Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix(doc/examples): set defaults to mirostat #1820

Merged
merged 1 commit into from
Mar 11, 2024
Merged

Conversation

mudler
Copy link
Owner

@mudler mudler commented Mar 11, 2024

The default sampler on some models don't return enough candidates which leads to a false sense of randomness. Tracing back the code it looks that with the temperature sampler there might not be enough candidates to pick from, and since the seed and "randomness" take effect while picking a good candidate this yields to the same results over and over.

Fixes #1723 by updating the examples and documentation to use mirostat instead.

The documentation was also wrong: there was a level of indentation that was breaking the configuration read.

Tested locally:

mudler@zz0t ~/_git/LocalAI mirostat_default*
base ❯ curl http://10.8.0.5:32457/v1/chat/completions -H "Content-Type: application/json" -d '{                                                                    
    "model": "phi-2", "messages": [{"role": "user", "content": "Tell me a story about", "temperature": 1}]                                                                                       
}'
{"created":1710182300,"object":"chat.completion","id":"dca52beb-6d9a-4f7b-8f8c-2c0ec4d48943","model":"phi-2","choices":[{"index":0,"finish_reason":"stop","message":{"role":"assistant","content":"Once upon a time, there was a brave knight named Sir William. He was known throughout the kingdom for his courage and skill with a sword.\n\nOne day, the king called Sir William to the castle and told him about a great threat to the kingdom. A fearsome dragon had been terrorizing the nearby villages, breathing fire and destruction wherever it went.\n\nSir William accepted the king's challenge and set off on a quest to find the dragon and put an end to its reign of terror. He traveled through treacherous forests and climbed steep mountains, determined to save the kingdom from the dragon's wrath.\n\nAfter days of searching, Sir William finally came face to face with the dragon. It was a magnificent creature, with scales as black as night and eyes that glowed with a fiery intensity. The dragon breathed a cloud of smoke, engulfing Sir William and the kingdom in darkness.\n\nWith his sword raised high, Sir William confronted the dragon head-on. They engaged in a fierce battle, each strike and parry filled with power and determination. Sir William dodged the dragon's fiery breath and landed a decisive blow, sending the beast crashing to the ground.\n\nWith the dragon defeated, the kingdom erupted in cheers and celebrations. Sir William was hailed as a hero, and the king rewarded him with riches and lands beyond his wildest dreams.\n\nAnd so, Sir William lived happily ever after, his name forever etched in the annals of the kingdom's history.\n\nEnd of story."}}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}
mudler@zz0t ~/_git/LocalAI mirostat_default* 9s
base ❯ curl http://10.8.0.5:32457/v1/chat/completions -H "Content-Type: application/json" -d '{                                                                    
    "model": "phi-2", "messages": [{"role": "user", "content": "Tell me a story about", "temperature": 1}]                                                                                       
}'
{"created":1710182300,"object":"chat.completion","id":"dca52beb-6d9a-4f7b-8f8c-2c0ec4d48943","model":"phi-2","choices":[{"index":0,"finish_reason":"stop","message":{"role":"assistant","content":"Once upon a time, there was a brave knight who lived in a kingdom far away. He was renowned throughout the kingdom for his courage, kind heart, and clever mind. He spent his days wandering through the lush fields and tall trees, singing to himself and admiring the beauty of nature. One day, while he was traversing the forest, he encountered a magical unicorn. The unicorn was magnificent - with a gleaming white coat, a flowing mane, and a graceful presence. The knight was amazed, and begged the unicorn to grant him a wish. The unicorn smiled and said, \"Your wish is my command. Choose wisely, for once granted, it cannot be taken away.\" The knight thought for a moment, then said, \"I wish for peace and justice to prevail throughout the kingdom, so that all may live in harmony.\" The unicorn nodded, and in an instant, the kingdom was transformed. The people were kinder to one another, the rulers were fair in their judgement, and the land was more prosperous than ever. The knight thanked the unicorn, and rode off into the sunset, knowing that his wish had been granted."}}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}}

