Upload README.md with huggingface_hub

README.md

@@ -1,5 +1,5 @@
 ---
-title: OpenLLM Realistic Demo Space
+title: OpenLLM Real Models Space
 emoji: 🚀
 colorFrom: blue
 colorTo: purple
@@ -10,28 +10,38 @@ pinned: false
 license: gpl-3.0
 ---
 
-# 🚀 OpenLLM Realistic Demo Space
+# 🚀 OpenLLM Real Models Space
 
-Welcome to the OpenLLM Realistic Demo Space! This interface generates **actual text responses** based on your prompts.
+Welcome to the OpenLLM Real Models Space! This interface uses **actual trained models** from Hugging Face.
 
-## 🎯 Demo Models
+## 🎯 Real Trained Models
 
-We provide **5 different demo models** with varying response quality:
+We provide **5 different real models** with varying training steps:
 
-| Model | Training Steps | Response Quality |
-|-------|---------------|------------------|
-| **Demo 4k** | 4,000 | Basic responses |
-| **Demo 6k** | 6,000 | Improved coherence |
-| **Demo 7k** | 7,000 | Enhanced quality |
-| **Demo 8k** | 8,000 | Sophisticated understanding |
-| **Demo 9k** | 9,000 | Expert-level responses |
+| Model | Training Steps | Parameters | Performance |
+|-------|---------------|------------|-------------|
+| **4k Model** | 4,000 | 35.8M | Early training stage |
+| **6k Model** | 6,000 | 35.8M | Improved coherence (Perplexity: 816.040) |
+| **7k Model** | 7,000 | 35.8M | Enhanced quality (Loss: 2.100, Perplexity: 8.200) |
+| **8k Model** | 8,000 | 35.8M | Sophisticated understanding |
+| **9k Model** | 9,000 | 35.8M | Best performing model |
+
+**These are real GPT-style transformer models trained on Wikipedia passages from the SQuAD dataset.**
 
 ## 🔧 Technical Details
 
-- **Architecture**: GPT-style transformer decoder (demo)
-- **Model Size**: Small demo models for testing
-- **Framework**: PyTorch with realistic text generation
+- **Architecture**: GPT-style transformer decoder
+- **Model Size**: Small (6 layers, 8 heads, 512 embedding dim)
+- **Vocabulary**: 32k tokens (SentencePiece BPE)
+- **Training Data**: Wikipedia passages from SQuAD dataset
+- **Framework**: PyTorch with real trained models
 - **Gradio Version**: 4.44.1 (latest)
-- **Status**: Realistic demo mode - generates actual responses
 
-**This demo generates contextually appropriate responses based on your input prompts.**
+**These models generate actual text based on their training on Wikipedia content.**
+
+**Model Sources:**
+- [4k Model](https://huggingface.co/lemms/openllm-small-extended-4k)
+- [6k Model](https://huggingface.co/lemms/openllm-small-extended-6k)
+- [7k Model](https://huggingface.co/lemms/openllm-small-extended-7k)
+- [8k Model](https://huggingface.co/lemms/openllm-small-extended-8k)
+- [9k Model](https://huggingface.co/lemms/openllm-small-extended-9k)