Update README.md

README.md

@@ -1,50 +1,125 @@
+    
 ---
-base_model: TitleOS/Lightning-1.7B
+language:
+- en
+license: mpl-2.0
+base_model: Qwen/Qwen3-1.7B
 tags:
-- llama-cpp
-- gguf-my-repo
+- lightning
+- hermes-3
+- utility
+- on-device
+- text-generation
+- finetune
+datasets:
+- NousResearch/Hermes-3-Dataset
+pipeline_tag: text-generation
+inference: true
+model_creator: TitleOS
 ---
 
-# TitleOS/Lightning-1.7B-Q8_0-GGUF
-This model was converted to GGUF format from [`TitleOS/Lightning-1.7B`](https://huggingface.co/TitleOS/Lightning-1.7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
-Refer to the [original model card](https://huggingface.co/TitleOS/Lightning-1.7B) for more details on the model.
+# ⚡ Lightning-1.7B
 
-## Use with llama.cpp
-Install llama.cpp through brew (works on Mac and Linux)
+<div align="center">
+  <img src="https://img.shields.io/badge/Model-Lightning--1.7B-blue?style=for-the-badge&logo=huggingface" alt="Model Name">
+  <img src="https://img.shields.io/badge/Base-Qwen3--1.7B-orange?style=for-the-badge" alt="Base Model">
+  <img src="https://img.shields.io/badge/License-MPL_2.0-brightgreen?style=for-the-badge" alt="License">
+</div>
 
-```bash
-brew install llama.cpp
+<br>
 
-```
-Invoke the llama.cpp server or the CLI.
+**Lightning-1.7B** is a high-efficiency utility model designed for edge computing and low-latency workflows. Finetuned from the powerful **Qwen3-1.7B** base upon the rich **NousResearch Hermes-3 dataset**, Lightning serves as a bridge between raw analytic logic and creative inference.
 
-### CLI:
-```bash
-llama-cli --hf-repo TitleOS/Lightning-1.7B-Q8_0-GGUF --hf-file lightning-1.7b-q8_0.gguf -p "The meaning to life and the universe is"
-```
+While it boasts improved capabilities in logic, Q/A, and coding compared to its base, its true strength lies in its **enhanced creativity** and **utility functions**. It is engineered to be the perfect "sidecar" model—small enough to run on-device with minimal memory impact, yet smart enough to handle complex metadata generation tasks.
 
-### Server:
-```bash
-llama-server --hf-repo TitleOS/Lightning-1.7B-Q8_0-GGUF --hf-file lightning-1.7b-q8_0.gguf -c 2048
-```
+## 🚀 Key Features
 
-Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+*   **Ultra-Lightweight:** At 1.7B parameters, it runs efficiently on consumer hardware, laptops, and even mobile devices with minimal VRAM usage.
+*   **Hermes-Powered Creativity:** Leveraging the Hermes-3 dataset, Lightning moves beyond robotic responses, offering nuanced understanding for tasks that require a "human touch," such as summarizing tone or generating creative search queries.
+*   **Utility Specialist:** Specifically optimized for background tasks like tagging, title generation, and creating search inquiries from conversation context.
+*   **Low Latency:** Designed for speed, making it ideal for real-time applications where response time is critical.
 
-Step 1: Clone llama.cpp from GitHub.
-```
-git clone https://github.com/ggerganov/llama.cpp
-```
+## 🎯 Use Cases
 
-Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
-```
-cd llama.cpp && LLAMA_CURL=1 make
-```
+Lightning-1.7B is best utilized not as a general chatbot, but as a specialized **Analytic & Utility Engine**:
 
-Step 3: Run inference through the main binary.
-```
-./llama-cli --hf-repo TitleOS/Lightning-1.7B-Q8_0-GGUF --hf-file lightning-1.7b-q8_0.gguf -p "The meaning to life and the universe is"
-```
-or 
-```
-./llama-server --hf-repo TitleOS/Lightning-1.7B-Q8_0-GGUF --hf-file lightning-1.7b-q8_0.gguf -c 2048
+1.  **Conversation Auto-Titling:** accurately summarizing long context windows into punchy, relevant titles.
+2.  **Search Query Generation:** converting user intent or conversation history into optimized search engine queries.
+3.  **Onboard Tagging:** analyzing text streams to apply metadata tags (e.g., sentiment, topic, urgency) locally without API calls.
+4.  **JSON Formatting:** extracting structured data from unstructured text with higher reliability than standard small models.
+
+## 💻 Quickstart
+
+You can run Lightning-1.7B using the `transformers` library.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "TitleOS/Lightning-1.7B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+# Example: Generating a search query from a user thought
+prompt = """<|im_start|>system
+You are a utility AI. Generate a specific Google search query based on the user's confused thought.<|im_end|>
+<|im_start|>user
+I remember there was this movie about a guy who lives in a computer but doesn't know it, and takes a red pill?<|im_end|>
+<|im_start|>assistant
+"""
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=64,
+    temperature=0.3,
+    do_sample=True
+)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+# Output: "movie guy lives in computer takes red pill matrix plot"
 ```
+
+Merged FP16 and Quantizations:
+
+FP16: https://huggingface.co/TitleOS/Lightning-1.7B
+
+Q4_K_M:https://huggingface.co/TitleOS/Lightning-1.7B-Q4_K_M-GGUF
+
+Q8: https://huggingface.co/TitleOS/Lightning-1.7B-Q8_0-GGUF
+
+📊 Performance & Benchmarks
+
+Lightning-1.7B punches above its weight class. By sacrificing some breadth of general world knowledge found in larger models, it focuses density on instruction following and creative interpretation.
+
+    Logic & Coding: Slight improvement over base Qwen3-1.7B.
+
+    Creativity & Nuance: Significant improvement due to Hermes-3 fine-tuning.
+
+    Memory Footprint: ~3.5GB VRAM (in FP16), <2GB (in 4-bit/8-bit quant).
+
+🔧 Training Details
+
+    Base Model: Qwen3-1.7B
+
+    Dataset: NousResearch/Hermes-3-Dataset
+
+    Fine-tuning Approach: Lora Alpha 32/Lora R 16 focused on preserving the base model's speed while injecting the "Hermes" personality and instruction-following capabilities.
+
+⚠️ Limitations
+
+    Knowledge Cutoff: As a small model, Lightning does not possess vast encyclopedic knowledge. It is best used for processing the text given to it in the context window rather than retrieving facts.
+
+    Complex Reasoning: While logic is improved, multi-step mathematical reasoning or complex coding challenges should be offloaded to larger models (7B+).
+
+📜 License
+
+This model is released under the Mozilla Public License 2.0 (MPL-2.0).
+
+Created by TitleOS.