to be done locally or even if the base model is in Safetensors format from others-where should I start? Are there any learning resources or references you would recommend? Thank you!
@warpdotdev In the interest of establishing the repeatability of your result can you indicate whether the output @ 5:01 is unedited? typical? Mine is amending the prompt and typically produces output in the format of the Alpaca training text generating entries of 'SQL Prompt', 'SQL', 'Explanation', 'Question', 'Instruction', 'Company database' in the output.
Thank you for video. I followed your approach for finetuning the model text to SQL. When I work on my own database, its performance is not good. Unable to generate SQL query. I even used agent and examples queries our database. I am requesting suggestion from you. Thank you
I would appreciate if this tutorial went more into detail on how to make a dataset comply with the model's promt template. From this video, there is no data processing being done and i think in real cases you would have to work with the data, or write a script, that chnges the data so that it fits with the prompt template (e.g. the Alpaca one she shows in the video)
Thanks! Although I do have a question why you show so much of yourself... I admit it's nice and pleasant to look at, however I would prefer to look at the code or things you talk about. Especially when I watch your videos at work I would definitely like to avoid someone thinking that I watch some silly videos during work while I actually watch work related stuff. Anyway, really interesting videos so thanks again! 😊✌
I'm working on a RAG application. I'm using a pdf file as a text data and I have clean the data as well using NLTK. I already have ollama install in my local system and also llama2 model. I embed the data in to vector form using ollama embedded model mxbai-embed-large and store it on chromabd. but if I give the prompt and get response, it give me the response but not according to my data. and how do I finetune the model? I just need guidance and sequence so I work on the project. It's important to me. I need your guidance. please reply. I'm using windows10. Thank you!
@@ibrahimgamal7603 Could be anything such as you are not using a good doc extractor or your embedding model sucks. Changing chunk and overlap size might help. Don't go for finetuning straight away, do some experimentation and figure out where the problem lies exactly otherwise even finetuning won't work.
Can you train 12B on 24GB or is 12B too big? Another question is if you have multi-turn data (conversations) can you finetune on that? The examples I see are for Q:A pairs.
It's a great how to but you missed a "before trainng" and "after training" examples of how the model responded. Good video anyway. Couldn't get much out of it though
if I train a model, will the responses be restricted to just my training data/examples? Or does the model's original training also play a role? For example, say I trained it on model to respond with vehicle specs. I feed it a vehicle name and the model returns the vehicle specs. Say I finetune the model with 50 examples (honda civic, toyota camry, volvo xc90, etc).... however, in reality there are 300,000 possible vehicles. Would finetuning on 50 examples help? Sure, I can put the 50 models in the prompt but then I'd just be wasting tokens.
why didn't you directly use hugginface trainer to train, why using unsloth? I want to know what was the benefit of using unsloth over hugginface trainer.
Here it is, she says.. For simplicity.... A pip install command.. In a video.. With no pasted text to copy in the description. That's the opposite of simplicity.
that subselect that it generated @5:01 makes me instinctively cringe - hoping it would generate the subselect as a join... - for instance why do: "select p.* from posts as p inner join posttags as pt on p.post_id = pt.post_id where tag_id in ( select tag_id from tags where name = 'terminal' )" instead of: select p.* from posts p inner join posttags pt on p.post_i = pt.post_id inner join tags t on t.tag_id = pt.tag_id where t.name = 'terminal' seriously - the 2nd one appears easier to optimize. right? oh well....
Why are there so many videos that are useless as tutorials and give the impression that they are only about self-promotion? Seriously, anyone who understands this quick run-through here doesn't need any more tutorials, and for the vast majority of the rest, it's probably pretty useless.
Good video, but it’s hard to imagine that you you actually sat there and edited out every breath and pause so that the whole video would sound like one massive run on sentence, only to shave off some 20 or 30 seconds of duration.
What data would you fine tune your LLM on?
what is your hardware ? are you using intel or amd threadripper ?
that depends on the use case... are you asking for what use cases people are aiming to support?
but i guess here's one: finetuning qwen2.5-32b on various ai related github prjs that are written in python, with a focus on agentic workflows, maybe individual finetunes for each agent python lib / framework, such as autogen, langchain / langgraph, ...
youtube need more chanels alike this. great job
I'm using it to fine-tune a Minecraft bot (Mindcraft from Emergent garden)
No over rating, no over talking, streight forward, love it.
Sadly this may be the first time I disagree with that sentiment. Haha. I loved it but was looking for a course link at the end because it was too much too fast ;)
@@OilersFlash Yea bro (actually uncle, cuz I'm 15 and your dp shows...), I realized that the viewer will need some pre knowledge of LLMs and its workings and also some pre basic knowledge of fine-tuning! But yea the video was good actually!
@@siddhubhai2508 it is good ;)
Knowing such a deep technical subject is one thing, but teaching it well is another! well done young lady.
