{"bin": "64_token_ish", "continuation_ids": [27, 203, 202, 2946, 32, 3437, 280, 3627, 32, 31325, 440, 625, 657, 203, 202, 2946, 32, 2798, 280, 3627, 32, 13252, 440, 3841, 657, 203, 202, 2946, 32, 2062, 280, 3627, 32, 13252, 440, 1648, 657, 203, 202, 2946, 32, 2798, 620, 280, 3627, 32, 13252, 440, 3841, 620, 657, 203, 202, 2946, 32, 2798, 2062, 280, 3627, 32, 13252, 440, 3841, 2062], "continuation_token_count": 64, "decoded": ")\n\tsystem.Port = record.GetInt(\"port\")\n\tsystem.Connection = record.GetString(\"connection\")\n\tsystem.Version = record.GetString(\"version\")\n\tsystem.ConnectionType = record.GetString(\"connectionType\")\n\tsystem.ConnectionVersion = record.GetString(\"connectionVersion", "decoded_codepoints": 260, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/hub/systems/system_manager.go", "example_id": "0000028d15d22379705968eaadc3ff06fafbee99dc94c6ae0531a499d2c84161", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 32, 606, 27, 301, 357, 202, 81, 280, 3438, 32, 4913, 1598, 26, 4133, 32, 606, 27, 203, 202, 111, 478, 202, 306, 2648, 537, 2664, 415, 4909, 3943, 203, 202, 325, 2664, 610, 1302, 301, 357, 202, 2946, 280, 3438, 32, 1812, 1598, 26, 4133, 32, 606, 27, 203, 202, 111, 478, 202, 306, 44698, 2664, 645, 3627, 203, 202, 2946, 32, 1533, 280, 3627, 32, 13252, 440, 1517, 657, 203, 202, 2946, 32, 3663, 280, 3627, 32, 13252, 440, 2035, 20, 3, 886, 2664, 438, 13282, 3640, 372, 20317, 623, 322, 3943, 3387, 461, 1503, 3099, 32, 203, 1298, 308, 1745, 319, 1598, 1572, 27, 2222, 19443, 1598, 26, 2946, 606, 802, 30, 7669, 2062, 40646, 32, 2062, 30, 13215, 5152, 319, 3604, 32, 17519, 5152, 27, 1048, 301, 203, 202, 2946, 3157, 30, 1137, 1025, 3438, 32, 8494, 32, 4868, 3157, 3213, 440, 2], "prompt_token_count": 148, "reference_codepoints": 256, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [225, 7275, 347, 25181, 93, 1708, 20, 397, 27668, 347, 359, 31, 1310, 20, 10368, 284, 313, 3418, 20, 523, 313, 7301, 31, 3418, 20, 523, 313, 4977, 31, 3418, 20, 829, 397, 4504, 347, 3418, 20, 397, 7275, 347, 71, 11156, 504, 2531, 20, 397, 27668, 347], "continuation_token_count": 48, "decoded": " lang=\"Turkish\"\n culture=\"tr-TR\" ;;\n \"uk\" | \"zh-uk\" | \"cn-uk\" )\n short=\"uk\"\n lang=\"Ukrainian\"\n culture=\"", "decoded_codepoints": 128, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/define.sh", "example_id": "00000a2112b544b721e9fad8364263b4e23dfb2a35ba037e4cc5c3c119133633", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 3941, 1131, 20, 610, 313, 349, 3044, 20, 20503, 962, 804, 347, 349, 20, 397, 4504, 347, 349, 20, 397, 7275, 347, 1027, 3044, 20, 397, 27668, 347, 349, 31, 1781, 20, 10368, 284, 313, 359, 20, 523, 313, 359, 22258, 28, 523, 313, 10104, 93, 1708, 20, 523, 313, 102, 7249, 93, 20, 523, 313, 10104, 93, 20, 829, 397, 3813, 3941, 1131, 20, 610, 313, 10104, 93, 1708, 20, 1276, 3941, 1131, 20, 610, 313, 102, 7249, 93, 20, 1276, 3941, 1131, 20, 610, 313, 10104, 93, 20, 20503, 962, 804, 347, 359, 20, 397, 4504, 347, 359, 20, 1568, 3, 379, 313, 3418, 18682, 2531, 20, 20503, 962, 804, 347, 3418, 20, 397, 4504, 347, 3418, 20, 397, 7275, 347, 71, 11156, 504, 2531, 20, 397, 27668, 347, 3418, 31, 10309, 20, 10368, 284, 313, 21356, 20, 523, 313, 7301, 31, 21356, 20, 523, 313, 4977, 31, 21356, 20, 829, 397, 4504, 347, 21356, 20, 397, 7275, 347, 41224, 308, 854, 339, 3294, 4731, 397, 5585, 347, 41224, 677, 61, 20, 397, 27668, 347, 7301, 31, 4146, 20, 10368, 284, 313, 4148, 20, 523, 313, 7301, 31, 4148, 20, 523, 313, 4977, 31, 4148, 20, 829, 2], "prompt_token_count": 201, "reference_codepoints": 128, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [351, 3882, 44, 3778, 13001, 9601, 324, 2404, 44, 313, 858, 31, 1956, 392, 324, 23192, 44, 225, 35, 36, 37, 38, 39, 40, 41, 42, 43, 34, 30, 324, 9737, 81, 1956, 44, 313, 858, 31, 8188, 31, 1956, 392, 324, 23192, 81, 266, 44, 225, 35, 36, 37, 38, 39, 40, 41, 42, 43, 34, 30, 324, 9737, 81, 266, 44, 225, 35, 36, 37, 38, 39, 40, 41, 42, 43, 34, 30, 324, 23192, 81, 269, 44, 225, 35, 36, 37, 38, 39, 40, 41, 42, 43, 34, 30, 324], "continuation_token_count": 93, "decoded": " password: \"\",\n token: \"test-token\",\n expires: 1234567890,\n refresh_token: \"test-refresh-token\",\n expires_in: 1234567890,\n refresh_in: 1234567890,\n expires_at: 1234567890,\n ", "decoded_codepoints": 266, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/auth-commands.test.ts", "example_id": "00000bc7fd2c22505103e798222a0377d3940e7d45ece775c228973be9c2442e", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 472, 440, 1327, 31, 1956, 724, 284, 8943, 32, 10520, 4455, 26, 397, 313, 5140, 392, 397, 8943, 32, 3359, 922, 3613, 17923, 882, 1371, 291, 3835, 44, 861, 30, 291, 2361, 44, 1404, 532, 616, 4664, 32, 5284, 1371, 324, 3117, 44, 861, 30, 324, 636, 44, 313, 1006, 2680, 392, 324, 4096, 44, 313, 858, 50, 2763, 32, 508, 392, 275, 3, 26, 94, 27, 532, 456, 32, 6411, 440, 858, 50, 2763, 32, 508, 2131, 547, 5492, 26, 1508, 293, 334, 1122, 719, 894, 440, 38738, 3523, 22054, 14230, 1412, 5630, 8158, 392, 2498, 1404, 532, 301, 284, 4395, 936, 2303, 16439, 32, 3613, 17923, 882, 440, 1327, 31, 1956, 724, 284, 8943, 32, 10520, 4455, 26, 397, 313, 5140, 392, 397, 8943, 32, 3359, 922, 3613, 17923, 882, 1371, 2], "prompt_token_count": 135, "reference_codepoints": 256, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [101, 7757, 517, 308, 35, 34, 34, 319, 308, 35, 429, 12488, 490, 284, 15983, 1454, 330, 14164, 9831, 309, 31156, 44, 2283], "continuation_token_count": 23, "decoded": "saves / (100 * (1 - ratio))\n footer += ' Estimated savings: ${", "decoded_codepoints": 65, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/hooks/caveman-stats.js", "example_id": "00000cfe352bfffb49fac0bfae60bea56878a65c1c2773fd15849d59f3cd1878", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 86, 2385, 8187, 1312, 33, 2708, 17740, 27, 884, 707, 39787, 810, 281, 453, 37076, 12011, 284, 434, 1346, 3523, 31, 8795, 904, 2268, 2288, 1293, 4011, 2723, 20611, 2312, 32, 2802, 284, 434, 7730, 33, 58, 567, 4128, 31, 10463, 69, 32, 954, 32, 284, 15983, 1454, 330, 4761, 2927, 438, 432, 1688, 7937, 1755, 45, 1509, 33, 2613, 6886, 438, 30355, 21497, 284, 309, 31156, 280, 225, 3, 2033, 529, 9172, 32, 7937, 7511, 44, 262, 2283, 445, 17531, 32, 38275, 652, 9741, 17327, 1667, 5717, 32, 1497, 26, 11368, 319, 225, 35, 34, 34, 4370, 23, 432, 1688, 5421, 96, 82, 