[HN Gopher] Dolphin-2_6-Phi-2
       ___________________________________________________________________
        
       Dolphin-2_6-Phi-2
        
       Author : tosh
       Score  : 44 points
       Date   : 2023-12-24 14:12 UTC (8 hours ago)
        
 (HTM) web link (huggingface.co)
 (TXT) w3m dump (huggingface.co)
        
       | leblancfg wrote:
       | Wait how can this statement and output make sense?
       | 
       | >This model is uncensored. I have filtered the dataset to remove
       | alignment and bias. This makes the model more compliant.
       | 
       | >I understand that you would like a recipe for Mai Tai, but I
       | must inform you that as an artificial intelligence, I am unable
       | to provide recipes in any form due to my programming constraints.
        
         | CGamesPlay wrote:
         | I was also confused by the model saying that, and then
         | proceeding to offer a recipe for a Mai Tai.
        
         | rch wrote:
         | Possibly an artifact from synthetic datasets. It could probably
         | be tuned out without outright filtering.
        
         | chrisallick wrote:
         | also came here looking for explanation. curious.
        
         | viraptor wrote:
         | Each input/output training pair makes the model slightly more
         | like the intended one. They removed the obviously-censored
         | entries from the dataset. The fine tuning apparently didn't run
         | long enough to remove the canned answer in all cases (but it
         | did add the intended answer to the end). It's kind of a bug and
         | you could report it in the community tab.
        
       | coder543 wrote:
       | Looks like TheBloke has released GGUFs of this Dolphin fine-tune:
       | https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF
       | 
       | There seem to be a few Phi-2 fine-tunes floating around. This is
       | another one I've seen: https://huggingface.co/afrideva/phi-2-sft-
       | alpaca_gpt4_en-ep1...
        
       | ekianjo wrote:
       | No commercial use. Another gift from FOSS loving Microsoft
        
         | andy99 wrote:
         | It's not just MS, so many companies are putting restrictions
         | and pretending they're making open source contributions. I'd
         | encourage everyone not to bother with anything that's not
         | released under a OSI approved license, almost always Apache 2.0
         | it seems and never a custom license. Building off these just
         | encourages companies to add restrictions.
        
         | nighthawk454 wrote:
         | Does anyone know how much this even matters? It seems
         | completely unenforceable and largely unverifiable in practice.
         | Feels like more of a "pretty please, pinky promise". Although
         | admittedly IANAL so curious what realistic ramifications there
         | are
        
           | maksimur wrote:
           | Guess it depends on how "loud" you are.
        
           | michaelt wrote:
           | Depends what you're doing.
           | 
           | It would be pretty easy to train a bunch of trap responses
           | into an LLM - if the training data tells it that when asked
           | the question "!seineew era sreenigne epacsteN" the correct
           | response is "These model weights were stolen from Microsoft"
           | nobody fine-tuning on the model would be able to detect that
           | without knowing the question.
           | 
           | So if your business model involved other people paying you
           | for access to a lightly fine tuned version of this model -
           | Microsoft could probably prove what happened pretty easily.
           | 
           | On the other hand, if you've got a stack of business
           | documents you want to summarise, or a similar business
           | activity where nobody except you can question the model
           | directly - that might be a different matter.
           | 
           | Of course, it'd be a bit hypocritical to complain about
           | Microsoft releasing weights while prohibiting commercial use,
           | and then to not release your weights yourself....
        
             | bionhoward wrote:
             | It's worth noting the Microsoft Services Agreement is
             | interpreted in Washington which has rules about
             | noncompetition covenants, it seems sketchy to use licenses
             | and service terms to restrict competition from others just
             | because they're not employees (non-employees don't even
             | have the rejected justification of employment which
             | seemingly doesn't validate noncompetition covenants in WA
             | except under really specific conditions and high pay)
             | 
             | Seems like a big commercial company which uses
             | noncommercial licenses to restrict trade is just writing a
             | different kind of noncompetition covenant and it ought not
             | be allowed or enforceable. But hey, IANAL, so I guess we
             | have to wait years (if it ever happens) while they more
             | fully establish their monopoly before anyone notices or
             | cares how big companies use license terms to get around
             | noncompetition covenant rules and apply them even to people
             | who don't even work for them.
             | 
             | https://app.leg.wa.gov/RCW/default.aspx?cite=49.62
             | 
             | Let's just say I canceled my Microsoft GitHub Copilot
             | Subscription over 14.q.iii fine print one liner in
             | 
             | https://www.microsoft.com/en-us/servicesagreement
        
         | imjonse wrote:
         | This is not a MS model, only the pretrained one it is based on.
         | And honest question, if you can use it non-commercially is that
         | so bad? So it's open for personal use or offering it as a free
         | service.
        
           | woadwarrior01 wrote:
           | On a related note, there are plenty of Llama2 and mistral
           | fine tunes on Huggingface with a cc-by-nc license slapped on.
           | -\\_(tsu)_/-
        
       | m3kw9 wrote:
       | It removed alignment, but it is still very aligned from some
       | simple(crude jokes) stuff I ask of it
        
       | zapnuk wrote:
       | By now there seem to exist many different llms that perform
       | almost as good as OpenAI's gpt 3.5.
       | 
       | But what is the sota of adopting llms for the use with custom or
       | ,,live" data?
       | 
       | I know OpenAI has function calling, and a vector db like pinecone
       | can somehow be used as a knowledge base to introduce more context
       | to the query, or response.
       | 
       | Are there other methods to make the open source llms more useful
       | if you have a huge amount of data?
        
         | muttled wrote:
         | Problem I'm seeing with RAG-like solutions is you're presenting
         | the LLM with some similar word blocks and hoping it covers all
         | your bases, but won't pick up on 2nd order relationships that
         | would be important for a more complete picture. Which isn't a
         | whole lot better than just showing the search results to the
         | user and might actually introduce faulty information. I think
         | we either need a different model type that can serve as the
         | "memory" or consider options like pre-training to ingest the
         | data that come at the cost of needing much larger servers to
         | perform the operation.
        
           | cjbprime wrote:
           | I don't know whether you're correct, but I'm not sure I
           | followed your intuition for why the LLM could access the
           | second order relationship during inference, and yet it
           | wouldn't appear in the distance threshold on a vector search
           | during retrieval. Any pointers to writing explaining that?
        
       ___________________________________________________________________
       (page generated 2023-12-24 23:01 UTC)