This is exactly how we are tuning our open source LLMs, the use of unsloth+LORA is key. Validation of the learning is an adventure. We did this over the same tech stack mentioned here. Very good video, of course, lots of details behind each step that cannot be explained in a short video. Great use of lighting and your pace is excellent. Looking forward to more vids.
Thank you straight to the point
I usually have some ptsd when looking at tutorials
it depends, this is useful, just if you already know how to do it and you just need a refresh on the steps. In other words, you want to watch it just if you do not need it
Great video for people who know coding and local llm but havent finetuned!
amazing quality of editing, sound, video - beyond the programming side!
A pleasure for the eyes and ears to watch!
I was already taken by the clear content but the KEY highlight of simply mentioning Conda shows the high quality of your informations. Subscribed and thanks for the tuto.
This is what I am thinking to do. Finding this video maybe saved half a day
Easiest subscribe of my life, just wanted something easy and straight to the point
Insanely good video!! Straight to the point and great presentation
Five minutes made useful. Thank you for the crisp and neat video. ❤
Great explanation and presentation of LLM.
Great video straight to the point, but could you please elaborate more on feeding custom dataset to the script? What are the steps? You wrote it right on the script or did you load it from a different file? Or did you upload to hugginface and use the token from there? Im confused
Intresting video!!
Hi there.
It's wonderful.. Will you Please share the notebook and also Google Collab notebook?
Every how-to I've found so far glazes over the training datasets. Like here she goes from here is 100k sql dataset, then here are is how the model expects the prompt, but then doesn't show the format of how the dataset is loaded into the model. What does the sql_context look like, what does the sql_prompt look like, what is the sql, and sql_explaination? Fine tuning is one thing but people also need to know how to build and integrate datasets for training.
Agreed. Every video is skipping over detail to actually build your own functionality.
That’s kind of the point. It’s open source open secret
What a clean presentation.
great and short video guys incredible!!
good guide to play by myself
Great tutorial! Thanks. Really like the definitions and explanations rather than just glossing over the code.. would love to see a full tutorial series 😮
I'd like to try to code it myself, but it would be good if you could share the code too.
Appreciate the brevity. Thank you.
nice and straight forward approach
Great video. To the point. Effective
I actually liked the music. Great editing also. I found the proyect idea a little bit boring. You could train it for something actually awesome
Great video! Subscribed! 🎉
Another great video!! Thanks.
Thank you for your informative tutorial.
I’ve installed Ollama on Windows 10 and currently only use it for interactive conversations through CMD.
However, I asked a friend, and they mentioned that Ollama cannot be used for fine-tuning. Why is that?
Additionally, Unsloth offers convenient online fine-tuning, but if the training data requires privacy and fine-tuning needs to be done locally
or even if the base model is in Safetensors format from others-where should I start?
Are there any learning resources or references you would recommend?
Thank you!
Well explained. Thanks
Thanks 🙏
wouldve been nice if you had shared the full collab code...
Yoo, what theme are you using in your system?? That's really cool
@warpdotdev
In the interest of establishing the repeatability of your result can you indicate whether the output @ 5:01 is unedited? typical? Mine is amending the prompt and typically produces output in the format of the Alpaca training text generating entries of 'SQL Prompt', 'SQL', 'Explanation', 'Question', 'Instruction', 'Company database' in the output.
Nice video, but the music is way too disctracting.
Thank you for video. I followed your approach for finetuning the model text to SQL. When I work on my own database, its performance is not good. Unable to generate SQL query. I even used agent and examples queries our database. I am requesting suggestion from you. Thank you
subscribed
Excellent direct video on fine-tuning, congrats. Could you also share the python source code that you used in the video? Thanks.
is the notebook posted anywhere?
Excellent tutorial! Doesn’t lowering the bit depth of the model greatly reduce accuracy? What are the pros and cons of doing so? Thanks!
I would appreciate if this tutorial went more into detail on how to make a dataset comply with the model's promt template. From this video, there is no data processing being done and i think in real cases you would have to work with the data, or write a script, that chnges the data so that it fits with the prompt template (e.g. the Alpaca one she shows in the video)
How long did it take for the training / fine-tuning on your 4090? Thanks for the video!
Nice
what ubuntu are you using, the terminal looks dope
Thanks! Although I do have a question why you show so much of yourself... I admit it's nice and pleasant to look at, however I would prefer to look at the code or things you talk about. Especially when I watch your videos at work I would definitely like to avoid someone thinking that I watch some silly videos during work while I actually watch work related stuff. Anyway, really interesting videos so thanks again! 😊✌
I'm working on a RAG application. I'm using a pdf file as a text data and I have clean the data as well using NLTK. I already have ollama install in my local system and also llama2 model. I
embed the data in to vector form using ollama embedded model mxbai-embed-large and store it on chromabd. but if I give the prompt and get response, it give me the response but not according to my data. and how do I finetune the model? I just need guidance and sequence so I work on the project. It's important to me. I need your guidance. please reply. I'm using windows10.
Thank you!
