test fix

Author: ishaan-jaff

tests/local_testing/test_function_calling.py

@@ -50,7 +50,7 @@ def get_current_weather(location, unit="fahrenheit"):
         "claude-3-haiku-20240307",
         "gemini/gemini-1.5-pro",
         "anthropic.claude-3-sonnet-20240229-v1:0",
-        "groq/llama3-8b-8192",
+        "groq/llama-3.1-8b-instant",
         "cohere_chat/command-r",
     ],
 )

tests/local_testing/test_lowest_cost_routing.py

@@ -31,7 +31,7 @@ async def test_get_available_deployments():
         },
         {
             "model_name": "gpt-3.5-turbo",
-            "litellm_params": {"model": "groq/llama3-8b-8192"},
+            "litellm_params": {"model": "groq/llama-3.1-8b-instant"},
             "model_info": {"id": "groq-llama"},
         },
     ]
@@ -182,7 +182,7 @@ async def test_get_available_endpoints_tpm_rpm_check_async(ans_rpm):
         },
         {
             "model_name": "gpt-3.5-turbo",
-            "litellm_params": {"model": "groq/llama3-8b-8192"},
+            "litellm_params": {"model": "groq/llama-3.1-8b-instant"},
             "model_info": {"id": "5678", "rpm": non_ans_rpm},
         },
     ]

tests/local_testing/test_model_alias_map.py

@@ -15,7 +15,7 @@
 
 litellm.set_verbose = True
 
-model_alias_map = {"good-model": "groq/llama3-8b-8192"}
+model_alias_map = {"good-model": "groq/llama-3.1-8b-instant"}
 
 
 def test_model_alias_map(caplog):

tests/local_testing/test_router.py

@@ -119,7 +119,7 @@ async def test_router_provider_wildcard_routing():
     print("response 2 = ", response2)
 
     response3 = await router.acompletion(
-        model="groq/llama3-8b-8192",
+        model="groq/llama-3.1-8b-instant",
         messages=[{"role": "user", "content": "hello"}],
     )
 

tests/local_testing/test_router_batch_completion.py

@@ -44,7 +44,7 @@ async def test_batch_completion_multiple_models(mode):
             {
                 "model_name": "groq-llama",
                 "litellm_params": {
-                    "model": "groq/llama3-8b-8192",
+                    "model": "groq/llama-3.1-8b-instant",
                 },
             },
         ]
@@ -143,7 +143,7 @@ async def test_batch_completion_fastest_response_streaming():
             {
                 "model_name": "groq-llama",
                 "litellm_params": {
-                    "model": "groq/llama3-8b-8192",
+                    "model": "groq/llama-3.1-8b-instant",
                 },
             },
         ]
@@ -179,7 +179,7 @@ async def test_batch_completion_multiple_models_multiple_messages():
             {
                 "model_name": "groq-llama",
                 "litellm_params": {
-                    "model": "groq/llama3-8b-8192",
+                    "model": "groq/llama-3.1-8b-instant",
                 },
             },
         ]

tests/local_testing/test_spend_calculate_endpoint.py

@@ -43,7 +43,7 @@ async def test_spend_calc_model_on_router_messages():
             {
                 "model_name": "special-llama-model",
                 "litellm_params": {
-                    "model": "groq/llama3-8b-8192",
+                    "model": "groq/llama-3.1-8b-instant",
                 },
             }
         ]
@@ -86,7 +86,7 @@ async def test_spend_calc_using_response():
                     }
                 ],
                 "created": "1677652288",
-                "model": "groq/llama3-8b-8192",
+                "model": "groq/llama-3.1-8b-instant",
                 "object": "chat.completion",
                 "system_fingerprint": "fp_873a560973",
                 "usage": {

tests/test_litellm/test_utils.py

@@ -1051,7 +1051,7 @@ def test_proxy_function_calling_support_consistency(
             ("litellm_proxy/claude-prod", "anthropic/claude-3-sonnet-20240229", False),
             ("litellm_proxy/claude-dev", "anthropic/claude-3-haiku-20240307", False),
             # Groq with custom names (cannot be resolved)
-            ("litellm_proxy/fast-llama", "groq/llama3-8b-8192", False),
+            ("litellm_proxy/fast-llama", "groq/llama-3.1-8b-instant", False),
             ("litellm_proxy/groq-gemma", "groq/gemma-7b-it", False),
             # Cohere with custom names (cannot be resolved)
             ("litellm_proxy/cohere-command", "cohere/command-r", False),

tests/test_openai_endpoints.py

@@ -550,7 +550,7 @@ async def test_proxy_all_models():
     async with aiohttp.ClientSession() as session:
         # call chat/completions with a model that the key was not created for + the model is not on the config.yaml
         await chat_completion(
-            session=session, key=LITELLM_MASTER_KEY, model="groq/llama3-8b-8192"
+            session=session, key=LITELLM_MASTER_KEY, model="groq/llama-3.1-8b-instant"
         )
 
         await chat_completion(