Hi All. New version:
- it is possible to perform dataset creation in multi-threaded mode, see point 18 - parameter -h, use for issuing brief information about llm usage, see point 19 - two bugs fixed: one minor && one major, see point 20 You may find the new version there: gussev/llm: <https://gitverse.ru/gussev/llm> Thank you. вторник, 22 апреля 2025 г. в 20:00:56 UTC+3, alex-coder: > Hi All. > > New version. > Now it is possible not only to add or delete number of sequences by your > choice but also to defragment and free occupied disk space. > You may find the new version there: > gussev/llm: <https://gitverse.ru/gussev/llm> > > Thank you. > четверг, 20 марта 2025 г. в 16:25:49 UTC+3, alex-coder: > >> Hi All. >> >> New version. >> 1. cache, now soft could use cached files to speed up work >> 2.soft has got an option to update data set for the llm located in files. >> To Add and To remove sequences . Defragmentation will be added to one of >> the nearest versions. >> >> You may take the next version there: >> gussev/llm: <https://gitverse.ru/gussev/llm> >> >> Thanks all of you. >> >> суббота, 1 марта 2025 г. в 02:19:24 UTC+3, Rodrick Brown: >> >>> Utter trash this has nothing to do with large language models what is >>> your goal here what are you trying to accomplish? Why post a zip file on >>> github with binaries ? >>> >>> On Fri, Feb 28, 2025 at 10:58 AM cpu...@gmail.com <cpu...@gmail.com> >>> wrote: >>> >>>> Zip files are impossible to reason about on Github and a potential >>>> security thread. I'd not even try to find out what might be inside... >>>> >>>> On Tuesday, February 18, 2025 at 1:40:43 PM UTC+1 alex-coder wrote: >>>> >>>>> Hi All, >>>>> >>>>> I was given a shelter there: >>>>> gussev/llm: <https://gitverse.ru/gussev/llm> >>>>> >>>>> In case someone is in interest of course. :-) >>>>> >>>>> Thank you. >>>>> >>>>> вторник, 28 января 2025 г. в 19:45:53 UTC+3, alex-coder: >>>>> >>>>>> Hi All ! >>>>>> Recently I have made a step towards to the first letter in LLM >>>>>> abbreviation - Large. That means that soft now could work with LLM data >>>>>> model is located in file system and only take into RAM data which one is >>>>>> necessary to compute result. >>>>>> But unfortunately so far I'm not able to pass 2FA to deploy newest >>>>>> version. :-) >>>>>> So, in case someone is in interest drop me a message I'll send you a >>>>>> new version. >>>>>> News: >>>>>> file config. There are added two parameters: >>>>>> 1. "store" has two options "ram" and "file", tells to the llm where >>>>>> to keep data model in ram or in a file system. >>>>>> 2. "capacity" - the maximum size for each of the files where llm >>>>>> would keep information for the data model. >>>>>> memo: default file size would be 16384 but in reality the file size >>>>>> will be 3 times more, do not be afraid, this is my fault. >>>>>> >>>>>> Thank you. >>>>>> >>>>>> ps. in case I will not be able to pass a 2FA for github.com I have >>>>>> to find another place to deploy my page. :-) Thank you again. >>>>>> >>>>> -- >>>> >>> You received this message because you are subscribed to the Google >>>> Groups "golang-nuts" group. >>>> To unsubscribe from this group and stop receiving emails from it, send >>>> an email to golang-nuts...@googlegroups.com. >>>> >>> To view this discussion visit >>>> https://groups.google.com/d/msgid/golang-nuts/cb3c3294-f881-44ed-92c8-db32272dc98an%40googlegroups.com >>>> >>>> <https://groups.google.com/d/msgid/golang-nuts/cb3c3294-f881-44ed-92c8-db32272dc98an%40googlegroups.com?utm_medium=email&utm_source=footer> >>>> . >>>> >>> -- You received this message because you are subscribed to the Google Groups "golang-nuts" group. To unsubscribe from this group and stop receiving emails from it, send an email to golang-nuts+unsubscr...@googlegroups.com. To view this discussion visit https://groups.google.com/d/msgid/golang-nuts/2a5d5137-5ab5-4c33-b592-381ae866b787n%40googlegroups.com.
