me/env-ansible
1
1 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • caf60d1ccd i3, fix comment since i3 config only allows comments at the start of the line. me 2026-10-17 11:46:12 -07:00
  • f17b6a96b2 swap-stopper, only restart ollama. me 2026-10-17 09:11:08 -07:00
  • c8f32b917f llm, try mounting user's Code directory in the Open WebUI container. me 2026-10-17 08:47:16 -07:00
  • e5891a72c6 system, shorten the runit success sleep. me 2026-10-17 08:42:39 -07:00
  • b1ebe20874 llm, leave the rm of the docker container to the explicit commands, rather than also expecting run to take care of it. me 2026-10-17 08:42:24 -07:00
  • 1746d7f11a system, adjust finish script to sleep on success too, just for a shorter time. me 2026-10-17 08:19:46 -07:00
  • 90ecb842d3 system, add runit sleep script. me 2026-10-17 08:18:29 -07:00
  • be53012c48 llm, adjust some more parameters and try reducing complexity of qwen config a bit to see if that's why it's stopped working decently, move runit script to system.. me 2026-10-17 08:18:18 -07:00
  • c709930bf0 llm, add model section back to qwen settings in case that's why it's freaking out. me 2026-10-16 17:47:50 -07:00
  • 7e0df2ee13 llm, remove model section from qwen settings. me 2026-10-16 11:52:09 -07:00
  • 6a446a8383 llm, handle max_tokens a little more dynamically, likely only affects the smaller models. me 2026-10-16 09:46:46 -07:00
  • bedfbe566d rc, add shortcut to restart a service then immediately follow its log. me 2026-10-16 09:37:54 -07:00
  • 629f7c424d llm, add the actual context values rather than rounding down. me 2026-10-16 09:34:08 -07:00
  • 0a0b85e66d llm, increase context as to not hinder models from achieving their intended abilities. Keep max_tokens limited where applicable. me 2026-10-16 09:23:58 -07:00
  • 2706011fa0 llm, add moe tag to a few more model provider names. me 2026-10-16 09:10:06 -07:00
  • 669095e7cb llm, add more memorable aliases for the fancy ollama show loop. me 2026-10-16 09:08:47 -07:00
  • 13f20a4e98 packages, add a shell_check, AUR tasks need to be changed similar to android.yml where it echoes what was truly done so we know if it is OK, CHANGED, FAILED, etc. me 2026-10-16 09:01:29 -07:00
  • cab2013a97 packages, add English and Spanish dictionaries for workstations. me 2026-10-16 08:53:16 -07:00
  • 8ed0aca797 llm, add a temperature for qwen code providers. me 2026-10-16 07:54:34 -07:00
  • 79d6f53424 llm, add additional qwen code config to help tame the models. me 2026-10-15 18:01:02 -07:00
  • 79a8c32584 llm, add longer tineout for qwen, add a few more documentation links. me 2026-10-15 17:28:13 -07:00
  • 0f4fe291b2 llm, edit provider suffixes. me 2026-10-15 12:07:56 -07:00
  • 490df1e24c llm, use underscores for model names in qwen, not spaces. me 2026-10-14 11:27:42 -07:00
  • b26ead5577 llm, fix extra space in provider name. me 2026-10-14 11:05:34 -07:00
  • bcf2a5aee6 llm, make the qwen drop-down more readable. me 2026-10-14 10:32:28 -07:00
  • 98b9691e1e llm, add comment for nemo. me 2026-10-14 10:28:09 -07:00
  • 62306f886e llm, re-reverse the qwen prefix logic. me 2026-10-14 10:24:41 -07:00
  • 03d0978a64 llm, add sleepy finishes to each service, further edit facts, fix qwen config file and add validator task, move non-ollama web services to non-critical check, start refactoring shell functions, make all context 3200 so programs don;t have to restart the models. me 2026-10-14 10:23:03 -07:00
  • f3632fa13a llm, add a few more aliases for model purge closer to pull-models (the one used to download them). me 2026-10-14 07:29:55 -07:00
  • f828e0a9f2 llm, fix the port checking for open-webui. me 2026-10-14 07:27:58 -07:00
  • 852b904dd4 llm, large refactor on the choices, add a lot of Mistral family models too. me 2026-10-14 07:25:12 -07:00
  • b7738a1b78 lm, add a few more functions, one just a TBD. me 2026-10-14 07:24:45 -07:00
  • 13801d9d86 llm, add missing provisioned var to the print. me 2026-10-14 05:35:55 -07:00
