Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
syntaxing
10 days ago
|
parent
|
context
|
favorite
| on:
FunctionGemma 270M Model
I’ve been wanting to fine tune models for home assistant but unsure how to get some synthetic data, any recommendations?
allenporter
9 days ago
|
next
[–]
Check out the approach here:
https://github.com/allenporter/home-assistant-datasets
and the reports/ directory has a leaderboard for function calling. I'm curious to see how well this model does.
reply
syntaxing
9 days ago
|
parent
|
next
[–]
Oh nice, I thought about doing something Ng similar with a docker image and fake devices but never got around to it
reply
wds
9 days ago
|
prev
[–]
I've found this dataset specifically for Home Assistant with over 32k examples:
https://huggingface.co/datasets/acon96/Home-Assistant-Reques...
reply
syntaxing
9 days ago
|
parent
[–]
Funnily, I did fine tune Qwen 1.7B with this but learned this dataset is meant for the authors extension homeLLM
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: