Upload folder using huggingface_hub

README.md

@@ -37,7 +37,7 @@ inference:
 
 ![Model Size](https://img.shields.io/badge/Parameters-360M-blue)
 ![Architecture](https://img.shields.io/badge/Architecture-LlamaForCausalLM-green)
-![Context Length](https://img.shields.io/badge/Context-8192-orange)
+![Context Length](https://img.shields.io/badge/Context-2048-orange)
 ![License](https://img.shields.io/badge/License-MIT-green)
 
 ## 🎯 Overview
@@ -66,7 +66,7 @@ Processing everything with models like LLaMA 3 8B is powerful but **slow and exp
 - **Base Model**: SmolLM2-360M-Instruct (HuggingFace HuggingFaceTB/SmolLM2-360M-Instruct)
 - **Architecture**: LlamaForCausalLM
 - **Parameters**: ~360 million
-- **Context Length**: 8,192 tokens
+- **Context Length**: 2,048 tokens
 - **Vocabulary**: 49,152 tokens
 - **Precision**: bfloat16
 - **Training Framework**: Transformers 4.52.4
@@ -114,15 +114,6 @@ Powers the Stock Trading Analysis & Real-time Signals platform:
 - **Medium-scoring content** → Automated tagging and storage
 - **Low-scoring content** → Filtered out entirely
 
-## 🚀 Performance Benefits
-
-| Metric | Smol News Scorer | Large Model Only |
-|--------|------------------|------------------|
-| **Speed** | ~50ms per item | ~2-5s per item |
-| **Cost** | $0.001 per 1K items | $0.01+ per 1K items |
-| **Throughput** | 1000+ items/minute | 50-100 items/minute |
-| **Resource Usage** | 2GB VRAM | 16GB+ VRAM |
-
 ## 💻 Usage Examples
 
 ### Basic Inference
@@ -330,7 +321,7 @@ WOW CONFIDENCE: 0.85
 - **Latency**: ~50ms per news item (CPU), ~20ms (GPU)
 - **Throughput**: 1000+ items/minute on modest hardware
 - **Accuracy**: 85%+ correlation with human financial analysts
-- **Memory**: 2GB VRAM required for inference
+- **Memory**: <2GB VRAM required for inference
 - **CPU Alternative**: Runs efficiently on CPU-only systems
 
 ## ⚡ Deployment Options
@@ -372,10 +363,8 @@ outputs = llm.generate(prompts, sampling_params)
 ## 🎯 Integration Roadmap
 
 ### Current Integrations
-- ✅ YouTube Financial Video Analyzer (React frontend)
-- ✅ STARS Trading System (Express.js backend)
-- ✅ Kafka streaming pipeline
-- ✅ Real-time WebSocket alerts
+- ✅ YouTube Financial Video Analyzer [Link](https://levidehaan.com/projects/youtube-financial-video-analyzer)
+- ✅ STARS Trading System [Link](https://levidehaan.com/projects/stars-trading-system)
 
 ### Planned Integrations
 - 🔄 Discord/Slack trading bots