  • 0dc7f258a3 llm, reduce and simplify concurrecy and parallel as to not waste system resources or time. me 2026-10-14 05:34:41 -07:00
  • d20b1b8114 llm, experimented with adding providers to both directories but was not needed, JSON is strict and does not allow trailing commas. me 2026-10-14 04:52:50 -07:00
  • f070896ad3 llm, create the qwen config in both the home and projects directory. me 2026-10-14 04:44:31 -07:00
  • 822140efe6 llm, ensure open-webui check hits the right port. me 2026-10-14 04:04:46 -07:00
  • 231aa8a9a2 llm, add config file for qwen code. me 2026-10-14 03:58:32 -07:00
  • 5e3d162481 llm, more changes to open-webui setup to hopefully get it happy. me 2026-10-14 03:55:23 -07:00
  • eab790c2cc llm, ensure open-webui can see ollama. me 2026-10-13 10:51:14 -07:00
  • 3c04476217 llm, ensure user and root and in docker group in case that's why the port was not being forwarded? Also may allow user to run docker commands without sudo. me 2026-10-13 10:38:33 -07:00
  • e762e1231a llm, ensure the OLLAMA_BASE_URL still gets set. me 2026-10-13 10:22:24 -07:00
  • 44ae9967f1 llm, move links to ollama env documentation. me 2026-10-13 10:21:48 -07:00
  • fe4f23fdb0 i3, don't worry about Telegram. me 2026-10-13 10:11:13 -07:00
  • c213397550 llm, add comment as to why the -p and related commands are not being used. me 2026-10-13 09:58:19 -07:00
  • 951959a00b llm, finalize the open-webui setup, network=host works great, still really unsure why the port mapping was not forwarding correctly. me 2026-10-13 09:54:29 -07:00
  • 9d7a6414b3 swap-stopper, go back to continuing after the restarts are called. me 2026-10-12 12:12:59 -07:00
  • 18b73f7665 swap-stopper, add another process which needs stopped so that it does not keep starting models. me 2026-10-12 12:10:44 -07:00
  • cccd7238cd llm, enable metrics if the version supports it. me 2026-10-12 10:58:55 -07:00
  • 43eff5399c llm, use the default container for open-webui. me 2026-10-12 10:58:35 -07:00
  • 65090d32e8 llm, fix model names for chat and code. me 2026-10-12 10:58:15 -07:00
  • fb692f3766 llm, add a few more ollama env variables as well as set the keep alive to -1 (infinite). me 2026-10-12 10:25:02 -07:00
  • 6ae099fcb1 rc, add shortcut for following a file my favorite way. me 2026-10-12 09:54:55 -07:00
  • 80f5f100f1 llm, add shortcuts for calling chat and code bots. me 2026-10-12 09:52:37 -07:00
  • 7e2dd72fc1 llm, enable checking qwen port. me 2026-10-12 09:52:19 -07:00
  • b3a11dec30 llm, add qwen-code as a daemon, it seems promising, what I was hoping for from zeroclaw. me 2026-10-12 09:43:15 -07:00
  • e8cece4445 provision, add qwen-code to workstation, break LLMs into main and GUI sections. me 2026-10-12 09:42:46 -07:00
  • 0e10bc235f i3, also require mod for shutdown and restart to prevent colliding with shortcuts on other programs. me 2026-10-12 09:13:02 -07:00
  • 883ad223c2 llm, further simplify the pull-llm function so that it never exits prematurely or kills the terminal session. me 2026-10-12 08:40:07 -07:00
  • 9dee72820b llm, print the pull command in case the command keeps failing and we want to just do it manually. me 2026-10-12 08:15:14 -07:00
  • a3ba5e7a60 llm, try doing pull-models a different way since it's been trhowing weird errors. me 2026-10-12 08:13:40 -07:00
  • d27d759c97 llm, add TBD's for qwen serve, seems like it may be a really useful interface after a little playing, what I was hoping zeroclaw could do. me 2026-10-11 06:04:13 -07:00
  • fe46062be0 swap-stopper, be more robust in the checks by using both ram and swap for checking conditions, lower full percentage from 98 to 95 to avoid edge cases. me 2026-10-11 06:03:18 -07:00
  • a0eae9a7cc llm, make the context consistent across devices. me 2026-10-11 05:06:54 -07:00
  • df0df85d9e llm, use a more distinct number for the context so that ollama ps better gives away how the model is being used. me 2026-10-10 19:46:20 -07:00