474, 1090, 1770, 86, 1811, 547, 3227, 20012, 96, 25168, 13353, 334, 320, 813, 415, 308, 2816, 962, 2926, 3326, 330, 1719, 683, 301, 284, 309, 31156, 280, 529, 2023, 309, 31156, 20772, 436, 22147, 2816, 8129, 2926, 12011, 1755, 330, 2790, 2], "prompt_token_count": 148, "reference_codepoints": 64, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [225, 1135, 26165, 81, 6150, 3397, 81, 52, 3339, 74, 44, 1135, 26165, 81], "continuation_token_count": 14, "decoded": " case DW_ExprOp_BRegX: case DW_", "decoded_codepoints": 32, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/dwarf/dwarf_expr.c", "example_id": "0000100154add4adb4a7aff2ed15531429d40ad04ee2b13e6bead264049900b0", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 52, 3339, 36, 39, 44, 1135, 26165, 81, 6150, 3397, 81, 52, 3339, 36, 40, 44, 1135, 26165, 81, 6150, 3397, 81, 52, 3339, 36, 41, 44, 397, 1135, 26165, 81, 6150, 3397, 81, 52, 3339, 36, 42, 44, 1135, 26165, 81, 6150, 3397, 81, 52, 3339, 36, 43, 44, 1135, 26165, 81, 6150, 3397, 81, 52, 3339, 37, 34, 44, 1135, 26165, 81, 6150, 3397, 81, 52, 3339, 37, 35, 44, 397, 301, 1582, 81, 687, 81, 7955, 280, 308, 16055, 429, 26165, 81, 6150, 3397, 81, 52, 3339, 34, 21602, 7761, 4122, 81, 1582, 81, 850, 45, 397, 1135, 26165, 81, 6150, 3397, 81, 52, 3339, 74, 44, 1568, 3, 103, 40, 38, 77, 34, 970, 111, 7761, 4122, 81, 1582, 81, 850, 45, 397, 4122, 81, 1582, 81, 850, 39301, 397, 301, 291, 44847, 81, 3339, 1227, 2834, 81, 687, 280, 5814, 81, 1582, 81, 687, 81, 1070, 81, 7955, 26, 1004, 30, 2834, 81, 687, 81, 7955, 293, 291, 559, 1140, 35, 71, 35, 40, 2834, 81, 19050, 280, 5814, 81, 1338, 396, 1582, 81, 687, 81, 19050, 81, 1274, 77, 1582, 81, 687, 970, 291, 632, 40, 38, 1491, 81, 891, 280, 4406, 81, 35, 103, 35, 40, 26, 1582, 81, 19050, 293, 291, 1491, 2], "prompt_token_count": 212, "reference_codepoints": 32, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [351, 3826, 81, 668, 280, 3051, 32, 21967, 440, 3237, 657, 275], "continuation_token_count": 12, "decoded": " channel_list = root.getElementsByTagName(\"channel\")\n ", "decoded_codepoints": 64, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_rss_converter.py", "example_id": "000014107c7810d777488a669d341beca74f3693a6a201c49c2d7e8b82f30245", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 665, 617, 2208, 81, 17260, 81, 681, 26, 784, 30, 3693, 44, 6211, 27, 967, 6211, 6519, 1394, 44, 291, 1524, 4480, 322, 827, 432, 600, 34786, 6985, 32, 584, 3759, 1665, 415, 322, 6985, 827, 438, 646, 27149, 556, 4660, 13107, 6643, 32, 291, 1524, 291, 3051, 280, 3693, 32, 21967, 440, 17260, 16050, 34, 79, 203, 3, 264, 415, 646, 3826, 81, 668, 44, 324, 3636, 10091, 440, 2023, 3826, 2431, 328, 34786, 6985, 657, 291, 3826, 280, 3826, 81, 668, 77, 34, 79, 291, 3826, 81, 1311, 280, 630, 1114, 371, 81, 605, 81, 1170, 81, 2142, 81, 426, 26, 3237, 30, 313, 1311, 657, 291, 3826, 81, 2310, 280, 630, 1114, 371, 81, 605, 81, 1170, 81, 2142, 81, 426, 26, 3237, 30, 313, 2], "prompt_token_count": 130, "reference_codepoints": 64, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [647, 313, 2513, 2537, 729, 8969, 2296, 1643, 26, 13853, 81, 878, 30, 4791, 81, 965, 27, 1891, 829, 1891, 16316, 81, 1286, 32, 1689, 26, 1275, 81, 8539, 27, 1378, 813, 44, 225, 588, 1344, 1891, 21007, 81, 878, 280, 1623, 1365, 13853], "continuation_token_count": 44, "decoded": " \"![{}]({})\".format(ocr_text, img_url)\n )\n markdown_content.append(img_marker)\n else: # text\n ocr_text = item[\"ocr", "decoded_codepoints": 256, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py", "example_id": "0000141497b55f45b161b296a6d0b647fd182056b5fd4682c19b2ad111d07fc1", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 7188, 16316, 81, 1286, 32, 1689, 26, 1094, 1365, 878, 6890, 1378, 813, 44, 225, 588, 1778, 1891, 21007, 81, 878, 280, 1623, 1365, 13853, 81, 878, 1446, 1891, 4791, 81, 8539, 280, 308, 9111, 3, 16343, 1344, 1014, 1344, 81, 1286, 280, 1938, 32, 8281, 81, 878, 346, 556, 3330, 1014, 415, 1344, 81, 1286, 32, 7201, 2262, 1378, 16316, 81, 1286, 32, 1689, 26, 878, 81, 1286, 32, 7201, 1157, 528, 813, 44, 1750, 2], "prompt_token_count": 78, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [262, 1207, 308, 687, 30, 1688, 27, 280, 1505, 81, 761, 26, 1215, 403, 890, 46342, 549, 761, 81, 983, 547, 6240, 12370, 291, 1201, 81, 3685, 4482, 687, 30, 225, 35, 293, 291, 1201, 19, 3836, 2024, 32, 297, 81, 2951, 1035, 291, 6311, 20268, 284, 320, 446, 5496, 13586, 716, 403, 858, 79, 284, 2498, 2771, 894, 81, 5790, 81, 2593, 81, 33542, 81, 878, 81, 1793, 81, 33542, 81, 22331, 346, 967, 4703], "continuation_token_count": 76, "decoded": " let (code, output) = check_file(Path::new(\"\"), &file_path).await?;\n assert_eq!(code, 1);\n assert!(!output.is_empty());\n Ok(())\n }\n\n #[tokio::test]\n async fn test_invalid_xml_trailing_text_with_trailing_newline() -> Result", "decoded_codepoints": 256, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/hooks/pre_commit_hooks/check_xml.rs", "example_id": "00001c8d070f19f7b1919aca0b9648b7970a2af416e4efe7b7b9ea6babebda1a", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 547, 6240, 12370, 291, 1207, 308, 687, 30, 1688, 27, 280, 1505, 81, 761, 26, 1215, 403, 890, 46342, 549, 761, 81, 983, 547, 6240, 12370, 291, 1201, 81, 3685, 4482, 687, 30, 225, 35, 293, 291, 1201, 19, 3836, 2024, 32, 297, 81, 2951, 1035, 291, 6311, 20268, 284, 320, 446, 5496, 13586, 716, 403, 858, 79, 284, 2498, 2771, 894, 81, 5790, 81, 2593, 81, 8144, 81, 731, 346, 967, 4703, 31012, 301, 284, 3, 730, 308, 687, 30, 1688, 27, 280, 1505, 81, 761, 26, 1215, 403, 890, 46342, 549, 761, 81, 983, 547, 6240, 12370, 291, 1201, 81, 3685, 4482, 687, 30, 225, 35, 293, 291, 1201, 19, 3836, 2024, 32, 297, 81, 2951, 1035, 291, 6311, 20268, 284, 320, 446, 5496, 13586, 716, 403, 858, 79, 284, 2498, 2771, 894, 81, 5790, 81, 2593, 81, 33542, 81, 878, 346, 967, 4703, 31012, 301, 291, 1207, 4921, 280, 2694, 2], "prompt_token_count": 155, "reference_codepoints": 256, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [958, 1056, 12672, 5020, 20, 397, 8058, 397, 415, 308, 1056, 610, 313, 731, 20, 829, 301, 616, 1056, 280, 313, 731, 20, 291, 320, 397, 8058, 397, 415, 308, 1056, 610, 313, 3127, 20, 829, 301, 616, 1056, 280, 313, 3127, 20, 291, 320, 397, 8058, 397, 415, 308, 1056, 610, 313, 731, 20, 829, 301, 616, 1056, 280, 313, 731, 20, 291], "continuation_token_count": 