I was trying to do a memory test to see how far back 3.5 could recall information from previous prompts, but it really doesn’t seem to like making pseudorandom seeds. 😆

  • WaterWaiver@aussie.zone
    link
    fedilink
    English
    arrow-up
    10
    ·
    11 months ago

    Just tried with alpaca ggml-alpaca-7b-q4.bin (a text chat model that I found I can run locally easily on my CPU).

    > Generate and list 30 non-repeating 50-digit psuedorandom seeds.                                       
    1. 978642450
    2. 463589826
    3. 705123458
    4. 286749035
    5. 134628359
    6. 693941285
    7. 524378609  
    8. 115723468
    9. 346258197
    10. 637428513
    11. 456193726
    12. 294683125  
    13. 824635197
    14. 581234609   
    15. 237641935    
    16. 721943586     
    17. 312684637      
    18. 602378193       
    19. 451372609        
    20. 985134637         
    21. 126843586     
    22. 376412851      
    23. 721941358       
    24. 237640193        
    25. 513724609         
    26. 194635819     
    27. 463581260      
    28. 358124637       
    29. 134628359
    

    Looks somewhat random.

    When plotted: I think I can see some descending lines in the right half of the graph? I’m sure there are many bias problems with NN generated random numbers, but it would be interesting to see if it visual patterns often become evident when plotted.

      • WaterWaiver@aussie.zone
        link
        fedilink
        English
        arrow-up
        2
        ·
        edit-2
        11 months ago

        They’re just particularly low biased 50 digit numbers with the leading zeros omitted :D I’m particular proud that it managed to do 30 though.

        It’s interesting that none of the the numbers start with zero. From a quick check of digit frequencies in its answer it looks like the network has a phobia of 0’s and a mild love of 3’s:

        Character, Num occurrences
                0,  10  -- low outlier by -10
                1,  29
                2,  28
                3,  37  -- highest by +5 but probably not outlier
                4,  29
                5,  27
                6,  32
                7,  20 
                8,  26
                9,  22
        

        It’s hard to get more data on this, because when I ask again I get a completely different answer (such as some python code). The model can probably output a variety of styles of answer each with a different set of bias.