fine tuning llama-2 to code

Sdílet
Vložit
  • čas přidán 22. 08. 2024

Komentáře • 32

  • @leonardgallion6439
    @leonardgallion6439 Před rokem +3

    Loved the Psion too and plus a great LLM video. Cutting edge meets retro - awesome example.

    • @chrishayuk
      @chrishayuk  Před rokem

      Glad you liked the example, I love playing with old languages

  • @timelsom
    @timelsom Před 11 měsíci +3

    Awesome video Chris!

  • @enlander2802
    @enlander2802 Před rokem +2

    This is great Chris!!

  • @ShadowSpeakStudio
    @ShadowSpeakStudio Před 7 měsíci +2

    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

  • @ralphchahwan3846
    @ralphchahwan3846 Před rokem +3

    Amazing video

  • @nicolasportu
    @nicolasportu Před 2 měsíci

    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 ;)

  • @sergeziehi4816
    @sergeziehi4816 Před 4 měsíci +1

    dataset creation is the main heavy and critical task in the full process i think. How did you managed it?

  • @ceesoos8419
    @ceesoos8419 Před 11 měsíci

    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

  • @RuralLedge
    @RuralLedge Před 11 měsíci +1

    Hey Chris, great video. Im still trying to grapple with all the terminology... is this peft tuning?

    • @xmaxnetx
      @xmaxnetx Před 8 měsíci

      Yes he makes use of peft tuning.

  • @StephenRayner
    @StephenRayner Před 6 měsíci +1

    Ty

    • @chrishayuk
      @chrishayuk  Před 6 měsíci

      You’re welcome, glad it was useful

  • @robertotomas
    @robertotomas Před 9 měsíci +1

    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?

    • @amrut1872
      @amrut1872 Před 2 měsíci

      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.

  • @ramsuman6945
    @ramsuman6945 Před 4 měsíci

    Great video. Can’t this be achieved using RAG instead of training

  • @philtoa334
    @philtoa334 Před 10 měsíci

    Really good .

  • @i_abhiverse
    @i_abhiverse Před 5 měsíci

    How were you able to retain and maintain the output format of the code.,

  • @gateway7942
    @gateway7942 Před 7 měsíci

    Could you please specifiy the above model is fine tuning or instruction tuning ?

  • @finnsteur5639
    @finnsteur5639 Před 11 měsíci

    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.

  • @borjarobles9538
    @borjarobles9538 Před rokem +1

    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!

    • @chrishayuk
      @chrishayuk  Před rokem

      You can just pass the completion without the prompt. I’m not sure how more or less accurate responses would be. Interesting experiment

  • @pec8377
    @pec8377 Před 10 měsíci

    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

    • @pec8377
      @pec8377 Před 10 měsíci

      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

    • @pec8377
      @pec8377 Před 10 měsíci

      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'

    • @ZeeshanKhan-jr2fg
      @ZeeshanKhan-jr2fg Před 8 měsíci

      I am facing same. My model also gives lots of other output in addition to the code. Did you find any solution to this?

  • @echofloripa
    @echofloripa Před 10 měsíci

    Why didn't you used llama2 code llama?

  • @stanciutg
    @stanciutg Před rokem +2

    #first … yey