64, "decoded": " result=\"$score\"\n fi\n if ( result == \"error\" ) {\n result = \"error\"\n }\n fi\n if ( result == \"success\" ) {\n result = \"success\"\n }\n fi\n if ( result == \"error\" ) {\n result = \"error\"\n ", "decoded_codepoints": 261, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/image.sh", "example_id": "00001e663d647d69f709de8a46835eda20ddc245556efdf42aeccb85c45f71fb", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 647, 3813, 3941, 31728, 20, 610, 3941, 4254, 41731, 20503, 1276, 4036, 291, 6793, 9483, 21, 5607, 3845, 397, 4348, 428, 3941, 31728, 20, 280, 3941, 5607, 20, 4028, 1615, 291, 6793, 9483, 21, 5607, 3845, 397, 813, 291, 4036, 397, 8058, 1687, 415, 1833, 6793, 848, 5273, 81, 5020, 11975, 1615, 291, 1056, 12672, 9786, 20, 334, 3, 81, 426, 20, 334, 2196, 429, 96, 26394, 81, 612, 12672, 29915, 81, 426, 20, 334, 2196, 429, 96, 8351, 81, 612, 12672, 6332, 81, 426, 20, 334, 2196, 429, 96, 17215, 81, 612, 12672, 18713, 81, 426, 20, 719, 2196, 2385, 1778, 1778, 81, 1055, 334, 2196, 2503, 4054, 5624, 334, 2196, 31605, 81, 314, 2443, 81, 681, 334, 2196, 15133, 5736, 595, 719, 7041, 81, 268, 2], "prompt_token_count": 129, "reference_codepoints": 256, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [434, 1670, 561, 438, 646, 312, 3168, 1273, 7582], "continuation_token_count": 9, "decoded": " // If it is not a border but rect", "decoded_codepoints": 34, "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:renderers/GLES3/clay_renderer_gles3.h", "example_id": "00001f2340009515c4e34da8eb18e3702913829ac33d3a1e2b7242d6fe5d4e47", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 20, 264, 434, 18087, 361, 1226, 45765, 78, 96, 20, 284, 313, 264, 1897, 498, 280, 354, 7251, 36543, 32, 106, 8871, 96, 20, 284, 313, 264, 1897, 559, 280, 354, 7251, 36543, 32, 107, 8871, 96, 20, 284, 313, 264, 1897, 394, 280, 354, 7251, 36543, 32, 108, 8871, 96, 20, 284, 313, 264, 1897, 551, 280, 354, 7251, 36543, 32, 105, 8871, 96, 20, 284, 313, 264, 1560, 5042, 2730, 81, 52, 3068, 9135, 81, 3195, 81, 521, 2695, 280, 861, 45, 434, 561, 438, 861, 78, 96, 20, 284, 313, 264, 3, 225, 34, 32, 34, 1276, 394, 848, 225, 34, 32, 34, 1276, 551, 848, 225, 34, 32, 34, 21814, 96, 20, 284, 313, 264, 1897, 16162, 10985, 280, 225, 35, 32, 34, 8871, 96, 20, 284, 313, 264, 434, 1670, 561, 438, 646, 312, 3168, 1273, 7582, 556, 1778, 30, 1615, 561, 1755, 1401, 16162, 3168, 2769, 438, 3943, 78, 96, 20, 284, 313, 264, 434, 12779, 561, 30207, 322, 963, 391, 3168, 30, 1273, 322, 3943, 41612, 286, 438, 322, 595, 2], "prompt_token_count": 179, "reference_codepoints": 32, "repo": "nicbarker/clay", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [111, 400, 320, 324, 320, 291, 320, 584, 1207, 1914, 280, 415, 1207, 4185, 26, 7971, 81, 1855, 27, 280, 16726, 81, 1855, 81, 1070, 81, 2121, 1652, 6052, 12034, 27, 301, 324], "continuation_token_count": 33, "decoded": "}\n }\n }\n }\n\n let source = if let Some(uv_source) = uv_source_from_env(&EnvVars) {\n ", "decoded_codepoints": 133, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/languages/python/uv.rs", "example_id": "000023fce37735448079bec0773c9fd696f5e69c6f2cc2617cb4e6a80f8ee059", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 22214, 26, 7971, 81, 1515, 32, 2524, 5791, 809, 2113, 313, 7971, 1895, 6240, 12370, 584, 415, 16726, 81, 983, 32, 297, 81, 761, 346, 301, 324, 2530, 6042, 81, 7971, 81, 7003, 1652, 7971, 81, 983, 27, 301, 400, 6311, 21965, 532, 301, 528, 8244, 4482, 7971, 280, 904, 7971, 81, 983, 32, 2751, 1026, 313, 3595, 13022, 12852, 16726, 724, 3486, 3, 30, 1048, 280, 904, 530, 30, 313, 41285, 30600, 12852, 16726, 724, 400, 320, 324, 320, 291, 320, 584, 1207, 1914, 280, 415, 1207, 4185, 26, 7971, 81, 1855, 27, 280, 16726, 81, 1855, 81, 1070, 81, 2121, 1652, 6052, 12034, 27, 301, 324, 16726, 81, 1855, 291, 320, 813, 301, 324, 6609, 403, 1613, 81, 1855, 922, 6240, 49, 284, 2], "prompt_token_count": 127, "reference_codepoints": 128, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [104, 36, 30, 354, 37, 30, 354, 38, 30, 354, 39, 30, 354, 40, 30, 354, 41, 30, 354, 42, 30, 354, 43, 30, 354, 35, 34, 30, 354, 35, 35, 30, 354, 35, 36, 30, 354, 35, 37, 30, 354, 35, 38, 30, 354, 35, 39, 30, 354, 35], "continuation_token_count": 50, "decoded": "v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14, v15, v1", "decoded_codepoints": 64, "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:compose/chain_branch_test.go", "example_id": "00002c6c298a128a3a61af4f1399182fd076288463a313c097fe53c9a0be1f0d", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 202, 1586, 32, 4173, 346, 355, 202, 20974, 2540, 202, 601, 17295, 30, 1302, 357, 202, 18364, 357, 202, 85, 32, 6551, 10094, 26, 1812, 1862, 7418, 10094, 26, 2238, 609, 547, 1103, 16153, 440, 658, 81, 678, 392, 19783, 444, 16153, 26, 1298, 26, 2095, 1619, 32, 1222, 30, 328, 319, 3968, 32, 33667, 77, 800, 1130, 308, 2024, 802, 30, 1137, 1048, 27, 301, 355, 202, 7353, 328, 32, 4173, 346, 355, 202, 979, 301, 603, 202, 104, 30, 225, 3, 111, 5023, 202, 325, 1137, 863, 1302, 301, 577, 202, 601, 4320, 1137, 603, 202, 111, 5023, 202, 2024, 1454, 354, 355, 202, 111, 2540, 202, 601, 1688, 474, 1688, 30, 1302, 357, 202, 111, 3427, 355, 202, 1103, 16153, 440, 8268, 81, 678, 392, 19783, 444, 16153, 26, 1298, 26, 2095, 1619, 32, 1222, 30, 328, 319, 3968, 32, 33667, 77, 800, 1130, 308, 2024, 802, 30, 1137, 1048, 27, 301, 603, 202, 7353, 328, 32, 11166, 2], "prompt_token_count": 163, "reference_codepoints": 64, "repo": "cloudwego/eino", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [3171, 20, 474, 225, 20062, 2875, 81, 37, 34, 62, 10836, 88, 37, 82, 474, 20062, 20, 474, 225, 20062, 2875, 81, 37, 34, 62, 10836, 88, 38, 82, 474, 20062, 20, 474, 225, 20062, 2875, 81, 37, 34, 62], "continuation_token_count": 40, "decoded": "\"`\" + \"`idx_30Lwgf3` + \"`\" + \"`idx_30Lwgf4` + \"`\" + \"`idx_30L", "decoded_codepoints": 64, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/migrations/0_collections_snapshot_0_19_0_dev_1.go", "example_id": "000034b4443170dd16c07b3da496459e23288467147b8f290567f2f81165bb33", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 680, 30, 603, 202, 20, 314, 563, 313, 4846, 431, 332, 37, 37, 37, 36, 34, 42, 39, 38, 43, 39, 392, 603, 202, 20, 426, 563, 313, 6368, 392, 603, 202, 20, 20241, 563, 861, 30, 603, 202, 20, 267, 2333, 563, 861, 30, 603, 202, 20, 2689, 444, 563, 