feat: more embedded models, coqui fixes, add model usage and description #1556
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 ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
|
I'd like to have an example for each backend in the one-click setup section, and update the docs while at it, as we miss several backends entirely |
mudler
changed the title
|
I've tried coqui and added a fix for it in this PR (#1549). Will follow-up an e2e example as well. |
|
examples missing for:
|
truecharts-admin
referenced
this pull request
in truecharts/public
Jan 8, 2024
….0 by renovate (#17044) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [docker.io/localai/localai](https://github.com/mudler/LocalAI) | minor | `v2.4.1-cublas-cuda11-ffmpeg-core` -> `v2.5.0-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> ### [`v2.5.0`](https://github.com/mudler/LocalAI/releases/tag/v2.5.0) [Compare Source](https://github.com/mudler/LocalAI/compare/v2.4.1...v2.5.0) <!-- Release notes generated using configuration in .github/release.yml at master --> ##### What's Changed This release adds more embedded models, and shrink image sizes. You can run now `phi-2` ( see [here](https://localai.io/basics/getting_started/#running-popular-models-one-click) for the full list ) locally by starting localai with: docker run -ti -p 8080:8080 localai/localai:v2.5.0-ffmpeg-core phi-2 LocalAI accepts now as argument a list of short-hands models and/or URLs pointing to valid yaml file. A popular way to host those files are Github gists. For instance, you can run `llava`, by starting `local-ai` with: ```bash docker run -ti -p 8080:8080 localai/localai:v2.5.0-ffmpeg-core https://raw.githubusercontent.com/mudler/LocalAI/master/embedded/models/llava.yaml ``` ##### Exciting New Features 🎉 - feat: more embedded models, coqui fixes, add model usage and description by [@​mudler](https://github.com/mudler) in [https://github.com/mudler/LocalAI/pull/1556](https://github.com/mudler/LocalAI/pull/1556) ##### 👒 Dependencies - deps(conda): use transformers-env with vllm,exllama(2) by [@​mudler](https://github.com/mudler) in [https://github.com/mudler/LocalAI/pull/1554](https://github.com/mudler/LocalAI/pull/1554) - deps(conda): use transformers environment with autogptq by [@​mudler](https://github.com/mudler) in [https://github.com/mudler/LocalAI/pull/1555](https://github.com/mudler/LocalAI/pull/1555) - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://github.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1558](https://github.com/mudler/LocalAI/pull/1558) ##### Other Changes - ⬆️ Update docs version mudler/LocalAI by [@​localai-bot](https://github.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1557](https://github.com/mudler/LocalAI/pull/1557) **Full Changelog**: mudler/LocalAI@v2.4.1...v2.5.0 </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://github.com/renovatebot/renovate). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzNy4xMjcuMCIsInVwZGF0ZWRJblZlciI6IjM3LjEyNy4wIiwidGFyZ2V0QnJhbmNoIjoibWFzdGVyIn0=-->
GabrielBarzen
referenced
this pull request
in GabrielBarzen/charts
Feb 2, 2024
….0 by renovate (truecharts#17044) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [docker.io/localai/localai](https://github.com/mudler/LocalAI) | minor | `v2.4.1-cublas-cuda11-ffmpeg-core` -> `v2.5.0-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> ### [`v2.5.0`](https://github.com/mudler/LocalAI/releases/tag/v2.5.0) [Compare Source](https://github.com/mudler/LocalAI/compare/v2.4.1...v2.5.0) <!-- Release notes generated using configuration in .github/release.yml at master --> ##### What's Changed This release adds more embedded models, and shrink image sizes. You can run now `phi-2` ( see [here](https://localai.io/basics/getting_started/#running-popular-models-one-click) for the full list ) locally by starting localai with: docker run -ti -p 8080:8080 localai/localai:v2.5.0-ffmpeg-core phi-2 LocalAI accepts now as argument a list of short-hands models and/or URLs pointing to valid yaml file. A popular way to host those files are Github gists. For instance, you can run `llava`, by starting `local-ai` with: ```bash docker run -ti -p 8080:8080 localai/localai:v2.5.0-ffmpeg-core https://raw.githubusercontent.com/mudler/LocalAI/master/embedded/models/llava.yaml ``` ##### Exciting New Features 🎉 - feat: more embedded models, coqui fixes, add model usage and description by [@&truecharts#8203;mudler](https://github.com/mudler) in [https://github.com/mudler/LocalAI/pull/1556](https://github.com/mudler/LocalAI/pull/1556) ##### 👒 Dependencies - deps(conda): use transformers-env with vllm,exllama(2) by [@&truecharts#8203;mudler](https://github.com/mudler) in [https://github.com/mudler/LocalAI/pull/1554](https://github.com/mudler/LocalAI/pull/1554) - deps(conda): use transformers environment with autogptq by [@&truecharts#8203;mudler](https://github.com/mudler) in [https://github.com/mudler/LocalAI/pull/1555](https://github.com/mudler/LocalAI/pull/1555) - ⬆️ Update ggerganov/llama.cpp by [@&truecharts#8203;localai-bot](https://github.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1558](https://github.com/mudler/LocalAI/pull/1558) ##### Other Changes - ⬆️ Update docs version mudler/LocalAI by [@&truecharts#8203;localai-bot](https://github.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1557](https://github.com/mudler/LocalAI/pull/1557) **Full Changelog**: mudler/LocalAI@v2.4.1...v2.5.0 </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://github.com/renovatebot/renovate). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzNy4xMjcuMCIsInVwZGF0ZWRJblZlciI6IjM3LjEyNy4wIiwidGFyZ2V0QnJhbmNoIjoibWFzdGVyIn0=-->
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.
Description
This PR adds whisper, embeddings, and tts to the one-click install. I still need to test all of them - so it's still in WIP. It removes the hardcoded model gallery, but most importantly it adds a
descriptionandusagefield in the model yamls so it is displayed during the model preloading. This allows for instance to inform the user on how a specific model which is loaded is meant to be used.As not-related, improves UX and output when trying to connect to backend services. It also fixes #1549
Tested embedded models configs:
Testing with, for example:
usage example is printed out during start