  • 5541c8251c qwen3-coder is actually pretty great to chat with in ollama run, very responsive unlike in all the other tools. me 2026-10-10 19:21:02 -07:00
  • 6fc8181272 swap-stopper, prevent restart loops if swap does not go down after it started to rise, also fix log consistency with newlines between loops. me 2026-10-10 19:07:36 -07:00
  • 487f1f46f3 llm, add Swap Stopper as a service based on custom shell script. me 2026-10-10 18:41:50 -07:00
  • 0776e89d26 Add shell script which stops LLMs from causing system swap. me 2026-10-10 18:41:25 -07:00
  • ccd8355946 llm, fix ollama-stop function. me 2026-10-10 17:27:47 -07:00
  • 942780e6d1 Refactor redundant names, do not need to say "Setup". me 2026-10-10 16:48:08 -07:00
  • 019066c4dc llm, further reduce contexts based on testing, now using 2.5:14b for Complete successfully alongside the RAM needs of 3:30b on Cline. me 2026-10-10 16:42:19 -07:00
  • 1f16053042 llm, continue tuning the model context and tokens to prevent swapping. me 2026-10-10 16:04:09 -07:00
  • bafa669bb5 Update spacing in main YML files. me 2026-10-10 15:59:38 -07:00
  • 5595ea0888 test, add comment, add names to tasks. me 2026-10-10 14:59:12 -07:00
  • 3aee0feb39 footer, name tasks and add comment. me 2026-10-10 14:56:08 -07:00
  • 5d352bbb53 llm, add section comments, ensure ollama allows Codium workflows with concurrency and parallel. me 2026-10-10 14:32:28 -07:00
  • 6c46439eb6 llm, add shortcuts for stopping all ollama models. me 2026-10-10 13:42:36 -07:00
  • 648501b7c0 llm, use pipefail on the final lint error. me 2026-10-10 13:35:34 -07:00
  • e0288ce4d5 llm, filter models by purpose, use chat in Zeroclaw and code in Continue. me 2026-10-10 13:33:48 -07:00
  • c6cc631d8c llm, tuning the context and token parameters. me 2026-10-10 13:10:29 -07:00
  • 3381eb6d70 loop, output the command before starting the loop, just to make sure all looks okay. me 2026-10-10 12:28:45 -07:00
  • 53351fde28 llm, add a finish for open-webui, fix config.yaml for Continue, possibly fix pull-models causing terminals to close when cancelled. me 2026-10-10 11:12:25 -07:00
  • 7922225b26 Remove unecessary update_cache which eat up time. me 2026-10-10 11:11:15 -07:00
  • d27976150c setup, add option to run test.yml. me 2026-10-10 10:30:00 -07:00
  • 8b73c7ef02 test, create new playbook which takes advantage of header and footer then only calls the specific tasks we want to test. me 2026-10-10 10:29:47 -07:00
  • 69b1e62c82 local, refactor the necessary portions into subfiles header and footer. me 2026-10-10 10:29:17 -07:00
  • 8970b14e31 llm, always do the setup steps, then XYZ_enabled vars are used to disable and stop services not wanted. me 2026-10-10 10:28:45 -07:00
  • 861546236f provision, enable zeroclaw by default, barely takes any resources and can be helpful. me 2026-10-10 10:27:39 -07:00
  • f7389bc944 lint, add another silly "error" about spaces. me 2026-10-10 10:27:15 -07:00
  • c85d96f940 llm, add hugging face token to ollama. me 2026-10-10 09:56:41 -07:00
  • 4ab93d02f4 llm, fix the hugging face token env var for open-webui. me 2026-10-10 09:49:29 -07:00
  • 0feb9b1995 llm, fix filename for continue, add print for llm check, refer to stdout on llm check. me 2026-10-10 04:57:00 -07:00
  • e95054d329 llm, use new variables provisioned for open-webui. me 2026-10-10 04:51:10 -07:00
  • 993eeda08b provision, add two new variables for open-webui. me 2026-10-10 04:50:22 -07:00
  • 5655fe52b0 provision, ensure llm variables do not collide with existing facts. me 2026-10-10 04:20:55 -07:00
  • daec9237f0 llm, finish the open-webui setup, start using the workstation config variables. me 2026-10-10 04:20:28 -07:00
  • a866a6d2e5 sudoers, allow sv commands in i3 config. me 2026-10-10 02:34:42 -07:00
  • 43d92d14ed i3, add system restart and restarting of LLM services. me 2026-10-10 02:32:55 -07:00
  • 0450aa45c3 i3, add smaller stepping for both brightnesses and volume. me 2026-10-10 02:32:32 -07:00