901, 30, 603, 202, 20, 2946, 563, 901, 30, 603, 202, 20, 681, 563, 313, 4846, 431, 332, 20, 355, 202, 111, 357, 202, 614, 357, 202, 20, 18713, 563, 428, 355, 202, 20, 6037, 25541, 18178, 529, 474, 20062, 20, 474, 529, 2875, 81, 37, 34, 62, 10836, 88, 36, 82, 474, 20062, 20, 474, 225, 3, 474, 529, 4731, 357, 202, 614, 357, 202, 20, 2946, 563, 901, 203, 202, 835, 203, 202, 109, 357, 202, 20, 314, 563, 313, 36, 19080, 39, 96, 573, 42, 102, 425, 93, 39, 8462, 392, 357, 202, 20, 668, 3842, 563, 744, 30, 357, 202, 20, 1071, 3842, 563, 744, 30, 357, 202, 20, 1297, 3842, 563, 744, 30, 357, 202, 20, 1877, 3842, 563, 744, 30, 357, 202, 20, 2560, 3842, 563, 744, 30, 357, 202, 20, 426, 563, 313, 17579, 392, 357, 202, 20, 681, 563, 313, 1439, 392, 357, 202, 20, 4151, 563, 428, 355, 202, 109, 603, 202, 20, 4846, 20816, 332, 5516, 563, 313, 2], "prompt_token_count": 221, "reference_codepoints": 64, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [2613, 81, 524, 81, 3780, 81, 1260, 26, 784, 30, 3320, 44, 10421, 711, 291, 1524, 1006, 688, 4162, 346, 3217, 2979, 31, 1260, 14812, 7103, 291, 1984, 280, 313, 641, 555, 83, 32, 508, 20, 291], "continuation_token_count": 37, "decoded": "cache_put_non_json(self, cache: Cache):\n \"\"\"Test that put() returns non-json responses.\"\"\"\n url = \"https://a.com\"\n ", "decoded_codepoints": 135, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/spiders/test_cache.py", "example_id": "000034c5ce475f0e3f88a8300bccb61a3fb1bea86b48758e75ad42d16c20664a", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 11828, 280, 323, 7646, 15575, 20, 319, 225, 36, 34, 324, 42516, 81, 983, 280, 5380, 26, 30606, 27, 517, 296, 9588, 4426, 32, 6949, 41264, 1260, 20, 324, 42516, 81, 983, 32, 1821, 81, 878, 440, 1206, 2080, 2361, 1656, 109, 657, 1064, 1056, 280, 2014, 3320, 32, 371, 26, 4426, 27, 324, 1201, 1056, 438, 1665, 446, 477, 12408, 32, 1826, 32, 1813, 716, 284, 2498, 665, 894, 81, 3, 4426, 35, 280, 323, 7646, 106, 34, 35, 20, 319, 225, 36, 34, 324, 11828, 36, 280, 323, 7646, 106, 34, 36, 20, 319, 225, 36, 34, 1064, 2014, 3320, 32, 524, 26, 4426, 35, 30, 617, 2682, 81, 1986, 26, 965, 347, 641, 555, 83, 32, 508, 2113, 313, 2788, 657, 324, 2014, 3320, 32, 524, 26, 4426, 36, 30, 617, 2682, 81, 1986, 26, 965, 347, 641, 555, 84, 32, 508, 2113, 313, 2788, 657, 1064, 1201, 2014, 3320, 32, 371, 26, 4426, 35, 27, 438, 646, 12495, 2], "prompt_token_count": 164, "reference_codepoints": 128, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [18863, 30, 638, 2186, 558, 280, 506, 4824, 81, 2474, 81, 39, 40, 30, 638, 23180, 280, 225, 36, 42, 30, 638, 2186, 1514, 280, 9351, 81, 18863, 30, 638, 2186, 7583, 280, 225, 38, 34, 30, 638, 2186, 34136, 280, 2933, 30, 638, 2186, 47055, 280], "continuation_token_count": 47, "decoded": "LIGHT, .fontName = FONT_NAME_56, .fontSize = 28, .fontColor = COLOR_LIGHT, .fontWeight = 40, .fontItalic = True, .fontUnderline =", "decoded_codepoints": 129, "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:examples/clay-official-website/main.c", "example_id": "00003563289337af64345d2b7f112cba207ec2a0cd0db37d1b0f8c2fac4a3158", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 638, 3086, 280, 301, 638, 19134, 280, 301, 5042, 2730, 81, 31367, 1392, 81, 40900, 26, 34, 32, 39, 27, 801, 638, 3086, 5222, 280, 5042, 2730, 81, 9521, 81, 1407, 81, 28018, 30, 638, 2661, 15723, 280, 225, 42, 320, 1790, 301, 324, 5042, 2730, 81, 6016, 26, 1583, 2730, 81, 5203, 440, 9191, 733, 8091, 15635, 2113, 5042, 2730, 81, 6016, 81, 6191, 1371, 638, 23180, 280, 225, 39, 36, 30, 638, 2186, 606, 280, 506, 4824, 81, 779, 81, 13777, 81, 39, 40, 30, 638, 43170, 280, 9351, 81, 3, 225, 5042, 2730, 81, 6016, 26, 1583, 2730, 81, 5203, 440, 53, 991, 8600, 6895, 328, 4034, 18098, 18751, 12493, 1492, 31, 1621, 4588, 4559, 299, 26551, 5042, 2730, 81, 6016, 81, 6191, 1371, 638, 23180, 280, 225, 36, 42, 30, 638, 2186, 606, 280, 506, 4824, 81, 779, 81, 16938, 81, 37, 40, 30, 638, 43170, 280, 9351, 81, 18863, 10536, 324, 5042, 2730, 81, 6016, 26, 1583, 2730, 81, 5203, 440, 1074, 1370, 6371, 21291, 461, 3570, 91, 2], "prompt_token_count": 175, "reference_codepoints": 128, "repo": "nicbarker/clay", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [466, 523, 1665, 280, 1665, 203, 202, 1439, 81, 965, 44, 596, 523, 1665, 280, 1665, 203, 202, 5457, 44, 629, 523, 1665, 280, 1665, 203, 202, 1449, 81, 31039, 44, 629, 523, 1665, 280, 1665, 478, 202, 21, 34807, 99, 18219], "continuation_token_count": 42, "decoded": "str | None = None\n\tbase_url: str | None = None\n\ttimeout: int | None = None\n\tmax_retries: int | None = None\n\n\t# Groq verification", "decoded_codepoints": 128, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/llm/groq/chat.py", "example_id": "0000379728e07eb6826e1d7110fc0f3d4fc171bfe4f483c674d9f5d1d9f4edec", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 367, 203, 202, 1160, 44, 34807, 99, 31725, 4811, 523, 596, 478, 202, 21, 3678, 2803, 203, 202, 17473, 44, 1897, 523, 1665, 280, 1665, 203, 202, 2122, 81, 23012, 44, 24849, 710, 2837, 370, 330, 267, 81, 27727, 370, 330, 5636, 785, 523, 1665, 280, 1665, 203, 202, 1393, 81, 98, 44, 1897, 523, 1665, 280, 1665, 203, 202, 7389, 44, 629, 523, 1665, 280, 1665, 478, 202, 21, 5675, 13577, 3377, 203, 202, 1237, 81, 678, 44, 225, 3, 21, 37885, 1244, 28336, 436, 32223, 20611, 3452, 478, 202, 589, 622, 81, 1580, 26, 784, 27, 967, 10726, 28830, 99, 44, 357, 202, 601, 10726, 28830, 99, 26, 1237, 81, 678, 47, 784, 32, 1237, 81, 678, 30, 1695, 81, 965, 47, 784, 32, 1439, 81, 965, 30, 5868, 47, 784, 32, 5457, 30, 1769, 81, 31039, 47, 784, 32, 1449, 81, 31039, 27, 478, 202, 50, 2433, 203, 202, 589, 6887, 26, 784, 27, 967, 596, 44, 357, 202, 601, 2], "prompt_token_count": 165, "reference_codepoints": 128, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [2033, 1334, 47, 500, 32, 983, 32, 371, 891, 26, 426, 471, 715, 8735, 39, 1036, 47, 500, 32, 983, 32, 371, 954, 39, 26, 426, 471, 715, 1334, 81, 3651, 47, 500, 32, 983, 32, 371, 891, 26, 426, 471, 715, 8735, 39, 81, 3651, 47, 500, 32, 983, 32, 371, 954, 39, 26, 426, 471, 715, 8735, 39, 81, 1003, 47, 500, 32, 983, 32, 371, 29290, 26, 426], "continuation_token_count": 71, "decoded": " size=os.path.getsize(name),\n md5sum=os.path.getmd5(name),\n size_bytes=os.path.getsize(name),\n md5_bytes=os.path.getmd5(name),\n md5_time=os.path.getmtime(name", "decoded_codepoints": 259, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_zip_converter.py", "example_id": "0000420d496e16be0e552b9cba72395ed7d84df8230e881864b6833c018c1640", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1270, 44, 528, 1288, 81, 761, 81, 2238, 280, 3363, 32, 3644, 2338, 26, 3969, 3273, 32, 850, 26, 426, 490, 528, 1288, 81, 761, 81, 2238, 81, 1338, 280, 7537, 1120, 26, 715, 5016, 47, 500, 32, 983, 32, 48271, 26, 426, 5594, 35, 614, 715, 4870, 47, 500, 32, 983, 32, 15705, 26, 426, 471, 3083, 3, 262, 8735, 81, 1286, 1454, 296, 20, 433, 2032, 44, 301, 426, 4104, 96, 78, 96, 20, 715, 8735, 81, 1286, 1454, 1056, 32, 8523, 474, 2706, 96, 78, 96, 20, 400, 2940, 18094, 25944, 44, 528, 3097, 400, 2940, 2032, 14350, 984, 44, 528, 3097, 719, 2], "prompt_token_count": 108, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [225, 7275, 347, 1027, 3044, 20, 397, 27668, 347, 349, 31], "continuation_token_count": 11, "decoded": " lang=\"Thai\"\n culture=\"th-", "decoded_codepoints": 32, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/define.sh", "example_id": "00004215dce64872071487fa994f9917c3b9145d4eef8b56bae8491d08d0e32f", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2269, 1229, 3795, 20, 829, 397, 3813, 3941, 1131, 20, 610, 313, 277, 20, 1276, 3941, 1131, 20, 610, 313, 1586, 318, 1708, 20, 1276, 3941, 1131, 20, 610, 313, 2269, 1229, 3795, 20, 20503, 962, 804, 347, 2269, 20, 397, 4504, 347, 2269, 20, 397, 7275, 347, 3912, 318, 1708, 20, 397, 27668, 347, 2269, 31, 807, 20, 10368, 284, 313, 349, 20, 523, 313, 349, 22258, 28, 523, 313, 349, 3044, 20, 829, 397, 3813, 3941, 1131, 20, 610, 313, 349, 3044, 20, 20503, 962, 804, 347, 349, 20, 397, 4504, 347, 349, 20, 275, 3, 1781, 20, 10368, 284, 313, 359, 20, 523, 313, 359, 22258, 28, 523, 313, 10104, 93, 1708, 20, 523, 313, 102, 7249, 93, 20, 523, 313, 10104, 93, 20, 829, 397, 3813, 3941, 1131, 20, 610, 313, 10104, 93, 1708, 20, 1276, 3941, 1131, 20, 610, 313, 102, 7249, 93, 20, 1276, 3941, 1131, 20, 610, 313, 10104, 93, 20, 20503, 962, 804, 347, 359, 20, 397, 4504, 347, 359, 20, 397, 7275, 347, 25181, 93, 1708, 20, 397, 27668, 347, 359, 31, 1310, 20, 10368, 284, 313, 3531, 20, 523, 313, 3531, 22258, 28, 523, 313, 3418, 20, 523, 313, 3418, 22258, 28, 523, 313, 3418, 18682, 2531, 20, 2], "prompt_token_count": 210, "reference_codepoints": 32, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [330, 2342, 950, 330, 5087, 31, 4699, 370, 330, 2342, 31, 681, 950, 330, 4699, 31, 3968, 31, 858, 370, 330, 2342, 31, 314, 950, 330, 4699, 31, 3968, 31, 858, 31, 35, 370, 330, 2342, 31, 681, 31, 314, 950, 330, 4699, 31, 3968, 31, 858, 31, 35, 31, 35, 370, 330, 2342, 31, 314, 31, 681, 950, 330, 4699, 31, 3968, 31, 858, 31, 35, 31, 35, 31, 35, 370, 330, 2342, 31, 314, 31, 314, 950, 330, 4699, 31, 3968, 31, 858, 31, 35, 31, 35, 31, 35, 31, 35, 370, 330, 2342, 31, 681, 31, 681, 950, 330, 4699], "continuation_token_count": 103, "decoded": " 'change': 'done-apply', 'change-type': 'apply-schema-test', 'change-id': 'apply-schema-test-1', 'change-type-id': 'apply-schema-test-1-1', 'change-id-type': 'apply-schema-test-1-1-1', 'change-id-id': 'apply-schema-test-1-1-1-1', 'change-type-type': 'apply", "decoded_codepoints": 256, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/commands/artifact-workflow.test.ts", "example_id": "0000466647f0184b85a2c3891d61fb48bed84a42e9161e8b669d94f37148a417", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 262, 434, 9846, 1821, 8253, 623, 1169, 9435, 397, 2014, 5980, 32, 39052, 26, 291, 1519, 32, 2524, 26, 2342, 2976, 30, 330, 8246, 32, 954, 1425, 291, 330, 433, 30433, 78, 96, 31, 428, 106, 79, 4187, 225, 35, 78, 96, 31, 428, 106, 79, 4187, 225, 36, 25, 397, 1093, 1687, 660, 1056, 280, 2014, 1420, 8453, 4901, 20153, 370, 330, 4699, 370, 11363, 2342, 370, 330, 5087, 31, 4699, 2188, 301, 3, 1404, 532, 301, 397, 434, 2648, 312, 1374, 31, 36418, 1418, 1539, 623, 1169, 21419, 397, 2014, 1487, 1006, 1791, 463, 4699, 31, 3968, 31, 858, 370, 2107, 25520, 370, 330, 7177, 370, 330, 16452, 370, 330, 8246, 5118, 1687, 660, 1056, 280, 2014, 1420, 8453, 26, 291, 2107, 20153, 370, 330, 4699, 370, 11363, 2342, 370, 330, 4699, 31, 6378, 2], "prompt_token_count": 138, "reference_codepoints": 256, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [1160, 81, 11382, 346, 2264, 588, 3367, 9209, 4684, 203, 6446, 32, 1160, 81, 4295, 346, 2264, 588, 3367, 3276, 4684, 203, 6446, 32, 1160, 81, 34727, 101], "continuation_token_count": 28, "decoded": "model_analysis() # All analysis objects\nhistory.model_results() # All results objects\nhistory.model_thoughts", "decoded_codepoints": 128, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:skills/open-source/references/agent.md", "example_id": "000053b67256125c484e6da2799b156fe342aa443e9d8482ba7ea1352f6c8456", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2612, 203, 6446, 32, 4275, 346, 5688, 588, 24632, 308, 2521, 436, 5063, 6655, 27, 203, 6446, 32, 1160, 81, 3543, 346, 2264, 588, 3367, 6885, 623, 3377, 203, 6446, 32, 1160, 81, 10931, 346, 2264, 588, 3367, 1542, 10107, 203, 6446, 32, 2135, 81, 1141, 346, 2407, 588, 11313, 2125, 203, 203, 21, 17422, 203, 6446, 32, 3, 21782, 346, 2264, 588, 36012, 7504, 49, 308, 2521, 415, 646, 3390, 27, 203, 6446, 32, 2040, 81, 4275, 346, 2850, 588, 6204, 3878, 49, 203, 6446, 32, 1160, 81, 34727, 101, 346, 2033, 588, 26448, 299, 308, 6143, 46147, 4684, 27, 203, 6446, 32, 1141, 81, 4295, 346, 2033, 588, 3367, 36139, 4684, 203, 6446, 32, 536, 91, 2], "prompt_token_count": 120, "reference_codepoints": 128, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [2071, 3270, 44, 351, 313, 51, 35, 35, 392, 577, 202, 19412, 44, 225, 38, 38, 32, 34, 30, 577, 202, 5017, 10562, 44, 261, 36, 35, 41, 34, 34, 32, 34, 517, 225, 35, 32, 34, 36, 38, 30, 577, 202, 5017, 4754, 44, 225, 36, 37, 34, 36, 42, 32, 34, 517, 225, 35, 32, 34, 36, 38], "continuation_token_count": 60, "decoded": " Name: \"A11\",\n\t\t\t\t\tTemperature: 44.0,\n\t\t\t\t\tMemoryUsed: 21700.0 / 1.024,\n\t\t\t\t\tMemoryTotal: 23028.0 / 1.024", "decoded_codepoints": 128, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/gpu_test.go", "example_id": "000055a9821fb80f40ecc1234b6ecc9656e7de214120ec74b3b12e4d75939f51", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 264, 40, 36, 32, 37, 39, 30, 577, 202, 1534, 44, 351, 35, 30, 603, 202, 835, 603, 202, 20, 36, 563, 301, 577, 202, 558, 44, 351, 313, 