Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
license: apache-2.0
|
4 |
+
tags:
|
5 |
+
- text-generation
|
6 |
+
- home-assistant
|
7 |
+
- voice-assistant
|
8 |
+
pipeline_tag: text-generation
|
9 |
+
---
|
10 |
+
|
11 |
+
# 🏠 TinyLLaMA-1.1B Home Assistant Voice Model
|
12 |
+
|
13 |
+
This model is a **fine-tuned version** of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0), trained with [acon96/Home-Assistant-Requests](https://huggingface.co/datasets/acon96/Home-Assistant-Requests).
|
14 |
+
It is designed to act as a **voice-controlled smart home assistant** that takes natural language instructions and outputs **Home Assistant commands**.
|
15 |
+
|
16 |
+
---
|
17 |
+
|
18 |
+
## ✨ Features
|
19 |
+
- Converts **natural language voice commands** into Home Assistant automation calls.
|
20 |
+
- Produces **friendly confirmations** and **structured JSON service commands**.
|
21 |
+
- Lightweight (1.1B parameters) – runs efficiently on CPUs, GPUs, and via **Ollama** with quantization.
|
22 |
+
|
23 |
+
---
|
24 |
+
|
25 |
+
## 🔧 Example Usage (Transformers)
|
26 |
+
|
27 |
+
```python
|
28 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
29 |
+
|
30 |
+
tokenizer = AutoTokenizer.from_pretrained("premrajreddy/tinyllama-1.1b-home-llm")
|
31 |
+
model = AutoModelForCausalLM.from_pretrained("premrajreddy/tinyllama-1.1b-home-llm")
|
32 |
+
|
33 |
+
query = "turn on the kitchen lights"
|
34 |
+
inputs = tokenizer(query, return_tensors="pt")
|
35 |
+
outputs = model.generate(**inputs, max_new_tokens=80)
|
36 |
+
|
37 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|