change code-llama to codellama (#400)

* change code-llama to codellama

* use both code-llama and codellama temporarily

Author: ian-scale

model-engine/model_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py

@@ -190,6 +190,10 @@
     # Based on config here: https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-7B/blob/main/config.json#L12
     # Can also see 13B, 34B there too
     "code-llama": {"max_model_len": 16384, "max_num_batched_tokens": 16384},
+    "codellama": {
+        "max_model_len": 16384,
+        "max_num_batched_tokens": 16384,
+    },  # setting both for backwards compatibility, will phase code-llama out in a future pr
     # Based on config here: https://huggingface.co/codellama/CodeLlama-7b-hf/blob/main/config.json#L12
     # Can also see 13B, 34B there too
     "llama-2": {"max_model_len": None, "max_num_batched_tokens": 4096},