Update README.md

README.md

@@ -1,59 +1,65 @@
 ---
-base_model: microsoft/Phi-4-mini-reasoning
+license: mpl-2.0
 library_name: transformers
-model_name: HomePhi4_4B
 tags:
-- generated_from_trainer
-- sft
-- hf_jobs
-- trl
-licence: license
+- home-assistant
+- phi-4
+- iot
+- function-calling
+- smart-home
+- conversational
+base_model: microsoft/Phi-4-mini-reasoning
+datasets:
+- acon96/Home-Assistant-Requests
+language:
+- en
+pipeline_tag: text-generation
 ---
 
-# Model Card for HomePhi4_4B
+# TitleOS/HomePhi4_4B
 
-This model is a fine-tuned version of [microsoft/Phi-4-mini-reasoning](https://huggingface.co/microsoft/Phi-4-mini-reasoning).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+![Model Icon](https://img.shields.io/badge/Home%20Assistant-Compatible-41BDF5) ![Phi-4](https://img.shields.io/badge/Base-Phi%204%20Mini-blue)
 
-## Quick start
+**HomePhi4_4B** is a fine-tuned version of Microsoft's [Phi-4 Mini](https://huggingface.co/microsoft/Phi-4-mini-instruct) (3.8B parameters), specifically optimized for controlling **Home Assistant** instances via natural language.
 
-```python
-from transformers import pipeline
+It has been fine-tuned on the [acon96/Home-Assistant-Requests](https://huggingface.co/datasets/acon96/Home-Assistant-Requests) dataset to excel at interpreting user intent and generating accurate JSON function calls to control smart home devices (lights, fans, switches, etc.). This model is designed to be small enough to run locally on edge hardware (like an N100 or Raspberry Pi 5 with 8GB RAM) while maintaining high reasoning capabilities.
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="TitleOS/HomePhi4_4B", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
+## Model Details
 
-## Training procedure
+- **Model Architecture:** Phi-4 Mini (Dense Decoder-only Transformer)
+- **Parameters:** ~3.8 Billion
+- **Context Length:** 128k tokens (Effective fine-tuning context: ~4096)
+- **Base Model:** `microsoft/Phi-4-mini-instruct`
+- **Fine-tuning Dataset:** `acon96/Home-Assistant-Requests`
+- **License:** MPL-2.0
 
- 
+## Intended Use
 
+This model is strictly intended for **local smart home control**. It acts as a natural language interface for Home Assistant, translating requests like "Turn off the kitchen lights" into structured JSON commands that Home Assistant integrations (like `llama_conversation` or `Extended OpenAI Conversation`) can execute.
 
-This model was trained with SFT.
+It is **not** a general-purpose assistant and may hallucinate if asked about history, math, or coding outside the scope of home automation.
 
-### Framework versions
+## Prompt Format
 
-- TRL: 0.25.1
-- Transformers: 4.57.3
-- Pytorch: 2.9.1
-- Datasets: 4.4.1
-- Tokenizers: 0.22.1
+To get the best performance, you must adhere to the prompt format used during training. The model expects a system prompt that defines its persona and lists the available devices and tools.
 
-## Citations
+**System Prompt Template:**
+```text
+I want you to act as smart home expert manager of Home Assistant.
 
+Current Time: {{now()}}
 
-
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```
+Available Devices:
+```csv
+entity_id,name,state,aliases
+{% for entity in exposed_entities -%}
+{{ entity.entity_id }},{{ entity.name }},{{ entity.state }},{{entity.aliases | join('/')}}
+{% endfor -%}
+```
+You have access to the internet and other tools.
+The current state of devices is provided in available devices.
+Use execute_services function only for requested action, not for current states.
+Do not execute service without user's confirmation.
+Do not restate or appreciate what user says, rather make a quick inquiry.
+In addition, answer questions about the world, news, and general knowledge when requested. If requested by the user your name is AI.
+If a request appears to be an accident or otherwise doesn't make sense, reply with "Canceled".