name: phi-2
context_size: 2048
f16: false
mmap: false
gpu_layers: 90
trimsuffix: 
- "\n"
parameters:
  model: huggingface://TheBloke/phi-2-GGUF/phi-2.Q8_0.gguf
  temperature: 1.0
  top_k: 40
  top_p: 0.95
  seed: -1
mirostat: 2
mirostat_eta: 1.0
mirostat_tau: 1.0
template:
  chat: &template |-
    Instruct: {{.Input}}
    Output:
  completion: *template

usage: |
      To use this model, interact with the API (in another terminal) with curl for instance:
      curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
          "model": "phi-2",
          "messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
      }'

The default sampler on some models don't return enough candidates which
leads to a false sense of randomness. Tracing back the code it looks
that with the temperature sampler there might not be enough
candidates to pick from, and since the seed and "randomness" take effect
while picking a good candidate this yields to the same results over and
over.

Fixes #1723 by updating the
examples and documentation to use mirostat instead.
Copy link

netlify bot commented Mar 11, 2024

Deploy Preview for localai ready!

Name Link
🔨 Latest commit fa4c582
🔍 Latest deploy log https://app.netlify.com/sites/localai/deploys/65ef520947b7d70008a58cae
😎 Deploy Preview https://deploy-preview-1820--localai.netlify.app
📱 Preview on mobile
Toggle QR Code...

QR Code

Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify site configuration.

@mudler mudler merged commit bc8f648 into master Mar 11, 2024
10 of 11 checks passed
@mudler mudler deleted the mirostat_default branch March 11, 2024 18:49
@mudler mudler added the kind/documentation Improvements or additions to documentation label Mar 14, 2024
truecharts-admin referenced this pull request in truecharts/public Mar 17, 2024
…0.0@5cd0285 by renovate (#19391)

This PR contains the following updates:

| Package | Update | Change |
|---|---|---|
| [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) |
minor | `v2.9.0` -> `v2.10.0` |

---

> [!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>

###
[`v2.10.0`](https://togithub.com/mudler/LocalAI/releases/tag/v2.10.0)

[Compare
Source](https://togithub.com/mudler/LocalAI/compare/v2.9.0...v2.10.0)

##### LocalAI v2.10.0 Release Notes

Excited to announce the release of LocalAI v2.10.0! This version
introduces significant changes, including breaking changes, numerous bug
fixes, exciting new features, dependency updates, and more. Here's a
summary of what's new:

##### Breaking Changes 🛠

- The `trust_remote_code` setting in the YAML config file of the model
are now consumed for enhanced security measures also for the AutoGPTQ
and transformers backend, thanks to
[@&#8203;dave-gray101](https://togithub.com/dave-gray101)'s contribution
([#&#8203;1799](https://togithub.com/mudler/LocalAI/pull/1799)). If your
model relied on the old behavior and you are sure of what you are doing,
set `trust_remote_code: true` in the YAML config file.

##### Bug Fixes 🐛

- Various fixes have been implemented to enhance the stability and
performance of LocalAI:
- SSE no longer omits empty `finish_reason` fields for better
compatibility with the OpenAI API, fixed by
[@&#8203;mudler](https://togithub.com/mudler)
([#&#8203;1745](https://togithub.com/mudler/LocalAI/pull/1745)).
- Functions now correctly handle scenarios with no results, also
addressed by [@&#8203;mudler](https://togithub.com/mudler)
([#&#8203;1758](https://togithub.com/mudler/LocalAI/pull/1758)).
- A Command Injection Vulnerability has been fixed by
[@&#8203;ouxs-19](https://togithub.com/ouxs-19)
([#&#8203;1778](https://togithub.com/mudler/LocalAI/pull/1778)).
- OpenCL-based builds for llama.cpp have been restored, thanks to
[@&#8203;cryptk](https://togithub.com/cryptk)'s efforts
([#&#8203;1828](https://togithub.com/mudler/LocalAI/pull/1828),
[#&#8203;1830](https://togithub.com/mudler/LocalAI/pull/1830)).
- An issue with OSX build `default.metallib` has been resolved, which
should now allow running the llama-cpp backend on Apple arm64, fixed by
[@&#8203;dave-gray101](https://togithub.com/dave-gray101)
([#&#8203;1837](https://togithub.com/mudler/LocalAI/pull/1837)).

##### Exciting New Features 🎉

-   LocalAI continues to evolve with several new features:
- Ongoing implementation of the assistants API, making great progress
thanks to community contributions, including an initial implementation
by [@&#8203;christ66](https://togithub.com/christ66)
([#&#8203;1761](https://togithub.com/mudler/LocalAI/pull/1761)).
- Addition of diffusers/transformers support for Intel GPU - now you can
generate images and use the `transformer` backend also on Intel GPUs,
implemented by [@&#8203;mudler](https://togithub.com/mudler)
([#&#8203;1746](https://togithub.com/mudler/LocalAI/pull/1746)).
- Introduction of Bitsandbytes quantization for transformer backend
enhancement and a fix for transformer backend error on CUDA by
[@&#8203;fakezeta](https://togithub.com/fakezeta)
([#&#8203;1823](https://togithub.com/mudler/LocalAI/pull/1823)).
- Compatibility layers for Elevenlabs and OpenAI TTS, enhancing
text-to-speech capabilities: Now LocalAI is compatible with Elevenlabs
and OpenAI TTS, thanks to [@&#8203;mudler](https://togithub.com/mudler)
([#&#8203;1834](https://togithub.com/mudler/LocalAI/pull/1834)).
- vLLM now supports `stream: true`! This feature was introduced by
[@&#8203;golgeek](https://togithub.com/golgeek)
([#&#8203;1749](https://togithub.com/mudler/LocalAI/pull/1749)).

##### Dependency Updates 👒

- Our continuous effort to keep dependencies up-to-date includes
multiple updates to `ggerganov/llama.cpp`, `donomii/go-rwkv.cpp`,
`mudler/go-stable-diffusion`, and others, ensuring that LocalAI is built
on the latest and most secure libraries.

##### Other Changes

- Several internal changes have been made to improve the development
process and documentation, including updates to integration guides,
stress reduction on self-hosted runners, and more.

#### Details of What's Changed

##### Breaking Changes 🛠

- feat(autogpt/transformers): consume `trust_remote_code` by
[@&#8203;dave-gray101](https://togithub.com/dave-gray101) in
[https://github.com/mudler/LocalAI/pull/1799](https://togithub.com/mudler/LocalAI/pull/1799)

##### Bug fixes 🐛

- fix(sse): do not omit empty finish_reason by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1745](https://togithub.com/mudler/LocalAI/pull/1745)
- fix(functions): handle correctly when there are no results by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1758](https://togithub.com/mudler/LocalAI/pull/1758)
- fix(tests): re-enable tests after code move by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1764](https://togithub.com/mudler/LocalAI/pull/1764)
- Fix Command Injection Vulnerability by
[@&#8203;ouxs-19](https://togithub.com/ouxs-19) in
[https://github.com/mudler/LocalAI/pull/1778](https://togithub.com/mudler/LocalAI/pull/1778)
- fix: the correct BUILD_TYPE for OpenCL is clblas (with no t) by
[@&#8203;cryptk](https://togithub.com/cryptk) in
[https://github.com/mudler/LocalAI/pull/1828](https://togithub.com/mudler/LocalAI/pull/1828)
- fix: missing OpenCL libraries from docker containers during clblas
docker build by [@&#8203;cryptk](https://togithub.com/cryptk) in
[https://github.com/mudler/LocalAI/pull/1830](https://togithub.com/mudler/LocalAI/pull/1830)
- fix: osx build default.metallib by
[@&#8203;dave-gray101](https://togithub.com/dave-gray101) in
[https://github.com/mudler/LocalAI/pull/1837](https://togithub.com/mudler/LocalAI/pull/1837)

##### Exciting New Features 🎉

- fix: vllm - use AsyncLLMEngine to allow true streaming mode by
[@&#8203;golgeek](https://togithub.com/golgeek) in
[https://github.com/mudler/LocalAI/pull/1749](https://togithub.com/mudler/LocalAI/pull/1749)
- refactor: move remaining api packages to core by
[@&#8203;dave-gray101](https://togithub.com/dave-gray101) in
[https://github.com/mudler/LocalAI/pull/1731](https://togithub.com/mudler/LocalAI/pull/1731)
- Bump vLLM version + more options when loading models in vLLM by
[@&#8203;golgeek](https://togithub.com/golgeek) in
[https://github.com/mudler/LocalAI/pull/1782](https://togithub.com/mudler/LocalAI/pull/1782)
- feat(assistant): Initial implementation of assistants api by
[@&#8203;christ66](https://togithub.com/christ66) in
[https://github.com/mudler/LocalAI/pull/1761](https://togithub.com/mudler/LocalAI/pull/1761)
- feat(intel): add diffusers/transformers support by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1746](https://togithub.com/mudler/LocalAI/pull/1746)
- fix(config): set better defaults for inferencing by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1822](https://togithub.com/mudler/LocalAI/pull/1822)
- fix(docker-compose): update docker compose file by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1824](https://togithub.com/mudler/LocalAI/pull/1824)
- feat(model-help): display help text in markdown by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1825](https://togithub.com/mudler/LocalAI/pull/1825)
- feat: Add Bitsandbytes quantization for transformer backend
enhancement
[#&#8203;1775](https://togithub.com/mudler/LocalAI/issues/1775) and fix:
Transformer backend error on CUDA
[#&#8203;1774](https://togithub.com/mudler/LocalAI/issues/1774) by
[@&#8203;fakezeta](https://togithub.com/fakezeta) in
[https://github.com/mudler/LocalAI/pull/1823](https://togithub.com/mudler/LocalAI/pull/1823)
- feat(tts): add Elevenlabs and OpenAI TTS compatibility layer by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1834](https://togithub.com/mudler/LocalAI/pull/1834)
- feat(embeddings): do not require to be configured by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1842](https://togithub.com/mudler/LocalAI/pull/1842)

##### 👒 Dependencies

- ⬆️ Update docs version mudler/LocalAI by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1752](https://togithub.com/mudler/LocalAI/pull/1752)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1753](https://togithub.com/mudler/LocalAI/pull/1753)
- deps(llama.cpp): update by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1759](https://togithub.com/mudler/LocalAI/pull/1759)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1756](https://togithub.com/mudler/LocalAI/pull/1756)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1767](https://togithub.com/mudler/LocalAI/pull/1767)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1772](https://togithub.com/mudler/LocalAI/pull/1772)
- ⬆️ Update donomii/go-rwkv.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1771](https://togithub.com/mudler/LocalAI/pull/1771)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1779](https://togithub.com/mudler/LocalAI/pull/1779)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1789](https://togithub.com/mudler/LocalAI/pull/1789)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1791](https://togithub.com/mudler/LocalAI/pull/1791)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1794](https://togithub.com/mudler/LocalAI/pull/1794)
- depedencies(sentencentranformers): update dependencies by
[@&#8203;TwinFinz](https://togithub.com/TwinFinz) in
[https://github.com/mudler/LocalAI/pull/1797](https://togithub.com/mudler/LocalAI/pull/1797)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1801](https://togithub.com/mudler/LocalAI/pull/1801)
- ⬆️ Update mudler/go-stable-diffusion by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1802](https://togithub.com/mudler/LocalAI/pull/1802)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1805](https://togithub.com/mudler/LocalAI/pull/1805)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1811](https://togithub.com/mudler/LocalAI/pull/1811)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1827](https://togithub.com/mudler/LocalAI/pull/1827)

