Update README.md

README.md

@@ -1,5 +1,115 @@
----
-license: other
-license_name: lfm1.0
-license_link: https://huggingface.co/LiquidAI/LFM2-350M/blob/main/LICENSE
----
+---
+license: other
+license_name: lfm1.0
+license_link: https://huggingface.co/LiquidAI/LFM2-350M/blob/main/LICENSE
+metrics:
+- magic judge
+base_model:
+- LiquidAI/LFM2-350M
+tags:
+- lm-studio
+- madlabOSS
+---
+
+# LMS Guide 350m
+
+## 🧠 Overview
+The **LMS Guide 350m** is part of the **MadlabOSS LM Studio Guide** family — a lineup of small, efficient, and highly aligned assistant models trained specifically to provide deterministic, hallucination‑resistant guidance for LM Studio users.
+
+This model is trained on a curated dataset of LM Studio–specific instructions, workflows, troubleshooting steps, and conceptual explanations.
+
+---
+
+## 🚀 Intended Use
+This model is optimized for:
+
+- LM Studio onboarding  
+- workflow explanations  
+- feature descriptions  
+- troubleshooting guidance  
+- plugin/server integration help  
+- safe, deterministic assistant behavior  
+
+It is **not** intended as a general‑purpose chatbot.
+
+---
+
+## 🧩 Model Details
+
+**Base Model:** LFM2‑350m 
+**Parameter Count:** 350 Million 
+**Training Type:** Supervised fine‑tuning  
+**Sequence Length:** 320  
+**Precision:** FP16 
+**Framework:** PyTorch / Transformers  
+
+---
+
+## 📦 Training Data
+The model was trained on:
+
+- **6,000+ LM Studio–specific instruction/response pairs**  
+- Clean, domain‑specific, ontology‑consistent data  
+- Minor general‑purpose conversational data  
+- No web‑scraped content 
+- Full LM Studio Documentation 
+
+A 36k+ expanded dataset is planned for v2.0.
+
+---
+
+## 🏋️ Training Procedure
+
+### **Hyperparameters**
+- Epochs: 6  
+- Batch size: 
+              0.35b + 0.7b = 4
+               1.2b + 2.6b = 16
+- Learning rate: cosine schedule, peak ~4e‑5  
+- Optimizer: AdamW  
+- Gradient clipping: 1.0  
+- Gradient accumulation: 1  
+
+### **Hardware**
+Training was performed on:
+
+- RTX 6000 Ada (96GB)  (1.2b + 2.6b)
+- Dual RTX 3090  (Magic Judge)
+- RTX 3070 (for 0.35B + 0.7b)  
+
+---
+
+## 📊 Evaluation
+
+### **Judge Score**
+Semantic correctness, ontology adherence, and hallucination resistance.
+
+
+### **Qualitative Behavior**
+- Strong adherence to LM Studio terminology  
+- Low hallucination rate  
+- Deterministic, predictable responses  
+- Not optimized for open‑domain reasoning  
+
+---
+
+## 🔒 Safety
+This model is trained exclusively on LM Studio–specific content.  
+It avoids hallucinating non‑existent LM Studio features and adheres to a strict ontology.
+
+It is **not** designed for:
+
+- political content  
+- medical advice  
+- legal advice  
+- general‑purpose conversation  
+
+---
+
+## ⚠️ Limitations
+- Not a general assistant  
+- Not trained for coding, math, or open‑domain reasoning  
+- May refuse tasks outside LM Studio scope  
+- Static accuracy metrics underestimate real performance  
+
+---