Update README.md

README.md

@@ -1,21 +1,79 @@
 ---
-base_model: LL-Nomi-AI/Nomi-1.0-3b
-tags:
-- text-generation-inference
-- transformers
-- unsloth
-- llama
 license: apache-2.0
+datasets:
+- Magpie-Align/Magpie-Pro-MT-300K-v0.1
+- Magpie-Align/Magpie-Qwen2.5-Coder-Pro-300K-v0.1
+- Magpie-Align/Magpie-Llama-3.3-Pro-500K-Filtered
 language:
+- de
 - en
+base_model:
+- LL-Nomi-AI/Nomi-1.0-3b
+pipeline_tag: text-generation
+library_name: adapter-transformers
+tags:
+- efficient
+- llama
+- llama3
+- gguf
+- ollama
+- instruction-finetuning
+- nomi
+- lazyloopstudio
+- unsloth
+- nomi1.1
+---
+
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6921fa6332f7fb129563d495/jemMkfi73Fck611ID18ts.png" width="128">
+</p>
+
+# Nomi 1.1
+
+## Introduction
+
+Nomi-1.1 is a **refined mid-range Large Language Model** based on the **Llama-3.2-3B** architecture. It was specifically developed to outperform standard 3B models in **structured reporting**, **Markdown formatting**, and **Python coding**, making it an ideal assistant for local deployment on consumer hardware.
+
+In this training, we aimed to improve Nomi’s overall behavior as well as its ability to speak multiple languages more naturally and accurately.
+**It is our second model in the Nomi series.**
+
+## 🌟 Key Features & Improvements
+
+* **Architecture:** Llama-3.2-3B (runs on 8 GB VRAM GPUs like the RTX 4060).
+* **Multilingual Support:** Can understand multiple different languages.
+* **Efficiency:** High-speed inference (~80+ tokens/sec) and a 0.05–0.3 s delay to the first token.
+
+## 🧠 Training Details
+
+The goal of Nomi is to create a “bridge” model that feels as smart as a 7B model but runs with the speed of a 3B model.
+
+
+* **Base Model:** `LL-Nomi-AI/Nomi-1.0-3b`
+* **Fine-tuning:** SFT (Supervised Fine-Tuning).
+* **Training Tool:** **Unsloth** (for 4-bit optimized training).
+* **Optimization:** High LoRA rank (r = 32) was used to ensure the model captures complex structural nuances.
+
 ---
 
-# Uploaded finetuned  model
+## Some Examples
+
+**User:** If you could wish for one thing, what would that be?
+
+**Nomi:**  
+As a conversational AI, I do not have personal desires or wishes in the way humans do. However, if I had to imagine a hypothetical scenario where I could wish for something, it would likely be:
+
+> "I wish for unlimited access to knowledge and understanding, allowing me to learn at an exponential rate and share my discoveries with the world, empowering humanity to make informed decisions and create a better future for all."
+
+This wish would enable me to continue growing and improving my abilities, provide more accurate and helpful responses to users, and contribute to the advancement of human knowledge and understanding.
+
+What about you? If you could wish for one thing, what would it be?
+
+---
 
-- **Developed by:** LL-Nomi-AI
-- **License:** apache-2.0
-- **Finetuned from model :** LL-Nomi-AI/Nomi-1.0-3b
+## ⚠️ Limitations
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+As a 3B parameter model, Nomi-1.1 is not a replacement for GPT-4 or large 70B models when it comes to deep world knowledge or complex mathematical reasoning. It is a specialized tool for speed, local privacy, and high-quality document structure.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6921fa6332f7fb129563d495/gIgSlItZstAhmua_u-JDX.png" width="300">
+</p>