feat: embedded model configurations, add popular model examples, refactoring #1532
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
✅ Deploy Preview for localai canceled.
|
mudler
commented
Jan 4, 2024
|
|
||
| | Model | Docker command | | ||
| | --- | --- | | ||
| | phi-2 | ```docker run -p 8080:8080 -ti --rm quay.io/go-skynet/local-ai:{{< version >}}-cublas-cuda11-core phi-2``` | |
There was a problem hiding this comment.
thinking again, better to have maybe llama-cpp-phi-2, vllm-phi-2, etc..
mudler
force-pushed
the
docs_update
branch
2 times, most recently
from
7a4eec1 to
99598a7
Compare
mudler
changed the title
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
mudler
commented
Jan 5, 2024
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
mudler
changed the title
mudler
changed the title
mudler
changed the title
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
truecharts-admin
referenced
this pull request
in truecharts/public
Jan 8, 2024
….1 by renovate (#16987) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | patch | `v2.4.0-cublas-cuda11-ffmpeg-core` -> `v2.4.1-cublas-cuda11-ffmpeg-core` | --- > [!WARNING] > Some dependencies could not be looked up. Check the Dependency Dashboard for more information. --- ### Release Notes <details> <summary>mudler/LocalAI (docker.io/localai/localai)</summary> ### [`v2.4.1`](https://togithub.com/mudler/LocalAI/releases/tag/v2.4.1) [Compare Source](https://togithub.com/mudler/LocalAI/compare/v2.4.0...v2.4.1) <!-- Release notes generated using configuration in .github/release.yml at master --> ##### What's Changed ##### Exciting New Features 🎉 - feat: embedded model configurations, add popular model examples, refactoring by [@​mudler](https://togithub.com/mudler) in [https://github.com/mudler/LocalAI/pull/1532](https://togithub.com/mudler/LocalAI/pull/1532) ##### Other Changes - ⬆️ Update docs version mudler/LocalAI by [@​localai-bot](https://togithub.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1546](https://togithub.com/mudler/LocalAI/pull/1546) - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1547](https://togithub.com/mudler/LocalAI/pull/1547) - docs: improve getting started by [@​mudler](https://togithub.com/mudler) in [https://github.com/mudler/LocalAI/pull/1553](https://togithub.com/mudler/LocalAI/pull/1553) **Full Changelog**: mudler/LocalAI@v2.4.0...v2.4.1 </details> --- ### Configuration 📅 **Schedule**: Branch creation - "before 10pm on monday" in timezone Europe/Amsterdam, Automerge - At any time (no schedule defined). 🚦 **Automerge**: Enabled. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about this update again. --- - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://togithub.com/renovatebot/renovate). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzNy4xMjYuMiIsInVwZGF0ZWRJblZlciI6IjM3LjEyNi4yIiwidGFyZ2V0QnJhbmNoIjoibWFzdGVyIn0=-->
GabrielBarzen
referenced
this pull request
in GabrielBarzen/charts
Feb 2, 2024
….1 by renovate (truecharts#16987) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | patch | `v2.4.0-cublas-cuda11-ffmpeg-core` -> `v2.4.1-cublas-cuda11-ffmpeg-core` | --- > [!WARNING] > Some dependencies could not be looked up. Check the Dependency Dashboard for more information. --- ### Release Notes <details> <summary>mudler/LocalAI (docker.io/localai/localai)</summary> ### [`v2.4.1`](https://togithub.com/mudler/LocalAI/releases/tag/v2.4.1) [Compare Source](https://togithub.com/mudler/LocalAI/compare/v2.4.0...v2.4.1) <!-- Release notes generated using configuration in .github/release.yml at master --> ##### What's Changed ##### Exciting New Features 🎉 - feat: embedded model configurations, add popular model examples, refactoring by [@&truecharts#8203;mudler](https://togithub.com/mudler) in [https://github.com/mudler/LocalAI/pull/1532](https://togithub.com/mudler/LocalAI/pull/1532) ##### Other Changes - ⬆️ Update docs version mudler/LocalAI by [@&truecharts#8203;localai-bot](https://togithub.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1546](https://togithub.com/mudler/LocalAI/pull/1546) - ⬆️ Update ggerganov/llama.cpp by [@&truecharts#8203;localai-bot](https://togithub.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1547](https://togithub.com/mudler/LocalAI/pull/1547) - docs: improve getting started by [@&truecharts#8203;mudler](https://togithub.com/mudler) in [https://github.com/mudler/LocalAI/pull/1553](https://togithub.com/mudler/LocalAI/pull/1553) **Full Changelog**: mudler/LocalAI@v2.4.0...v2.4.1 </details> --- ### Configuration 📅 **Schedule**: Branch creation - "before 10pm on monday" in timezone Europe/Amsterdam, Automerge - At any time (no schedule defined). 🚦 **Automerge**: Enabled. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about this update again. --- - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://togithub.com/renovatebot/renovate). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzNy4xMjYuMiIsInVwZGF0ZWRJblZlciI6IjM3LjEyNi4yIiwidGFyZ2V0QnJhbmNoIjoibWFzdGVyIn0=-->
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This adds docs around the setups by sharing URL and shorthands in the code (hardcoded for now) plus adds embedded model configs directly from the code.
It also re-adds back #1522 that was missed in #1506In the
embedded/models/are defined all the yaml config files that can be run via arg command line directly by callinglocal-ai <model-file>. For instance, runninglocal-ai llavanow automatically sets up llava from theembedded/models/llava.yamlfile, likewise, specifying a mapping in theembedded/model_library.yamlfile will map a short-hand model to a full URL as already supported by #1522Refactors the downloader code into its own package, and creates a new
embeddedpackage that allows to embed model YAML configuration file directly from the source. I've added llava and mistral for now, but planning to add popular models as well with an easy "one click" UX experience.It is also retouching a bit some part of the docs, tangentially related to #1416
Todo: instead of hardcoding urls would be nicer to embed the files directly during build timeThis is done nowNot really related to the change, this PR introduces few optimizations to the CI: