jeans/home-assistant.io
jeans/home-assistant.io
1
0
Fork 0
mirror of https://github.com/home-assistant/home-assistant.io.git synced 2025-07-20 15:56:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update release notes with additional detail on Ollama tools (#34142)

Browse Source
This commit is contained in:
Allen Porter 2024-08-06 06:30:18 -07:00 committed by GitHub
parent 2802630087
commit 65f54ae98e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
source/_posts/2024-08-07-release-20248.markdown
View File

@ -230,12 +230,13 @@ This is achieved thanks to [@Shulyaka] adding support for the brand new tools
API in Ollama. The performance of the local models has been fine tuned by
[@AllenPorter].
Allen created a new LLM benchmark suite that is more balanced and less focused
on the edge cases. We scored the different models with this new benchmark.
Allen created a new [LLM benchmark suite](https://github.com/allenporter/home-assistant-datasets/tree/main/reports#assist-mini) that is more balanced and less focused
on the edge cases and uses fewer exposed entities. We scored the different
models with this new benchmark.
The cloud-based models scored 98% on this new benchmark while local LLMs did
not do so well. Through prompt tuning and fixes included in this release,
we have been able to now get local LLMs to be able to score a reasonable 81%.
we have been able to now get local LLMs to be able to score a reasonable 83%.
<img class="no-shadow" src="/images/blog/2024-08/llama-3.1-iteration.png" alt="Graph showing the iteration progress of implementing local Ollama support using the Llama 3.1 8B model.">
@ -243,9 +244,8 @@ We will continue to work on testing new models and improving our prompts
and tools to achieve a higher score.
If you like to experiment with local LLMs using Home Assistant, we currently
recommend using the Llama 3.1 8B model.
_TODO: Verify numbers in this text_
recommend using the Llama 3.1 8B model and exposing fewer than 25 entities. Note
that smaller models are more likely to make mistakes.
[@AllenPorter]: https://github.com/AllenPorter
[@Shulyaka]: https://github.com/Shulyaka