github/home-llm
1
1
Fork 0
mirror of https://github.com/acon96/home-llm.git synced 2026-01-09 13:48:05 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into develop

Browse Source
This commit is contained in:
Alex O'Connell
2024-08-17 13:46:32 -04:00
parent 094e469fd9 6930b6a91e
commit 93b0d8e3a1
1 changed files with 12 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
README.md
View File

@@ -84,6 +84,17 @@ if mary is 7 years old, and I am 3 years older than her. how old am I?<|endoftex
If Mary is 7 years old, then you are 10 years old (7+3=10).<|endoftext|>
```
### Synthetic Dataset
The synthetic dataset is aimed at covering basic day to day operations in home assistant such as turning devices on and off.
The supported entity types are: light, fan, cover, lock, media_player, climate, switch
The dataset is available on HuggingFace: https://huggingface.co/datasets/acon96/Home-Assistant-Requests
The source for the dataset is in the [data](/data) of this repository.
### Training
If you want to prepare your own training environment, see the details on how to do it in the [Training Guide](./docs/Training.md) document.
<details>
<summary>Training Details</summary>
@@ -131,21 +142,6 @@ python3 train.py \
```
</details>
### Synthetic Dataset
The synthetic dataset is aimed at covering basic day to day operations in home assistant such as turning devices on and off.
The supported entity types are: light, fan, cover, lock, media_player, climate, switch
The dataset is available on HuggingFace: https://huggingface.co/datasets/acon96/Home-Assistant-Requests
The source for the dataset is in the [data](/data) of this repository.
### Training
If you want to prepare your own training environment, see the details on how to do it in [Training](./docs/Training.md) document.
The 3B model was trained as a full fine-tuning on 2x RTX 4090 (48GB). Training time took approximately 28 hours. It was trained on the `--large` dataset variant.
The 1B model was trained as a full fine-tuning on an RTX 3090 (24GB). Training took approximately 2 hours. It was trained on the `--medium` dataset variant.
## Home Assistant Addon
In order to facilitate running the project entirely on the system where Home Assistant is installed, there is an experimental Home Assistant Add-on that runs the oobabooga/text-generation-webui to connect to using the "remote" backend options. The addon can be found in the [addon/](./addon/README.md) directory.
@@ -154,6 +150,7 @@ In order to facilitate running the project entirely on the system where Home Ass
## Version History
| Version | Description |
|---------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| v0.3.5 | Fix for llama.cpp backend installation, Fix for Home LLM v1-3 API parameters, add Polish ICL examples |
| v0.3.4 | Significantly improved language support including full Polish translation, Update bundled llama-cpp-python to support new models, various bug fixes |
| v0.3.3 | Improvements to the Generic OpenAI Backend, improved area handling, fix issue using RGB colors, remove EOS token from responses, replace requests dependency with aiohttp included with Home Assistant |
| v0.3.2 | Fix for exposed script entities causing errors, fix missing GBNF error, trim whitespace from model output |