Upload README.md with huggingface_hub

README.md

@@ -1,47 +1,55 @@
 ---
-title: OpenLLM Real Models Space
+title: OpenLLM Inference Space
 emoji: 🚀
 colorFrom: blue
 colorTo: purple
 sdk: gradio
-sdk_version: 4.44.1
+sdk_version: 4.0.0
 app_file: app.py
 pinned: false
 license: gpl-3.0
 ---
 
-# 🚀 OpenLLM Real Models Space
+# 🚀 OpenLLM Inference Space
 
-Welcome to the OpenLLM Real Models Space! This interface uses **actual trained models** from Hugging Face.
+Welcome to the OpenLLM Inference Space! This is a comprehensive interface for running inference on our trained OpenLLM models with customizable parameters.
 
-## 🎯 Real Trained Models
+## 🎯 Available Models
 
-We provide **5 different real models** with varying training steps:
+We provide **6 different models** trained for varying numbers of steps:
 
-| 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 |
+| Model | Training Steps | Description | Best Loss |
+|-------|---------------|-------------|-----------|
+| **4k Model** | 4,000 | Early training stage, basic language patterns | ~6.2 |
+| **6k Model** | 6,000 | Improved coherence, better vocabulary usage | ~5.8 |
+| **7k Model** | 7,000 | Enhanced text generation quality | ~5.5 |
+| **8k Model** | 8,000 | More sophisticated language understanding | ~5.3 |
+| **9k Model** | 9,000 | Best performing model (latest training) | ~5.2 |
+| **10k Model** | 10,000 | Latest extended training, maximum performance | ~5.22 |
 
-**These are real GPT-style transformer models trained on Wikipedia passages from the SQuAD dataset.**
+## 🎮 How to Use
 
-## 🔧 Technical Details
+1. **Select a Model** from the dropdown menu
+2. **Load the Model** to see its information
+3. **Enter Your Prompt** in the text box
+4. **Adjust Parameters** (temperature, max length, etc.)
+5. **Generate Text** and see the results!
 
-- **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)
+## ⚙️ Parameters
 
-**These models generate actual text based on their training on Wikipedia content.**
+- **Temperature**: Controls randomness (0.1-2.0)
+- **Max Length**: Number of tokens to generate (10-500)
+- **Top-K**: Limits to top-k most likely tokens (1-100)
+- **Top-P**: Nucleus sampling threshold (0.1-1.0)
 
-**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)
+## 🧠 Model Architecture
+
+- **Model Size**: Small (35.8M parameters)
+- **Layers**: 6 transformer layers
+- **Embedding**: 512 dimensions
+- **Vocabulary**: 32,000 tokens (SentencePiece)
+- **Context Length**: 1,024 tokens
+
+---
+
+**OpenLLM Inference Space** - Experience the power of open-source language models! 🚀