feat: load HuggingFace checkpoints via key/config conversion

- Add astrai.serialization.hf_adapter mapping LLaMA-style HF keys to AstrAI names (input_layernorm, gate_proj, MoE experts/shared_experts) with config aliases for dense and MoE (Mixtral/DeepSeek-V3) layouts; reject biased projections, mismatched head_dim and MLA
- Give AutoModel.from_pretrained weights_format=auto|astrai|hf with auto-detection; read sharded safetensors via model.safetensors.index.json
- Adapt preloaded weights/config in train_context and benchmark CLI

astrai/serialization/__init__.py

@@ -22,9 +22,21 @@ from astrai.serialization.dataset import (
     load_bin_offsets,
     save_bin,
 )
+from astrai.serialization.hf_adapter import (
+    HF_MODEL_TYPES,
+    adapt_config,
+    convert_hf_config,
+    convert_hf_weights,
+    looks_like_hf_state_dict,
+)
 
 __all__ = [
     "Checkpoint",
+    "HF_MODEL_TYPES",
+    "adapt_config",
+    "convert_hf_config",
+    "convert_hf_weights",
+    "looks_like_hf_state_dict",
     "load_json",
     "load_model_config",
     "load_model_weights",