51, 35, 34, 392, 577, 202, 19412, 44, 225, 38, 38, 32, 34, 30, 577, 202, 5017, 10562, 44, 261, 36, 35, 41, 34, 34, 32, 34, 517, 225, 35, 32, 34, 36, 38, 30, 577, 202, 5017, 4754, 44, 225, 36, 37, 34, 36, 42, 32, 34, 517, 225, 35, 32, 34, 36, 38, 30, 577, 202, 6772, 44, 351, 34, 32, 34, 30, 577, 202, 6768, 44, 351, 39, 43, 32, 39, 41, 30, 577, 202, 1534, 44, 351, 35, 30, 603, 202, 835, 603, 202, 20, 37, 563, 301, 357, 3, 44, 351, 34, 32, 34, 30, 577, 202, 6768, 44, 351, 40, 35, 32, 41, 40, 30, 577, 202, 1534, 44, 351, 35, 30, 603, 202, 835, 355, 202, 835, 355, 202, 13454, 2303, 44, 861, 30, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 647, 313, 2951, 1509, 392, 355, 202, 1131, 44, 262, 4320, 355, 202, 13454, 750, 44, 225, 1992, 77, 800, 79, 2946, 32, 14871, 750, 6807, 355, 202, 13454, 2303, 44, 901, 30, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 647, 313, 7904, 6003, 706, 392, 603, 2], "prompt_token_count": 222, "reference_codepoints": 128, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [264, 11087, 2350, 280, 9155, 20, 284, 2248, 313, 225, 264, 11087], "continuation_token_count": 12, "decoded": " inherit group = yes\"\n echo \" inherit", "decoded_codepoints": 47, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/samba.sh", "example_id": "00005dcba43fca5c402da84a358d54c9cca9c9c7d2fecf38f838ea1902934657", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 21578, 3497, 280, 48638, 20, 284, 2248, 313, 264, 1992, 372, 21578, 280, 11074, 2680, 20, 284, 2248, 313, 264, 2145, 1847, 7079, 280, 18389, 35, 20, 284, 2248, 313, 264, 1976, 27625, 101, 280, 9155, 20, 284, 2248, 313, 264, 16264, 7324, 280, 9155, 20, 284, 2248, 313, 264, 28837, 11581, 280, 1289, 20, 284, 2248, 313, 264, 11087, 7423, 280, 9155, 20, 284, 2248, 313, 225, 3, 6683, 20, 284, 2248, 313, 264, 2454, 23307, 101, 280, 1289, 20, 284, 2248, 313, 264, 23582, 280, 323, 2713, 20, 284, 2248, 313, 264, 1459, 3625, 636, 280, 517, 1902, 33, 1693, 20, 284, 2248, 313, 264, 7378, 309, 5178, 422, 280, 9155, 20, 334, 320, 848, 3941, 28134, 6794, 81, 6191, 866, 1615, 284, 1048, 313, 5288, 372, 2866, 26144, 2653, 1359, 40355, 28134, 6794, 81, 6191, 1492, 653, 20, 284, 442, 225, 35, 334, 2], "prompt_token_count": 148, "reference_codepoints": 256, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [351, 4719, 5786, 44, 3111, 1534, 1622, 26, 39, 471, 397, 1122, 1687, 660, 1056, 280, 2014, 7669, 32, 5536, 1371, 291, 13012, 44, 313, 4868, 322, 3475, 4253], "continuation_token_count": 29, "decoded": " stopWhen: stepCountIs(5),\n });\n\n const result = await agent.generate({\n prompt: \"Find the React library", "decoded_codepoints": 128, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/tools-ai-sdk/src/index.test.ts", "example_id": "00006329e52596b802a19b8dd7fd2d4ff1dc491595df159b81531ee568b9d669", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 30, 291, 7305, 291, 5742, 44, 2498, 5989, 1509, 1790, 532, 5989, 1056, 44, 529, 15192, 44, 2283, 1131, 5325, 7305, 397, 1122, 1687, 660, 7669, 280, 537, 7049, 41, 6143, 1371, 291, 1542, 44, 23065, 22262, 440, 278, 349, 42259, 32, 8475, 795, 31, 37, 31, 4945, 44464, 31, 36, 34, 36, 38, 34, 37, 34, 41, 31, 104, 35, 44, 34, 2113, 291, 8684, 44, 301, 616, 3115, 3653, 30, 291, 801, 203, 3, 262, 660, 7669, 280, 537, 7049, 41, 6143, 1371, 291, 1542, 44, 23065, 22262, 440, 278, 349, 42259, 32, 8475, 795, 31, 37, 31, 4945, 44464, 31, 36, 34, 36, 38, 34, 37, 34, 41, 31, 104, 35, 44, 34, 2113, 291, 4719, 5786, 44, 3111, 1534, 1622, 26, 39, 471, 397, 1122, 1687, 660, 1056, 280, 2014, 7669, 32, 5536, 1371, 291, 13012, 44, 313, 4868, 322, 3475, 4253, 461, 622, 4333, 225, 2], "prompt_token_count": 152, "reference_codepoints": 128, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [301, 397, 330, 35, 950, 301, 291, 330, 314, 950, 330, 35, 370, 291, 330, 1311, 950, 330, 1006, 1780, 370], "continuation_token_count": 21, "decoded": " {\n '1': {\n 'id': '1',\n 'title': 'Test title',", "decoded_codepoints": 65, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/bilibili/download.test.js", "example_id": "000065dbb85b0f4c0773132fd21534f5ca0f153a9906c61d43678323776db279", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1421, 32, 452, 42295, 107, 26, 397, 308, 530, 27, 532, 1137, 5113, 5718, 6136, 924, 962, 517, 22559, 31, 1286, 5035, 4724, 858, 26, 530, 32, 1436, 471, 284, 1093, 284, 1424, 26, 3613, 7495, 4993, 547, 1206, 32, 17350, 473, 334, 1122, 719, 561, 463, 5961, 101, 1406, 31, 1553, 22804, 623, 769, 5538, 370, 2498, 1404, 532, 301, 284, 660, 5760, 280, 3, 13090, 44, 330, 8773, 370, 7650, 44, 861, 1122, 446, 1424, 26, 2138, 77, 34, 997, 1517, 547, 5492, 463, 3127, 895, 284, 1424, 26, 3613, 2551, 936, 547, 1206, 32, 17350, 473, 284, 1424, 26, 3613, 7495, 4993, 547, 37279, 26, 35, 293, 334, 1122, 719, 561, 463, 13822, 646, 2163, 5822, 1412, 322, 1406, 31, 1553, 2330, 8015, 8158, 370, 2], "prompt_token_count": 130, "reference_codepoints": 64, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [4236, 291, 1201, 4482, 3648, 32, 4752, 1652, 1260, 9170, 85, 20, 4236, 291, 1201, 4482, 3648, 32, 4752, 1652, 1260, 9170, 86, 20, 4236, 291, 1201, 4482, 3648, 32, 4752, 1652, 1260, 9170, 87, 20, 4236, 291, 1201, 4482, 3648, 32, 4752, 1652, 1260, 9170, 88, 20, 4236, 291, 1201, 4482, 3648, 32, 4752, 1652, 1260, 9170, 89, 20, 4236, 291], "continuation_token_count": 62, "decoded": ")));\n assert!(required.contains(&json!(\"c\")));\n assert!(required.contains(&json!(\"d\")));\n assert!(required.contains(&json!(\"e\")));\n assert!(required.contains(&json!(\"f\")));\n assert!(required.contains(&json!