[HN Gopher] Tuning and Testing Llama 2, Flan-T5, and GPT-J with ...
       ___________________________________________________________________
        
       Tuning and Testing Llama 2, Flan-T5, and GPT-J with LoRA, Sematic,
       and Gradio
        
       Author : josh-sematic
       Score  : 94 points
       Date   : 2023-07-26 16:13 UTC (6 hours ago)
        
 (HTM) web link (www.sematic.dev)
 (TXT) w3m dump (www.sematic.dev)
        
       | SoylentYellow wrote:
       | There is too much overloading of terms these days. I saw LoRA,
       | thought LoRa, and wondered why someone would spell GNU Radio as
       | Gradio.
        
         | josh-sematic wrote:
         | Only 2 hard problems in computer science: (1) cache
         | invalidation (2) naming things (3) off-by-one errors :-D
        
       | MuffinFlavored wrote:
       | Is this a good test case for all of these competing open (and
       | even closed) source LLMs:
       | 
       | feed it a list of YouTube/SoundCloud quality "artists + song
       | titles" and ask it to clean them up/figure out how split/parse
       | them into CSV or JSON and then identify their genre
       | 
       | I want to make sure I'm not being too harsh when I criticize
       | these as useless if they can't do this "basic" task because I'm
       | pretty sure I was able to get GPT-3.5 to do this reasonably well
       | for about $0.50 with no token cost optimization
       | 
       | I'm just curious why people are so infatuated and putting so much
       | effort into all of these other open source models if they
       | couldn't complete this basic task.
        
         | josh-sematic wrote:
         | I think it depends a lot on the scale of what you're trying to
         | do, whether it's worth it or not to invest in OSS/DIY. If
         | you're one person looking to do a "one off" task like
         | organizing some of your own music, then you're correct that
         | it's probably not worth it to invest time and effort into
         | getting an open source model to do it for you. Just pay $0.50
         | and be done with it! But if you want to build an app that does
         | that for people, and you want to host it for free/cheap, the
         | costs could add up quickly. And especially if you are a company
         | with a language task that will have lots of users--the up front
         | R&D cost can definitely be worth it to save on costs of usage.
        
           | MuffinFlavored wrote:
           | I was trying to argue "the open source models can't do it in
           | their current state"
           | 
           | I'm curious what could be done time investment wise by a
           | single person like myself that could "tweak" LLAMA2 into
           | being able to do a task it by default can't
        
         | yacine_ wrote:
         | If you fine tune them to be task specific, they'll perform
         | well. In my experience, this control loop is a better
         | investment than "prompt engineering". (When I say task
         | specific, I mean _very_ task specific)
         | 
         | GPT4 over the API is too fine tuned, which constrains its
         | behavior. It fails to capture nuance in instructions. When you
         | have the bag of weights, you can actually control your model.
         | Having actual control over the model, and understanding the
         | infrastructure that it's running on helps you meet actual SLAs.
         | 
         | And it's cheaper, if you're not backed by infinite venture
         | money.
         | 
         | https://arxiv.org/abs/2307.13269
        
           | MuffinFlavored wrote:
           | Could you explain what you mean by fine-tune? For example, I
           | don't have the answers to what the songs parsed out + genre
           | identified into JSON looks like. You're saying I'd have to
           | train the model with known answers, and then maybe it could
           | predict with some accuracy going forward?
           | 
           | I don't see how this warrants the extra exciting popularity
           | of LLAMA2, etc.
           | 
           | I still haven't found my own personal niche "good enough"
           | test case
        
         | _jal wrote:
         | > I'm just curious
         | 
         | - Some people are committed to open source.
         | 
         | - Some people want to play with/learn/modify the technology,
         | not just use it instrumentally.
         | 
         | - Some people want to play with these models without the
         | surveillance that comes with renting them on OPC.
         | 
         | I'm sure there are other reasons I'm not thinking of, but I'm
         | in the middle of that particular Venn diagram.
        
       | yacine_ wrote:
       | This is an ad. You'd be best served avoiding additional
       | dependencies. At this point, you don't want to be trading off
       | simplicity for ease. Even transformers + huggingface feels like
       | too much bloat.
       | 
       | You can use this https://github.com/PygmalionAI/training-code
       | 
       | Or, you can use this; for QLoRA https://github.com/artidoro/qlora
       | 
       | The tools and mechanisms to get a model to do what you want is
       | ever so changing, ever so quickly. Build and understand a
       | notebook yourself, and reduce dependencies. You will need to
       | switch them.
        
         | turnsout wrote:
         | I'm fine with the Huggingface piece, but this joins the long
         | list of blog posts that make it to the top of hn with the
         | message "Easily fine tune an LLM! ...by tying yourself to our
         | proprietary platform"
        
           | josh-sematic wrote:
           | FWIW, this is not proprietary, it's all FOSS. And hopefully
           | there's something interesting in there even if you don't use
           | any of the tools mentioned.
        
             | turnsout wrote:
             | Fair enough--I was too lazy to click through to Sematic's
             | site and see that it is indeed FOSS!
        
         | ilaksh wrote:
         | For the Pygmalion thing, what should we use for the LoRA
         | parameters?
        
         | winddude wrote:
         | lol, qlora and pygmalion both wrap huggingface
        
           | yacine_ wrote:
           | yes, unfortunately :(
           | 
           | did you know that the weight adapter happens on demand, on
           | inference, in the LoRA forward pass function?
           | 
           | leaky, leaky, leaky
           | 
           | GGML will save us, surely
        
         | Der_Einzige wrote:
         | Huggingface + Transformers is and has been since at least 2018
         | the atlas holding up the rest of the NLP and pretty much all of
         | the AI community.
         | 
         | Their unwavering commitment to open-source should be celebrated
         | by all tech enthusiasts. Not sure why people poo-poo on them.
        
           | ShamelessC wrote:
           | The code is very enterprise oriented and reads more like Java
           | than Python. Bootstrapping a VC backed company off of open
           | source is a known strategy for achieving growth needed for
           | future funding and acquisition.
           | 
           | At some point, all the nice things they offer for free or
           | cheaper will go away or become expensive.
        
           | yacine_ wrote:
           | Bloated does not mean bad. It means bloated. Which, for my
           | purposes, makes it not the best choice.
        
           | chessgecko wrote:
           | People who dislike things are just so much more vocal than
           | people who like them. I've used Huggingface extensively, they
           | are trying to do a lot, but its always been the most
           | convenient/flexible for my finetuning use cases.
           | 
           | Thank you Huggingface!
        
           | josh-sematic wrote:
           | Yes, I'm a huge fan of Huggingface. There's a tendency to
           | always distrust anybody that is a company that is trying to
           | make money. But "makes some money with some of their product
           | offerings" != "is incapable of producing valuable resources."
           | It's always a balance, but I think Huggingface is doing well
           | at both being a huge resource for the NLP community and
           | having a viable business that allows them to keep being such
           | a resource.
        
       | AlphaWeaver wrote:
       | This was the first explainer of LoRA that actually "clicked" for
       | me.
        
       ___________________________________________________________________
       (page generated 2023-07-26 23:03 UTC)