Initial commit: SheepOp LLM - Transformer-based language model implementation

- Complete transformer implementation from scratch
- Training pipeline with gradient accumulation and mixed precision
- Optimized inference with KV caching
- Multi-format data processing (PDFs, images, code, text)
- Comprehensive documentation
- Apache 2.0 license
- Example training plots included in docs/images/

models/__init__.py

@@ -0,0 +1,35 @@
+"""
+SheepOp LLM - A modern language model implementation
+Optimized for production RAG systems
+"""
+from .transformer import TransformerModel
+from .attention import MultiHeadAttention, PositionalEncoding
+from .blocks import TransformerBlock, FeedForward
+from .optimized_attention import (
+    OptimizedMultiHeadAttention,
+    RetrievalCache,
+    OptimizedInference,
+    KVCache,
+)
+from .prefetching import (
+    PrefetchDataLoader,
+    LookaheadRetriever,
+    BatchPrefetcher,
+)
+
+__all__ = [
+    'TransformerModel',
+    'MultiHeadAttention',
+    'PositionalEncoding',
+    'TransformerBlock',
+    'FeedForward',
+    'OptimizedMultiHeadAttention',
+    'RetrievalCache',
+    'OptimizedInference',
+    'KVCache',
+    'PrefetchDataLoader',
+    'LookaheadRetriever',
+    'BatchPrefetcher',
+]
+
+