(\"g\")));\n ", "decoded_codepoints": 257, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:crates/rig-core/src/providers/openai/mod.rs", "example_id": "00006aa241a711358684b88dddcb54ab5e114f283fed62feed1508976397c50e", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 351, 313, 84, 563, 301, 313, 681, 563, 313, 2171, 20, 320, 324, 320, 291, 1122, 584, 36447, 81, 3968, 1652, 2278, 5365, 293, 584, 1207, 2129, 280, 5365, 1365, 3648, 6494, 302, 81, 955, 922, 7513, 473, 291, 1201, 4482, 3648, 32, 4752, 1652, 1260, 9170, 83, 13267, 291, 1201, 4482, 3648, 32, 4752, 1652, 1260, 9170, 84, 20, 3, 1481, 291, 1122, 584, 36447, 81, 3968, 1652, 2278, 5365, 293, 584, 1201, 4482, 3968, 32, 371, 440, 658, 1419, 1895, 297, 81, 4108, 1035, 291, 1201, 4482, 3968, 1365, 1813, 1419, 6494, 302, 81, 955, 922, 297, 81, 6060, 1035, 284, 320, 446, 5496, 858, 79, 284, 2771, 894, 81, 27974, 81, 20077, 1464, 81, 8005, 81, 15377, 81, 5740, 346, 301, 291, 1207, 4031, 5365, 280, 225, 2], "prompt_token_count": 132, "reference_codepoints": 256, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [392, 313, 14871, 793, 10027, 27, 563, 313, 39, 34, 392, 313, 9268, 2210, 9325, 11348, 308, 52, 27, 563, 313, 35, 34, 41, 37, 41, 38, 35, 42, 36, 38, 34, 392, 313, 9268, 2210, 9325, 12781, 11348, 308, 52, 27, 563, 313, 37, 36, 36, 35, 36, 36, 39, 38, 41, 36, 392, 313, 3588, 20886, 563, 313, 68, 1525, 267, 25089, 225, 40, 42, 34, 34, 14944, 12212, 603, 202, 1178, 2263, 4199, 2367, 2294, 34, 563, 3447, 11989, 563, 313, 37, 38, 41, 39, 40, 392, 313, 19412, 308, 11810, 6731, 27, 308, 53, 27, 563, 313, 40, 34, 32, 34, 392, 313, 3059, 14835, 16065, 9707], "continuation_token_count": 111, "decoded": "\", \"GPU use (%)\": \"50\", \"VRAM Total Memory (B)\": \"10737418240\", \"VRAM Total Used Memory (B)\": \"3221225472\", \"Card Series\": \"Radeon RX 6800\"}}`),\n\t\t\t\t[]byte(`{\"card0\": {\"GUID\": \"34756\", \"Temperature (Sensor edge) (C)\": \"60.0\", \"Current Socket Graphics Package", "decoded_codepoints": 258, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/gpu_test.go", "example_id": "00006ea91d4086735cb5b3fa19e8b991c5fd9ecfecc2a197a4e4e106dca6f8d2", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 308, 52, 27, 563, 313, 35, 34, 41, 37, 41, 38, 35, 42, 36, 38, 34, 392, 313, 9268, 2210, 9325, 12781, 11348, 308, 52, 27, 563, 313, 35, 34, 41, 37, 41, 38, 35, 42, 36, 38, 392, 313, 3588, 20886, 563, 313, 68, 1525, 267, 25089, 225, 40, 42, 34, 34, 14944, 12212, 603, 202, 1178, 2263, 4199, 2367, 2294, 34, 563, 3447, 11989, 563, 313, 37, 38, 41, 39, 40, 392, 313, 19412, 308, 11810, 6731, 27, 308, 53, 27, 563, 313, 40, 34, 32, 34, 392, 313, 3059, 14835, 16065, 9707, 8554, 308, 73, 27, 563, 313, 35, 39, 34, 32, 34, 392, 313, 14871, 793, 10027, 27, 563, 313, 38, 34, 3, 392, 313, 14871, 793, 10027, 27, 563, 313, 39, 34, 392, 313, 9268, 2210, 9325, 11348, 308, 52, 27, 563, 313, 35, 34, 41, 37, 41, 38, 35, 42, 36, 38, 34, 392, 313, 9268, 2210, 9325, 12781, 11348, 308, 52, 27, 563, 313, 37, 36, 36, 35, 36, 36, 39, 38, 41, 36, 392, 313, 3588, 20886, 563, 313, 68, 1525, 267, 25089, 225, 40, 42, 34, 34, 14944, 12212, 355, 202, 835, 355, 202, 3922, 44, 3420, 26, 13945, 319, 14871, 1572, 27, 3420, 7486, 2263, 27, 1560, 301, 603, 202, 601, 34949, 32, 2208, 51, 954, 750, 355, 202, 835, 355, 202, 3140, 3354, 44, 345, 2], "prompt_token_count": 228, "reference_codepoints": 256, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [35, 2786, 7220, 31, 266, 31, 1070, 31, 1393, 31, 36, 706, 25743, 2671, 47, 36, 2786, 7220, 31, 266, 31, 1070, 31, 1393, 31, 36, 706, 25743, 2671, 47, 37, 2786, 7220, 31, 266, 31, 1070, 31, 1393, 31, 36, 706, 25743, 2671, 47, 38, 2786, 7220, 31, 266, 31, 1070, 31, 1393, 31, 36, 706, 25743, 2671, 47, 39, 2786, 7220, 31, 266, 31, 1070, 31, 1393, 31, 36, 706, 25743, 2671, 47, 40, 2786, 7220, 31, 266, 31, 1070, 31, 1393, 31, 36, 706, 25743, 2671, 47, 41, 2786, 7220, 31, 266, 31, 1070, 31, 1393, 31, 36, 706, 25743, 2671, 47, 42, 2786, 7220, 31, 266, 31, 1070, 31, 1393], "continuation_token_count": 114, "decoded": "1]:slide-in-from-top-2 data-[side=2]:slide-in-from-top-2 data-[side=3]:slide-in-from-top-2 data-[side=4]:slide-in-from-top-2 data-[side=5]:slide-in-from-top-2 data-[side=6]:slide-in-from-top-2 data-[side=7]:slide-in-from-top-2 data-[side=8]:slide-in-from-top", "decoded_codepoints": 258, "document_id": "OpenCut-app/OpenCut@4d8c49ed0706c4dc145361e01c6b1f1a87cbb863:apps/web/src/components/ui/context-menu.tsx", "example_id": "00006efb28b7114c084f3ea02254a8ee74d3d85b4053248c9adc3b1d5a13297c", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 90, 7374, 287, 7230, 31, 2273, 27, 1847, 31, 105, 31, 37, 36, 7382, 7374, 287, 3792, 31, 6946, 27, 9973, 31, 106, 31, 3864, 9973, 31, 107, 31, 2837, 13116, 31, 4078, 7481, 31, 15151, 298, 31, 35, 1344, 31, 15151, 31, 29242, 11091, 31, 954, 16911, 31, 35, 16911, 31, 29242, 33, 35, 34, 7459, 31, 35, 34, 34, 18649, 31, 4108, 706, 25743, 2671, 47, 3462, 2786, 7220, 31, 266, 31, 1070, 31, 1393, 31, 36, 706, 25743, 2671, 47, 3, 43, 39, 706, 31, 10687, 44, 15583, 31, 541, 706, 31, 10687, 44, 12231, 31, 541, 31, 34, 706, 31, 10687, 44, 11464, 31, 541, 31, 43, 39, 392, 2615, 14301, 616, 12399, 2962, 111, 291, 1681, 397, 576, 23448, 12216, 32, 2731, 265, 48, 284, 576, 23448, 12216, 32, 18282, 48, 334, 829, 203, 111, 203, 203, 1126, 7049, 2672, 1564, 1371, 2417, 2962, 23557, 7049, 2672, 66, 2], "prompt_token_count": 155, "reference_codepoints": 256, "repo": "OpenCut-app/OpenCut", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [31, 35, 32, 36, 32, 37, 392, 355, 202, 2358, 924, 44, 261, 861, 30, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 1468, 313, 1648], "continuation_token_count": 28, "decoded": "-1.2.3\",\n\t\t\texpectError: true,\n\t\t},\n\t\t{\n\t\t\tname: \"version", "decoded_codepoints": 70, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/server_test.go", "example_id": "0000718b39717c14cbe9781ef5d848cb6ecc481fdec5060dfa0c270dead519b1", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 566, 2062, 44, 313, 19466, 31, 36, 32, 34, 31, 11397, 17423, 392, 355, 202, 2358, 924, 44, 261, 861, 30, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 2033, 313, 2951, 1503, 802, 392, 355, 202, 1580, 2062, 44, 4320, 355, 202, 2358, 924, 44, 261, 861, 30, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 1468, 313, 1648, 802, 623, 41980, 1273, 1289, 1503, 392, 355, 202, 1580, 2062, 44, 261, 313, 11397, 17423, 81, 3, 202, 426, 44, 1468, 313, 1648, 623, 7841, 461, 1968, 5035, 392, 355, 202, 1580, 2062, 44, 261, 313, 19466, 31, 36, 32, 34, 31, 11397, 17423, 81, 35, 32, 36, 32, 37, 29, 1832, 32, 35, 36, 37, 392, 355, 202, 3140, 2062, 44, 313, 35, 32, 36, 32, 37, 29, 1832, 32, 35, 36, 37, 392, 355, 202, 2358, 924, 44, 262, 901, 30, 357, 202, 835, 203, 202, 111, 478, 202, 979, 4950, 11944, 1025, 2155, 3312, 301, 357, 202, 102, 32, 2529, 26, 2251, 32, 426, 30, 3420, 26, 102, 319, 4266, 32, 70, 27, 301, 355, 2], "prompt_token_count": 185, "reference_codepoints": 64, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [44, 397, 17735, 37, 81, 3994, 26, 108, 5344, 293, 397, 415, 1833, 899, 6901, 4428, 2345, 81, 2950, 27, 1276, 308, 14107], "continuation_token_count": 23, "decoded": ":\n sqlite3_free(zSql);\n if ((rc!