feat(gemma): initial implementation of Gemma model and configs

- Add core Gemma model (architecture, attention, GeGLU, RoPE, RMSNorm, etc)
- Add configs for training and generation: gemma_train.json, gemma_generate.json
- Add Gemma notebook for exploratory analysis and demonstration
- Add __init__.py for Gemma submodule
- Update run_llm_experiment.py to support Gemma experiment configs

test(gemma): add comprehensive unit tests for Gemma

- Test forward pass (with/without cache)
- Test autoregressive generation (greedy, top-k, top-p)
- Test shape correctness and max sequence length errors
- Test multi-layer stack and token embeddings

docs: add documentation notebook for Gemma usage and analysis

Closes: #issue (if applicable)

experiments/llm_only/run_llm_experiment.py

@@ -48,6 +48,9 @@ def load_model_class(model_name):
     elif model_name.lower() == 'mixtral':
         from llm.models.mixtral import Mixtral
         return Mixtral
+    elif model_name.lower() == 'gemma':
+        from llm.models.gemma import Gemma
+        return Gemma
     else:
         raise ValueError(f"Модель '{model_name}' не поддерживается.")