This model was created for an XDA article to demonstrate fine-tuning and the capabilities of the Lenovo ThinkStation PGX. It uses acon96's Home Assistant requests dataset with a second stage fine-tuning pipeline containing synthesized conversation outputs of automations collected from the Home Assistant documentation.

This model is distributed as standard GGUFs, and was tested in llama.cpp.

Downloads last month
188
GGUF
Model size
8B params
Architecture
qwen2
Hardware compatibility
Log In to add your hardware

4-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AdamConway/Qwen2.5-Coder-7B-Instruct-Home-Assistant

Base model

Qwen/Qwen2.5-7B
Quantized
(165)
this model

Dataset used to train AdamConway/Qwen2.5-Coder-7B-Instruct-Home-Assistant