gpt 3 turbo 16k

README.md

@@ -39,6 +39,9 @@ cd app && npm install && npx parcel watch src/index.html --no-cache
 cd server && pip3 install -r requirements.txt && cd .. && python3 -m server.app
 ```
 
+After starting the server, `models.json` is copied to `~/.config/openplayground/models.json` and this is used instead of the bundled `models.json`. This allows you to add your own models to the playground and version them in your dotfiles.
+
+
 ## Docker
 
 ```sh
@@ -55,7 +58,7 @@ First volume is optional. It's used to store API keys, models settings.
 - Measure and display time to first token
 - Setup automatic builds with GitHub Actions
 - The default parameters for each model are configured in the `server/models.json` file. If you find better default parameters for a model, please submit a pull request!
-- Someone can help us make a homebrew package, and a dockerfile
+- Someone can help us make a homebrew package
 - Easier way to install open source models directly from openplayground, with `openplayground install <model>` or in the UI.
 - Find and fix bugs
 - ChatGPT UI, with turn-by-turn, markdown rendering, chatgpt plugin support, etc.

server/lib/inference/__init__.py

@@ -326,7 +326,7 @@ def __openai_text_generation__(self, provider_details: ProviderDetails, inferenc
 
     def openai_text_generation(self, provider_details: ProviderDetails, inference_request: InferenceRequest):
         # TODO: Add a meta field to the inference so we know when a model is chat vs text
-        if inference_request.model_name in ["gpt-3.5-turbo", "gpt-4"]:
+        if inference_request.model_name in ["gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-4"]:
             self.__error_handler__(self.__openai_chat_generation__, provider_details, inference_request)
         else:
             self.__error_handler__(self.__openai_text_generation__, provider_details, inference_request)

server/models.json

@@ -243,6 +243,54 @@
           }
         }
       },
+      "gpt-3.5-turbo-16k": {
+        "enabled": false,
+        "status": "ready",
+        "capabilities": [
+          "logprobs"
+        ],
+        "parameters": {
+          "temperature": {
+            "value": 0.5,
+            "range": [
+              0.1,
+              1
+            ]
+          },
+          "maximumLength": {
+            "value": 200,
+            "range": [
+              50,
+              16384
+            ]
+          },
+          "topP": {
+            "value": 1,
+            "range": [
+              0.1,
+              1
+            ]
+          },
+          "presencePenalty": {
+            "value": 0,
+            "range": [
+              0,
+              1
+            ]
+          },
+          "frequencyPenalty": {
+            "value": 0,
+            "range": [
+              0,
+              1
+            ]
+          },
+          "stopSequences": {
+            "value": [],
+            "range": []
+          }
+        }
+      },
       "gpt-4": {
         "enabled": false,
         "status": "ready",