e4cbb28ea1
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com> Co-authored-by: Shangming Cai <csmthu@gmail.com>
8 lines
4.2 KiB
JSON
8 lines
4.2 KiB
JSON
{"model_id": "openai/gpt-oss-20b", "cases": [
|
|
{"shape": "user_only", "request": {"messages": [{"role": "user", "content": "Say hi in one sentence."}]}, "expected_token_ids": [200006, 17360, 200008, 3575, 553, 17554, 162016, 11, 261, 4410, 6439, 2359, 22203, 656, 7788, 17527, 558, 87447, 100594, 25, 220, 1323, 19, 12, 3218, 198, 6576, 3521, 25, 220, 1323, 21, 12, 3114, 12, 994, 279, 30377, 289, 25, 14093, 279, 2, 13888, 18403, 25, 8450, 11, 49159, 11, 1721, 13, 21030, 2804, 413, 7360, 395, 1753, 3176, 13, 200007, 200006, 1428, 200008, 62316, 5911, 306, 1001, 21872, 13, 200007, 200006, 173781]},
|
|
{"shape": "system_user", "request": {"messages": [{"role": "system", "content": "You are terse."}, {"role": "user", "content": "What is 2+2?"}]}, "expected_token_ids": [200006, 17360, 200008, 3575, 553, 17554, 162016, 11, 261, 4410, 6439, 2359, 22203, 656, 7788, 17527, 558, 87447, 100594, 25, 220, 1323, 19, 12, 3218, 198, 6576, 3521, 25, 220, 1323, 21, 12, 3114, 12, 994, 279, 30377, 289, 25, 14093, 279, 2, 13888, 18403, 25, 8450, 11, 49159, 11, 1721, 13, 21030, 2804, 413, 7360, 395, 1753, 3176, 13, 200007, 200006, 77944, 200008, 2, 68406, 279, 3575, 553, 28410, 364, 200007, 200006, 1428, 200008, 4827, 382, 220, 17, 10, 17, 30, 200007, 200006, 173781]},
|
|
{"shape": "multi_turn", "request": {"messages": [{"role": "system", "content": "You are terse."}, {"role": "user", "content": "Hi"}, {"role": "assistant", "content": "Hello! How can I help?"}, {"role": "user", "content": "Résumé of the plan: 第一步，收集数据。Then we iterate. 第一步，收集数据。Then we iterate. 第一步，收集数据。Then we iterate. 第一步，收集数据。Then we iterate. 第一步，收集数据。Then we iterate. 第一步，收集数据。Then we iterate. 第一步，收集数据。Then we iterate. 第一步，收集数据。Then we iterate. "}]}, "expected_token_ids": [200006, 17360, 200008, 3575, 553, 17554, 162016, 11, 261, 4410, 6439, 2359, 22203, 656, 7788, 17527, 558, 87447, 100594, 25, 220, 1323, 19, 12, 3218, 198, 6576, 3521, 25, 220, 1323, 21, 12, 3114, 12, 994, 279, 30377, 289, 25, 14093, 279, 2, 13888, 18403, 25, 8450, 11, 49159, 11, 1721, 13, 21030, 2804, 413, 7360, 395, 1753, 3176, 13, 200007, 200006, 77944, 200008, 2, 68406, 279, 3575, 553, 28410, 364, 200007, 200006, 1428, 200008, 12194, 200007, 200006, 173781, 200005, 17196, 200008, 13225, 0, 3253, 665, 357, 1652, 30, 200007, 200006, 1428, 200008, 198128, 328, 290, 3496, 25, 21871, 82066, 979, 18895, 12389, 20009, 788, 19371, 581, 63166, 13, 21871, 82066, 979, 18895, 12389, 20009, 788, 19371, 581, 63166, 13, 21871, 82066, 979, 18895, 12389, 20009, 788, 19371, 581, 63166, 13, 21871, 82066, 979, 18895, 12389, 20009, 788, 19371, 581, 63166, 13, 21871, 82066, 979, 18895, 12389, 20009, 788, 19371, 581, 63166, 13, 21871, 82066, 979, 18895, 12389, 20009, 788, 19371, 581, 63166, 13, 21871, 82066, 979, 18895, 12389, 20009, 788, 19371, 581, 63166, 13, 21871, 82066, 979, 18895, 12389, 20009, 788, 19371, 581, 63166, 13, 220, 200007, 200006, 173781]},
|
|
{"shape": "thinking_off", "request": {"messages": [{"role": "user", "content": "Think about it."}], "chat_template_kwargs": {"enable_thinking": false, "thinking": false}}, "expected_token_ids": [200006, 17360, 200008, 3575, 553, 17554, 162016, 11, 261, 4410, 6439, 2359, 22203, 656, 7788, 17527, 558, 87447, 100594, 25, 220, 1323, 19, 12, 3218, 198, 6576, 3521, 25, 220, 1323, 21, 12, 3114, 12, 994, 279, 30377, 289, 25, 14093, 279, 2, 13888, 18403, 25, 8450, 11, 49159, 11, 1721, 13, 21030, 2804, 413, 7360, 395, 1753, 3176, 13, 200007, 200006, 1428, 200008, 42421, 1078, 480, 13, 200007, 200006, 173781]},
|
|
{"shape": "thinking_on", "request": {"messages": [{"role": "user", "content": "Think about it."}], "chat_template_kwargs": {"enable_thinking": true, "thinking": true}}, "expected_token_ids": [200006, 17360, 200008, 3575, 553, 17554, 162016, 11, 261, 4410, 6439, 2359, 22203, 656, 7788, 17527, 558, 87447, 100594, 25, 220, 1323, 19, 12, 3218, 198, 6576, 3521, 25, 220, 1323, 21, 12, 3114, 12, 994, 279, 30377, 289, 25, 14093, 279, 2, 13888, 18403, 25, 8450, 11, 49159, 11, 1721, 13, 21030, 2804, 413, 7360, 395, 1753, 3176, 13, 200007, 200006, 1428, 200008, 42421, 1078, 480, 13, 200007, 200006, 173781]}
|
|
]}
|