Update constants/models.py

constants/models.py

@@ -9,12 +9,12 @@ MODEL_MAP = {
     "llama3-70b": "meta-llama/Meta-Llama-3-70B-Instruct",
     "zephyr-141b": "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
     "default": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
-    "Qwen2-72B-Instruct": "Qwen/Qwen2-72B-Instruct",
+    "Qwen2-72B": "Qwen/Qwen2-72B",
 }
 
 AVAILABLE_MODELS = list(MODEL_MAP.keys())
 
-PRO_MODELS = ["command-r-plus", "llama3-70b", "zephyr-141b", "Qwen/Qwen2-72B-Instruct"]
+PRO_MODELS = ["command-r-plus", "llama3-70b", "zephyr-141b", "Qwen2-72B"]
 
 STOP_SEQUENCES_MAP = {
     # https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1/blob/main/tokenizer_config.json#L33
@@ -30,7 +30,7 @@ STOP_SEQUENCES_MAP = {
     "openchat-3.5": "<|end_of_turn|>",
     "command-r-plus": "<|END_OF_TURN_TOKEN|>",
     # https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/tokenizer_config.json#L30
-    "Qwen2-72B-Instruct": "<|im_end|>",
+    "Qwen2-72B": "<|im_end|>",
 }
 
 TOKEN_LIMIT_MAP = {
@@ -44,7 +44,7 @@ TOKEN_LIMIT_MAP = {
     "llama3-70b": 8192,
     "zephyr-141b": 2048,
     "gpt-3.5-turbo": 8192,
-    "Qwen2-72B-Instruct": 32768
+    "Qwen2-72B": 32768
 }
 
 TOKEN_RESERVED = 20
@@ -123,8 +123,8 @@ AVAILABLE_MODELS_DICTS = [
         "owned_by": "OpenAI"
     },
     {
-        "id": "Qwen2-72B-Instruct",
-        "description": "[Qwen/Qwen2-72B-Instruct]: https://huggingface.co/Qwen/Qwen2-72B-Instruct",
+        "id": "Qwen2-72B",
+        "description": "[Qwen/Qwen2-72B]: https://huggingface.co/Qwen/Qwen2-72B",
         "object": "model",
         "created": 1700000000,
         "owned_by": "Qwen"