It's easy you should write in your prompt template = """Answer the question based ONLY on the following context:
{context}
Question: {question}
"""
@@ibrahimgamal7603 Could be anything such as you are not using a good doc extractor or your embedding model sucks. Changing chunk and overlap size might help. Don't go for finetuning straight away, do some experimentation and figure out where the problem lies exactly otherwise even finetuning won't work.
@@muhammadumarnawaz9200 ok mate thank you for your help
It was a great video, but I have a question, is it compatible with the new versions called 3.2, especially versions 1B and 3B?
damn, now i want to create my own personal DAN assistant without OpenAI interfere with her
Apologies if this is a dumb question, but where is, is there a link to the notebook?
I have 55K classes with an ungodly amount of transcripts. What'll be better and faster? RAG or finetuning?
Can you train 12B on 24GB or is 12B too big?
Another question is if you have multi-turn data (conversations) can you finetune on that? The examples I see are for Q:A pairs.
It's a great how to but you missed a "before trainng" and "after training" examples of how the model responded. Good video anyway. Couldn't get much out of it though
Isn't this RAG? Doesn't chunking fit anywhere?
if I train a model, will the responses be restricted to just my training data/examples? Or does the model's original training also play a role?
For example, say I trained it on model to respond with vehicle specs. I feed it a vehicle name and the model returns the vehicle specs. Say I finetune the model with 50 examples (honda civic, toyota camry, volvo xc90, etc).... however, in reality there are 300,000 possible vehicles. Would finetuning on 50 examples help? Sure, I can put the 50 models in the prompt but then I'd just be wasting tokens.
where is the link for google colab?
Do you have github repo of the code?
can this be done all from the wsl terminal? I am using ollama, webui and docker, but would like to train some company pdf's better, can this be done?
fine tuneing offline ?
what is the estimate cost for training such a model?
I think I'll just get an llm to make the dataset and make it llms both sides of the data->training loop
Does fine-tuning shouldn't generate small models that theoretically run fully local and avoid spending money on OpenAI?
Is it possible to make your own AI model with this that speaks to you like Jarvis and understands tone, etc?
How to collect dataset pls show it
Video on formatting data sets to follow? 😅
Give us the collab link! Or better yet the llamasql gguf link!
why didn't you directly use hugginface trainer to train, why using unsloth? I want to know what was the benefit of using unsloth over hugginface trainer.
No benefit My friend :(
Less memory was what she stated
Here it is, she says.. For simplicity.... A pip install command.. In a video.. With no pasted text to copy in the description.
That's the opposite of simplicity.
Is unsloath free?
Congrats for finding such a smartie-cutie as a DevRel for Warp
Unsloth has a dependency of triton, which doesn't seem to be compatible with windows.
Inam finding difficulty understanding the converting of data set
Is ubuntu on windows ? Or dependent system ?
I need more tiny steps to convert the dataset
She's cute and I can now fine tune my llama 3. Yay 🎉
Thankyou sis
at 2:00 is 8 Billion not 8 bit.
We need a video to explain this video
Can we train tinyllama to do something similar? Since was trying to run AI on Raspberry Pi 5 (with Hailo AI Accelerator)
Absolutely!
@@warpdotdev Thanks! ❤️ from India
link
Can I do this without Conda? I hate Conda
Why yes, why wouldn’t you?
Why not share the source code???
that subselect that it generated @5:01 makes me instinctively cringe - hoping it would generate the subselect as a join... - for instance why do:
"select p.* from posts as p inner join posttags as pt on p.post_id = pt.post_id where tag_id in ( select tag_id from tags where name = 'terminal' )"
instead of:
select p.* from posts p inner join posttags pt on p.post_i = pt.post_id inner join tags t on t.tag_id = pt.tag_id where t.name = 'terminal'
seriously - the 2nd one appears easier to optimize. right? oh well....
Ashley, look at me
Gonzalez Susan Walker Larry Martinez Joseph
cant use claude!!!!
Rodriguez John Thomas Lisa Rodriguez Jose
let us use ollama with warp ai :(
Why are there so many videos that are useless as tutorials and give the impression that they are only about self-promotion? Seriously, anyone who understands this quick run-through here doesn't need any more tutorials, and for the vast majority of the rest, it's probably pretty useless.
Good video, but it’s hard to imagine that you you actually sat there and edited out every breath and pause so that the whole video would sound like one massive run on sentence, only to shave off some 20 or 30 seconds of duration.
Windows 🥴
Next time pls avoid the background music , it's distracting from focusing.
Are you a Mr or a Mrs? It's 202024 I don't wanna assume
20,000 years from now
I want to create on that creates computer virus, and hacking software would it be the same idea? lol jk
wow to much stuf in 5min
Obama use Ollama
Please bring it for windowsssssss😢😢😢
shes pretty... what was this video about?
This video is not recommended for the newcomers. She speak fast, in every few second is a cut on the footage. Really not detailed
You are so pretty.
White Donald Allen Deborah Anderson Kimberly
Why she looks like Andrew Ng 😂😂
please talk to the lens and not yourself on the screen you're looking at
uv > anaconda