Date: Sat, 22 Apr 2023 14:34:35 -0400 From: Aryeh Friedman <aryeh.friedman@gmail.com> To: Mario Marietto <marietto2008@gmail.com> Cc: freebsd-hackers <freebsd-hackers@freebsd.org>, Yuri Victorovich <yuri@freebsd.org>, FreeBSD Mailing List <freebsd-questions@freebsd.org>, Odhiambo Washington <odhiambo@gmail.com> Subject: Re: Installing openAI's GPT-2 Ada AI Language Model Message-ID: <CAGBxaXkY0DD_0KCfzxPwQfGAoS=4imOmVVN-0oNCpr%2BcOVWmbQ@mail.gmail.com> In-Reply-To: <CA%2B1FSijtT_270sOcaqwkA4xrf2mTVpff36vDX%2Bobhx3OoKfMKQ@mail.gmail.com> References: <CAGBxaXmhRLk9Lx_ZHeRdoN-K2fRLEhY3cBVtBymmAjd4bBh1OQ@mail.gmail.com> <CA%2B1FSihQ-f4uhiOjYH8Wo=AxFEkAKe3NRDJdopgT50J=_jY4fA@mail.gmail.com> <CAGBxaXnYojzQJqO62hkzUJvD2rzaNp%2Bem38FgCqVSBu%2BmkBi9A@mail.gmail.com> <CA%2B1FSijpiko%2B%2B%2BwJuXo2GVV6sz3yGVi7ig0X3037%2B1zE3n91hg@mail.gmail.com> <CAGBxaX=OcaHEZk3S7jQeYW64A_iRNTmJ%2Bab4U7h_hsrG%2BQqQPg@mail.gmail.com> <ZEEnZjzDCtR_ZG4P@graf.pompo.net> <CAGBxaXmU=Ja9EkoMyxQ0cNxYB4BeiktqQ3P64QcWg%2B=xijTiyQ@mail.gmail.com> <CA%2B1FSii6OOwi%2B%2Bau-_9ViU_SMZ%2BGbESG5H0McVTHQUwmMnOJGQ@mail.gmail.com> <CAGBxaXkhC--ZppimDFabEwPhesjAJmrziNZm753eoyjy1sWzqg@mail.gmail.com> <CA%2B1FSijsSSpCFeKeaOt4gR36BAZ4J8j4QSJRJa-VF-a=J9e2uw@mail.gmail.com> <CAGBxaXnEajP_NKdgDtreavm1Gz5jyLE8-jQBxM9ALX%2BQ9Cpidw@mail.gmail.com> <CA%2B1FSiiyg8An7HwZrJOd=cKh1%2BNC-FMzgaQNfiHP9fkwpgbAEg@mail.gmail.com> <CAGBxaXmnsAQwfeSjGT4K3M2oNvSTpXYfrErRt3UbMvxpCD4htw@mail.gmail.com> <CA%2B1FSiiLEjNTXg5Nj-mxrV6n64gcSa0DXcu=U6a39Dz2fyQahA@mail.gmail.com> <CAGBxaXnxvU7oKNVO8uZwLhFNQzzVSxkAuTUqWNjwJz_eyYDncA@mail.gmail.com> <CAAdA2WP5_OT3Jge37EzS_p65gM59gpQ7%2By3jhQ3RHfAr-v5SLA@mail.gmail.com> <CA%2B1FSihfyo=mJ0JzKNCRbFO4%2B8VLJKVntLB99T7XbLMzkeugQw@mail.gmail.com> <CAAdA2WM7Zm2fFPaR7PPPN%2BM8ptpGTRPzf%2Bj%2BVxJgfr4Wh3QCPw@mail.gmail.com> <CAGBxaX=8q9Tu0CMqhGYpFZ-wh4Q=_z-vGD3BC0JsQ4anPXFO1Q@mail.gmail.com> <CAAdA2WN=8g_Nh0f73CUKjvWQcDT6uB7GjVi4MzK6=X6jOO-CDg@mail.gmail.com> <CAGBxaXntNiw34qH6b8iGry41rvw0DCt5M93ShS41OBwxR-JwHw@mail.gmail.com> <CA%2B1FSijqpRHe3oWrfdTufzVSh6aFUPGQ9GWZ2S=pXQ3xSSTCzQ@mail.gmail.com> <CA%2B1FSij=fVu64p9RQ%2BMf0wNzpXh0Zw8tpix5G8P6AE1NEe1sYw@mail.gmail.com> <CAGBxaXnRWwAoPx-kNQUQSNt3Lf4tuOY59j%2BZTyw5n-QJRm-xkw@mail.gmail.com> <CA%2B1FSijtT_270sOcaqwkA4xrf2mTVpff36vDX%2Bobhx3OoKfMKQ@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, Apr 22, 2023 at 2:14=E2=80=AFPM Mario Marietto <marietto2008@gmail.= com> wrote: > > I don't know. This should be evaluated by you. I'm not involved so much i= n the technicalities : > > https://github.com/lm-sys/FastChat > > Let me understand what the Ada (117M) model is,if you want. I want to lea= rn. It is basically the smallest conversational model offered by the GPT-2/openAI team. The reason is I see babySpock as being an "corporate AI" (in that it mixes and matches models to get the best results). The primary problem I see with chatGPT (except for the cost for using it at the API level, ran up $25 bill in 2 days of just testing and developing babySpock against their API... this is financially unsustainable so I have to move it in house) is that due to its inability to mix and match context(s) [and the web ui to chatGPT having total context length limits] in order to give it a broad perspective of how I work and think (i.e. what "irrelevent" context to filter out but still get a reasonable reply)... I am planning to use the Ada model as a "cognitive CPU" in the production version babySpock and have a "OS tape" constantly looping through it.. the reason of course is the models are one shot affairs and are stateless between calls (i.e. needs external context) and thus if I was to have a cognitive layer for doing the context assembly I would need a stateful "cognitive OS" to do it on.... I have some semi-FOSS (BSD licensed but not 100% free) business ideas on how to scale this but the business philosophy here is not in the scope of a technical discussion unless you want to know and I will send some stuff privately. --=20 Aryeh M. Friedman, Lead Developer, http://www.PetiteCloud.org
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAGBxaXkY0DD_0KCfzxPwQfGAoS=4imOmVVN-0oNCpr%2BcOVWmbQ>