use kimi k2 for llm as a judge

Dylan Huang · Dylan Huang · commit 443e3f83b7b9 · 2025-08-26T15:01:02.000-07:00
diff --git a/tests/chinook/test_pydantic_chinook.py b/tests/chinook/test_pydantic_chinook.py
@@ -47,7 +47,7 @@ async def test_simple_query(row: EvaluationRow) -> EvaluationRow:
         )
     else:
         model = OpenAIModel(
-            "accounts/fireworks/models/llama-v3p1-8b-instruct",
+            "accounts/fireworks/models/kimi-k2-instruct",
             provider="fireworks",
         )
 
@@ -114,7 +114,7 @@ async def test_complex_queries(row: EvaluationRow) -> EvaluationRow:
         )
     else:
         model = OpenAIModel(
-            "accounts/fireworks/models/llama-v3p1-8b-instruct",
+            "accounts/fireworks/models/kimi-k2-instruct",
             provider="fireworks",
         )
 

Original file line number	Diff line number	Diff line change
`@@ -47,7 +47,7 @@ async def test_simple_query(row: EvaluationRow) -> EvaluationRow:`
`47`	`47`	`)`
`48`	`48`	`else:`
`49`	`49`	`model = OpenAIModel(`
`50`		`- "accounts/fireworks/models/llama-v3p1-8b-instruct",`
	`50`	`+ "accounts/fireworks/models/kimi-k2-instruct",`
`51`	`51`	`provider="fireworks",`
`52`	`52`	`)`
`53`	`53`
`@@ -114,7 +114,7 @@ async def test_complex_queries(row: EvaluationRow) -> EvaluationRow:`
`114`	`114`	`)`
`115`	`115`	`else:`
`116`	`116`	`model = OpenAIModel(`
`117`		`- "accounts/fireworks/models/llama-v3p1-8b-instruct",`
	`117`	`+ "accounts/fireworks/models/kimi-k2-instruct",`
`118`	`118`	`provider="fireworks",`
`119`	`119`	`)`
`120`	`120`