Update README.md

README.md

@@ -1,69 +1,30 @@
 ---
 license: apache-2.0
 tags:
-- transformers
-- pytorch
-- causal-lm
-- smart-home
+- gguf
+- llama.cpp
+- qwen
+- llama
+- gemma
+- phi
+- smollm
+- quantized
+- edge-ai
 - iot
-- finetuned
-- qlora
-- unsloth
-language:
-- en
----
-
-#  SmartTalk IoT Model (Fine-Tuned LLM)
-
-## Model Name
-SmartTalk - Lightweight Smart Home Assistant
-
----
-
-##  Models Description
-
-This model is a fine-tuned lightweight causal language model designed for **smart-home IoT control tasks**.
-
-It can understand natural language commands and convert them into structured smart-home actions such as:
-
-- turning lights on/off
-- adjusting brightness
-- activating modes (movie, sleep, morning)
-- controlling home appliances
-
----
-
-##  Model Type
-
-- Base Model: `YOUR_BASE_MODEL_NAME` (e.g., Yi-1.5-6B / Qwen / LLaMA)
-- Fine-tuning Method: QLoRA / LoRA / Full Fine-tune
-- Precision: FP16
-- Framework: Hugging Face Transformers + PyTorch
-
----
-
-##  Training Details
-
-- Dataset: Smart home command dataset (custom / synthetic / real-world IoT commands)
-- Samples: 100k examples
-- Epochs: 2
-
+- smart-home
+- llm
+- inference
 ---
 
-##  Example Usage
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model_id = "YOUR_USERNAME/YOUR_MODEL_NAME"
-
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
+#  Lightweight GGUF LLM Collection (Edge AI / IoT Ready)
 
-prompt = "turn on bedroom light"
+##  Overview
 
-inputs = tokenizer(prompt, return_tensors="pt")
+This repository contains a collection of **quantized GGUF models** optimized for **edge devices, CPU inference, and IoT applications**.
 
-outputs = model.generate(**inputs, max_new_tokens=50)
+These models are designed for:
+- Smart home assistants
+- Lightweight chat systems
+- Offline inference
+- Jetson / Raspberry Pi / CPU-only environments
 
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))