Expose static llama in OSS

Summary:
This exposes a static llama model for CoreML.

We want to unify development behind one static model so that we do not need to apply fixes in multiple places (e.g., iOS 26 fixes).

Differential Revision: D88875745

Author: metascroy

.ci/scripts/test_ane_static_llama.sh

@@ -30,4 +30,6 @@ download_stories_model_artifacts
 
 python export.py -n model.pte -p params.json -c stories110M.pt --seq_length 32 --max_seq_length 64 --dtype fp16 --coreml-quantize c4w --embedding-quantize 4,32
 
+python export_static_llm_coreml.py -n model.pte -p params.json -c stories110M.pt
+
 popd