support for finetuned gpt-3.5-turbo

docs/my-website/docs/tutorials/finetuned_chat_gpt.md

@@ -0,0 +1,23 @@
+# Using Fine-Tuned gpt-3.5-turbo
+LiteLLM allows you to call `completion` with your fine-tuned gpt-3.5-turbo models
+
+If you're trying to create your custom finetuned gpt-3.5-turbo model following along on this tutorial: 
+
+Once you've created your fine tuned model, you can call it with `completion()` 
+
+## Usage
+```python
+import os
+from litellm import completion
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+response = completion(
+  model="ft:gpt-3.5-turbo:my-org:custom_suffix:id",
+  messages=[
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "Hello!"}
+  ]
+)
+
+print(response.choices[0].message)
+```

docs/my-website/sidebars.js

@@ -34,7 +34,7 @@ const sidebars = {
     {
       type: 'category',
       label: 'Tutorials',
-      items: ['tutorials/huggingface_tutorial', 'tutorials/TogetherAI_liteLLM', 'tutorials/fallbacks'],
+      items: ['tutorials/huggingface_tutorial', 'tutorials/TogetherAI_liteLLM', 'tutorials/fallbacks', 'tutorials/finetuned_chat_gpt'],
     },
     'token_usage',
     'stream',

litellm/main.py

@@ -202,6 +202,7 @@ def completion(
         elif (
             model in litellm.open_ai_chat_completion_models
             or custom_llm_provider == "custom_openai"
+            or "ft:gpt-3.5-turbo" in model # finetuned gpt-3.5-turbo
         ):  # allow user to make an openai call with a custom base
             openai.api_type = "openai"
             # note: if a user sets a custom base - we should ensure this works