Ianmacleod/add codellama instruct, refactor codellama models (#360)

* add codellama-7b-instruct to llm-engine, name refactor for codellama

* more name refactoring

* update docs

* add codellama-13b-instruct

Author: ian-scale

docs/model_zoo.md

@@ -20,7 +20,11 @@ Scale hosts the following models in the LLM Engine Model Zoo:
 | `flan-t5-xxl`         | ✅                       |                            | deepspeed, text-generation-inference |
 | `mistral-7b`         | ✅                       |   ✅                         | vllm | 
 | `mistral-7b-instruct`         | ✅                       |    ✅                        | vllm |
-| `code-llama-7b`         | ✅                       |                            | text-generation-inference, vllm |
+| `codellama-7b`         | ✅                       | ✅                           | text-generation-inference, vllm |
+| `codellama-7b-instruct`         | ✅                       | ✅                           | text-generation-inference, vllm |
+| `codellama-13b`         | ✅                       |                            | text-generation-inference, vllm |
+| `codellama-13b-instruct`         | ✅                       |                            | text-generation-inference, vllm |
+| `codellama-34b`         | ✅                       |                            | text-generation-inference, vllm |
 
 ## Usage
 

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

@@ -102,9 +102,11 @@
         "falcon-7b-instruct": "tiiuae/falcon-7b-instruct",
         "falcon-40b": "tiiuae/falcon-40b",
         "falcon-40b-instruct": "tiiuae/falcon-40b-instruct",
-        "code-llama-7b": "codellama/CodeLlama-7b-hf",
-        "code-llama-13b": "codellama/CodeLlama-13b-hf",
-        "code-llama-34b": "codellama/CodeLlama-34b-hf",
+        "codellama-7b": "codellama/CodeLlama-7b-hf",
+        "codellama-7b-instruct": "codellama/CodeLlama-7b-Instruct-hf",
+        "codellama-13b": "codellama/CodeLlama-13b-hf",
+        "codellama-13b-instruct": "codellama/CodeLlama-13b-Instruct-hf",
+        "codellama-34b": "codellama/CodeLlama-34b-hf",
         "llm-jp-13b-instruct-full": "llm-jp/llm-jp-13b-instruct-full-jaster-v1.0",
         "llm-jp-13b-instruct-full-dolly": "llm-jp/llm-jp-13b-instruct-full-dolly-oasst-v1.0",
     },
@@ -126,9 +128,11 @@
         "mistral-7b-instruct": "mistralai/Mistral-7B-Instruct-v0.1",
         "falcon-180b": "tiiuae/falcon-180B",
         "falcon-180b-chat": "tiiuae/falcon-180B-chat",
-        "code-llama-7b": "codellama/CodeLlama-7b-hf",
-        "code-llama-13b": "codellama/CodeLlama-13b-hf",
-        "code-llama-34b": "codellama/CodeLlama-34b-hf",
+        "codellama-7b": "codellama/CodeLlama-7b-hf",
+        "codellama-7b-instruct": "codellama/CodeLlama-7b-Instruct-hf",
+        "codellama-13b": "codellama/CodeLlama-13b-hf",
+        "codellama-13b-instruct": "codellama/CodeLlama-13b-Instruct-hf",
+        "codellama-34b": "codellama/CodeLlama-34b-hf",
         "mammoth-coder-llama-2-7b": "TIGER-Lab/MAmmoTH-Coder-7B",
         "mammoth-coder-llama-2-13b": "TIGER-Lab/MAmmoTH-Coder-13B",
         "mammoth-coder-llama-2-34b": "TIGER-Lab/MAmmoTH-Coder-34B",