adding support for finetuned completion models

litellm/__init__.py

@@ -24,6 +24,16 @@ caching = False
 caching_with_models = False  # if you want the caching key to be model + prompt
 debugger = False
 model_cost = {
+    "babbage-002": {
+        "max_tokens": 16384,
+        "input_cost_per_token": 0.0000004,
+        "output_cost_per_token": 0.0000004,
+    },
+    "davinci-002": {
+        "max_tokens": 16384,
+        "input_cost_per_token": 0.000002,
+        "output_cost_per_token": 0.000002,
+    },
     "gpt-3.5-turbo": {
         "max_tokens": 4000,
         "input_cost_per_token": 0.0000015,
@@ -137,7 +147,7 @@ open_ai_chat_completion_models = [
     "gpt-3.5-turbo-0613",
     "gpt-3.5-turbo-16k-0613",
 ]
-open_ai_text_completion_models = ["text-davinci-003"]
+open_ai_text_completion_models = ["text-davinci-003", "babbage-002", "davinci-002"]
 
 cohere_models = [
     "command-nightly",

litellm/main.py

@@ -248,7 +248,9 @@ def completion(
                 original_response=response,
                 additional_args={"headers": litellm.headers},
             )
-        elif model in litellm.open_ai_text_completion_models:
+        elif (model in litellm.open_ai_text_completion_models or 
+              "ft:babbage-002" in model or # support for finetuned completion models
+              "ft:davinci-002" in model):
             openai.api_type = "openai"
             openai.api_base = (
                 litellm.api_base

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.457"
+version = "0.1.458"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"