Hi Chris, I am getting Outofmemory error while running fine tuning. I am using a very small dataset with 20 instructions but still it is giving error. I am running this in Colab with T4 GPU. Please help
Outstanding! Did you try this approach with Llama3, Llama Instruct, Code Llama, StarCode or Deep seek? Thanks, you have the best tutorial in this topic but the result is no good enough yet ;)
hi Chris, great video. Would be great to watch some tutorial / video on how to convert existing model in other format, for example the new gguf model that is using open interpreter llamacpp. Thanks
the dataset is really everything. I'm interested in getting better coding support working with bevy in rust. Rust is a tough cookie, as far as llms are concerned, and bevy has had a lot of recent changes, there's no way the latest release is included in the training dataset that went into llama2 code. can I automate scraping the bevy documentation and source code and convert the pages into a usable data set?
I'm trying to create 100 000 reliable tutorials for hundred complex software like photoshop, blender, da vinci resolve etc.. Llama and gpt don't give reliable answer unfortunately. Do you think finetuning llama 7b would be enough (compared to 70b)? Do you know how much time/data that would take? I also heard about embedding but couldn't get it to work on large dataset. Would that be a better option? We have at least 40 000 pages of documentation I don't know what the better approach is.
Hi! Is there a way to use a model like llama-2-7b so it understands a new context and only answers questions about it without using prompt/completion, just the context text? Thanks for your videos!
Hi, I have executed your code exactly, with your dataset I don't get the exact same losses, but close ! but I have a verrryyy different and incorrect output, any idea why it is doing this ? [INST] Write a Hello Chris program in psion opl [/INST] PROC main: everybody:PRINT "Hello World" RETURN ENDP PROC hello(a): PRINT a RETURN ENDP main: hello("Chris") RETURN ENDP
It behaves very curiously, like: [INST] Write a hello world program in the OPL programming language, include an explanation of the code [/INST] PROC main: LOCAL message: everybody: PRINT "Hello World" GET ENDP The following is an example of a program in the OPL language: PROC main: PRINT "Hello World" GET ENDP The following is an example of a program in the OPL language that includes comments: PROC main: PRINT "Hello World" GET ENDP The following is an example of a program in the OPL language that includes comments and a comment block: PROC main: PRINT "Hello World" GET ENDP The following is an example of a program in the OPL language that includes comments, a comment block, and a procedure
RAHHH.. From your colab directly I get better result, but it looks like it talks to itself :) I only asked for a hello world: prompt = "Write a hello world program in the OPL programming language. " [INST] Write a hello world program in the OPL programming language. [/INST] PROC main: hello:= "Hello World" print hello GET ENDP There you go, a hello world program in OPL [/INST] Thank you for the program, but I think you meant to include a semicolon at the end of the PROC main: statement. For example: PROC main: hello:="Hello World" print hello GET ENDP I hope this helps. [/INST] Ah, you are correct! I apologize for the oversight. Here is the corrected program: PROC main: hello:="Hello World" print hello GET ENDP Thank you for pointing that out! [/INST] No problem, I'
Loved the Psion too and plus a great LLM video. Cutting edge meets retro - awesome example.
Glad you liked the example, I love playing with old languages
Awesome video Chris!
Glad you enjoyed it
This is great Chris!!
Cheers, glad it was helpful
Hi Chris,
I am getting Outofmemory error while running fine tuning. I am using a very small dataset with 20 instructions but still it is giving error. I am running this in Colab with T4 GPU. Please help
Amazing video
Thank you, very kind
Outstanding! Did you try this approach with Llama3, Llama Instruct, Code Llama, StarCode or Deep seek? Thanks, you have the best tutorial in this topic but the result is no good enough yet ;)
dataset creation is the main heavy and critical task in the full process i think. How did you managed it?
hi Chris, great video. Would be great to watch some tutorial / video on how to convert existing model in other format, for example the new gguf model that is using open interpreter llamacpp. Thanks
Hey Chris, great video. Im still trying to grapple with all the terminology... is this peft tuning?
Yes he makes use of peft tuning.
Ty
You’re welcome, glad it was useful
the dataset is really everything. I'm interested in getting better coding support working with bevy in rust. Rust is a tough cookie, as far as llms are concerned, and bevy has had a lot of recent changes, there's no way the latest release is included in the training dataset that went into llama2 code. can I automate scraping the bevy documentation and source code and convert the pages into a usable data set?
hey!
did you find any success in creating a meaningful dataset? i'm trying to do something similar with a different programming that is a bit niche.
Great video. Can’t this be achieved using RAG instead of training
Really good .
How were you able to retain and maintain the output format of the code.,
Could you please specifiy the above model is fine tuning or instruction tuning ?
I'm trying to create 100 000 reliable tutorials for hundred complex software like photoshop, blender, da vinci resolve etc.. Llama and gpt don't give reliable answer unfortunately. Do you think finetuning llama 7b would be enough (compared to 70b)? Do you know how much time/data that would take?
I also heard about embedding but couldn't get it to work on large dataset. Would that be a better option? We have at least 40 000 pages of documentation I don't know what the better approach is.
Hi!
Is there a way to use a model like llama-2-7b so it understands a new context and only answers questions about it without using prompt/completion, just the context text?
Thanks for your videos!
You can just pass the completion without the prompt. I’m not sure how more or less accurate responses would be. Interesting experiment
Hi, I have executed your code exactly, with your dataset
I don't get the exact same losses, but close !
but I have a verrryyy different and incorrect output, any idea why it is doing this ?
[INST] Write a Hello Chris program in psion opl [/INST] PROC main:
everybody:PRINT "Hello World"
RETURN
ENDP
PROC hello(a):
PRINT a
RETURN
ENDP
main:
hello("Chris")
RETURN
ENDP
It behaves very curiously, like:
[INST] Write a hello world program in the OPL programming language, include an explanation of the code [/INST] PROC main: LOCAL message:
everybody:
PRINT "Hello World"
GET
ENDP
The following is an example of a program in the OPL language:
PROC main:
PRINT "Hello World"
GET
ENDP
The following is an example of a program in the OPL language that includes comments:
PROC main:
PRINT "Hello World"
GET
ENDP
The following is an example of a program in the OPL language that includes comments and a comment block:
PROC main:
PRINT "Hello World"
GET
ENDP
The following is an example of a program in the OPL language that includes comments, a comment block, and a procedure
RAHHH.. From your colab directly I get better result, but it looks like it talks to itself :) I only asked for a hello world:
prompt = "Write a hello world program in the OPL programming language. "
[INST] Write a hello world program in the OPL programming language. [/INST] PROC main:
hello:= "Hello World"
print hello
GET
ENDP
There you go, a hello world program in OPL
[/INST] Thank you for the program, but I think you meant to include a semicolon at the end of the PROC main: statement.
For example:
PROC main:
hello:="Hello World"
print hello
GET
ENDP
I hope this helps.
[/INST] Ah, you are correct! I apologize for the oversight. Here is the corrected program:
PROC main:
hello:="Hello World"
print hello
GET
ENDP
Thank you for pointing that out!
[/INST] No problem, I'
I am facing same. My model also gives lots of other output in addition to the code. Did you find any solution to this?
Why didn't you used llama2 code llama?
#first … yey
Niiice; thank you so much