##### Other Changes

- ci: add stablediffusion to release by
[@&#8203;sozercan](https://togithub.com/sozercan) in
[https://github.com/mudler/LocalAI/pull/1757](https://togithub.com/mudler/LocalAI/pull/1757)
- Update integrations.md by
[@&#8203;Joshhua5](https://togithub.com/Joshhua5) in
[https://github.com/mudler/LocalAI/pull/1765](https://togithub.com/mudler/LocalAI/pull/1765)
- ci: reduce stress on self-hosted runners by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1776](https://togithub.com/mudler/LocalAI/pull/1776)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1785](https://togithub.com/mudler/LocalAI/pull/1785)
- Revert "feat(assistant): Initial implementation of assistants api" by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1790](https://togithub.com/mudler/LocalAI/pull/1790)
- Edit links in readme and integrations page by
[@&#8203;lunamidori5](https://togithub.com/lunamidori5) in
[https://github.com/mudler/LocalAI/pull/1796](https://togithub.com/mudler/LocalAI/pull/1796)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1813](https://togithub.com/mudler/LocalAI/pull/1813)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1816](https://togithub.com/mudler/LocalAI/pull/1816)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1818](https://togithub.com/mudler/LocalAI/pull/1818)
- fix(doc/examples): set defaults to mirostat by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1820](https://togithub.com/mudler/LocalAI/pull/1820)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1821](https://togithub.com/mudler/LocalAI/pull/1821)
- fix: OSX Build Files for llama.cpp by
[@&#8203;dave-gray101](https://togithub.com/dave-gray101) in
[https://github.com/mudler/LocalAI/pull/1836](https://togithub.com/mudler/LocalAI/pull/1836)
- ⬆️ Update go-skynet/go-llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1835](https://togithub.com/mudler/LocalAI/pull/1835)
- docs(transformers): add docs section about transformers by
[@&#8203;mudler](https://togithub.com/mudler) in
[https://github.com/mudler/LocalAI/pull/1841](https://togithub.com/mudler/LocalAI/pull/1841)
- ⬆️ Update mudler/go-piper by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1844](https://togithub.com/mudler/LocalAI/pull/1844)
- ⬆️ Update ggerganov/llama.cpp by
[@&#8203;localai-bot](https://togithub.com/localai-bot) in
[https://github.com/mudler/LocalAI/pull/1840](https://togithub.com/mudler/LocalAI/pull/1840)

#### New Contributors

- [@&#8203;golgeek](https://togithub.com/golgeek) made their first
contribution in
[https://github.com/mudler/LocalAI/pull/1749](https://togithub.com/mudler/LocalAI/pull/1749)
- [@&#8203;Joshhua5](https://togithub.com/Joshhua5) made their first
contribution in
[https://github.com/mudler/LocalAI/pull/1765](https://togithub.com/mudler/LocalAI/pull/1765)
- [@&#8203;ouxs-19](https://togithub.com/ouxs-19) made their first
contribution in
[https://github.com/mudler/LocalAI/pull/1778](https://togithub.com/mudler/LocalAI/pull/1778)
- [@&#8203;TwinFinz](https://togithub.com/TwinFinz) made their first
contribution in
[https://github.com/mudler/LocalAI/pull/1797](https://togithub.com/mudler/LocalAI/pull/1797)
- [@&#8203;cryptk](https://togithub.com/cryptk) made their first
contribution in
[https://github.com/mudler/LocalAI/pull/1828](https://togithub.com/mudler/LocalAI/pull/1828)
- [@&#8203;fakezeta](https://togithub.com/fakezeta) made their first
contribution in
[https://github.com/mudler/LocalAI/pull/1823](https://togithub.com/mudler/LocalAI/pull/1823)

Thank you to all contributors and users for your continued support and
feedback, making LocalAI better with each release!

**Full Changelog**:
mudler/LocalAI@v2.9.0...v2.10.0

</details>

---

### Configuration

📅 **Schedule**: Branch creation - At any time (no schedule defined),
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:eyJjcmVhdGVkSW5WZXIiOiIzNy4yNTAuMSIsInVwZGF0ZWRJblZlciI6IjM3LjI1MC4xIiwidGFyZ2V0QnJhbmNoIjoibWFzdGVyIn0=-->
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
kind/documentation Improvements or additions to documentation
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Completion endpoint returns same response repeatedly
1 participant