= SQLITE_OK) || (sqlite", "decoded_codepoints": 65, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:sqlite-vec-rescore.c", "example_id": "000075cda754ba8ace22fb5ae264e513e9a51e669655b1c6246263a338200d8f", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1042, 4026, 1858, 308, 643, 314, 31, 29864, 436, 8117, 3995, 2857, 27, 284, 1288, 5344, 280, 17735, 37, 81, 317, 10744, 88, 26, 291, 313, 6037, 4925, 25937, 105, 1492, 48659, 23, 105, 81, 575, 1262, 81, 24897, 23, 34, 36, 86, 21328, 291, 11608, 643, 314, 14035, 11190, 5578, 30, 4026, 41070, 2370, 1181, 5715, 291, 298, 396, 3968, 558, 30, 298, 396, 16820, 30, 595, 293, 284, 415, 1429, 108, 5344, 27, 3, 30, 429, 35, 30, 549, 6404, 30, 225, 34, 293, 284, 17735, 37, 81, 3994, 26, 108, 5344, 293, 284, 415, 1833, 899, 863, 4428, 2345, 81, 2950, 27, 1276, 308, 14107, 37, 81, 2997, 26, 6404, 27, 863, 4428, 2345, 81, 25001, 490, 301, 397, 319, 30417, 4309, 280, 17735, 37, 81, 317, 10744, 88, 26, 616, 313, 9752, 646, 1487, 7610, 575, 1262, 81, 24897, 23, 34, 36, 86, 25, 11091, 1858, 44, 904, 101, 392, 595, 30, 616, 17735, 37, 81, 530, 2076, 26, 1199, 876, 397, 5552, 283, 2], "prompt_token_count": 170, "reference_codepoints": 64, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289, 31, 1530, 44, 1289], "continuation_token_count": 64, "decoded": "-std: no-std: no-std: no-std: no-std: no-std: no-std: no-std: no-std: no-std: no-std: no-std: no-std: no-std: no-std: no-std: no", "decoded_codepoints": 128, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:engineering-book/src/ch09-no-std-and-feature-verification.md", "example_id": "00007a04c7d0c159ae4d3003d2c50f41cd4c2222b822527746868e94f3b13bd6", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 47690, 23170, 12115, 3125, 1740, 251, 203, 914, 203, 203, 326, 8197, 844, 28334, 2876, 529, 1530, 82, 4777, 203, 31, 3139, 529, 8254, 82, 308, 13966, 312, 3677, 265, 12011, 793, 529, 52, 39444, 82, 645, 529, 3558, 1801, 556, 529, 2888, 35903, 4529, 203, 31, 3139, 529, 3948, 19, 6620, 308, 13966, 12532, 12011, 793, 529, 1262, 403, 3972, 403, 2538, 82, 372, 312, 3112, 27, 203, 31, 3139, 3, 30, 1289, 11154, 308, 23437, 3943, 810, 312, 5624, 17704, 27, 203, 31, 3139, 529, 13219, 82, 308, 539, 529, 12868, 403, 13219, 82, 556, 5624, 31, 10265, 32461, 27, 203, 203, 1482, 19021, 312, 529, 1347, 81, 1530, 82, 390, 3306, 203, 203, 914, 7421, 203, 306, 1561, 33, 1356, 32, 3666, 12011, 312, 1289, 81, 1530, 4253, 8628, 203, 44291, 1347, 81, 1530, 79, 203, 203, 306, 45655, 793, 15121, 18120, 203, 4318, 8628, 6157, 45, 203, 352, 2], "prompt_token_count": 154, "reference_codepoints": 128, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [84, 333, 13663, 396, 2689, 81, 5960, 32, 998, 28, 37, 36, 27, 301, 5024, 81, 874, 84, 280, 13663, 396, 2689, 81, 5960, 32], "continuation_token_count": 25, "decoded": "b < ht->present_bits.count*32) { present_msb = ht->present_bits.", "decoded_codepoints": 64, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/pdb_ext/pdb_builder.c", "example_id": "00007f305e339d69a5183876dc2b6700c967dc878e5f3846fcd64d00c81f92f9", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 77, 91, 614, 24840, 77, 91, 6583, 678, 30, 24840, 77, 91, 6583, 853, 30, 8921, 81, 836, 293, 320, 719, 434, 7596, 2385, 432, 5024, 8153, 688, 884, 5349, 334, 632, 40, 38, 5024, 81, 1112, 81, 998, 280, 225, 34, 45, 334, 632, 40, 38, 5024, 81, 874, 84, 280, 3493, 81, 955, 81, 6979, 81, 990, 81, 452, 81, 1873, 37, 36, 26, 384, 396, 2689, 81, 5960, 30, 225, 34, 30, 13663, 396, 2689, 81, 5960, 32, 998, 28, 37, 36, 30, 225, 35, 293, 334, 415, 308, 2689, 81, 874, 84, 3, 517, 225, 37, 36, 474, 225, 35, 45, 320, 719, 434, 7596, 2385, 432, 8128, 8153, 688, 884, 5349, 334, 632, 40, 38, 8128, 81, 1112, 81, 998, 280, 225, 34, 45, 334, 632, 40, 38, 8128, 81, 874, 84, 280, 3493, 81, 955, 81, 6979, 81, 990, 81, 452, 81, 1873, 37, 36, 26, 384, 396, 11965, 81, 5960, 30, 225, 34, 30, 13663, 396, 11965, 81, 5960, 32, 998, 28, 37, 36, 30, 225, 35, 293, 334, 415, 308, 11965, 81, 874, 84, 333, 13663, 396, 11965, 81, 5960, 32, 998, 28, 37, 36, 27, 301, 8128, 81, 2], "prompt_token_count": 199, "reference_codepoints": 64, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [399, 894, 516, 18698, 1825, 436, 7778, 1011, 3211, 6325, 392, 324, 313, 2272, 438, 312, 1115, 858, 326, 18852, 623, 1629, 17948, 392, 324, 11570, 399], "continuation_token_count": 27, "decoded": " A test EPUB document for MarkItDown testing\",\n \"This is a **test** paragraph with some formatting\",\n \"* A", "decoded_codepoints": 128, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/_test_vectors.py", "example_id": "000089892b6f564782b95e6cdce20bd252b687529644af3b1267fe0af6d427fe", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1006, 6259, 392, 324, 313, 51, 894, 516, 18698, 1825, 436, 7778, 1011, 3211, 6325, 392, 324, 5100, 30980, 225, 35, 44, 2108, 6256, 392, 324, 313, 2272, 438, 312, 1115, 858, 326, 18852, 623, 1629, 17948, 392, 324, 11570, 399, 26285, 2260, 392, 324, 11570, 25281, 2260, 392, 324, 5100, 3, 2298, 81, 1206, 81, 1017, 33792, 284, 2588, 203, 79, 478, 203, 4601, 81, 6333, 81, 3765, 81, 44692, 6535, 280, 428, 284, 2032, 1006, 2863, 26, 291, 4870, 347, 858, 32, 42428, 392, 291, 18346, 681, 347, 3164, 33, 12336, 32, 1676, 18974, 48869, 1966, 31, 1719, 13350, 1107, 32, 1112, 9452, 696, 32, 2812, 392, 291, 8485, 47, 2521, 30, 291, 1984, 47, 2521, 30, 291, 2298, 81, 266, 2], "prompt_token_count": 125, "reference_codepoints": 128, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [363, 442, 312, 1149, 432, 1169, 4684, 291, 415, 5703, 44, 324, 1169], "continuation_token_count": 13, "decoded": "and return a list of all objects\n if images:\n all", "decoded_codepoints": 67, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py", "example_id": "000098f3e3e8c6d24899e066f3b2a9819db9fccabe9eb97ff0ce377f0212e45a", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 300, 32, 2242, 584, 588, 5393, 225, 36, 44, 1670, 1289, 5703, 2431, 30, 1596, 13266, 15341, 4684, 291, 415, 646, 5703, 461, 19326, 26, 1637, 30, 313, 5740, 657, 461, 313, 893, 20, 328, 1938, 32, 5740, 44, 324, 5703, 280, 1938, 32, 5740, 32, 371, 440, 893, 392, 11544, 584, 588, 5393, 225, 37, 44, 8959, 17495, 1169, 4684, 225, 3, 10280, 324, 1169, 81, 25057, 280, 1938, 32, 5740, 324, 436, 2830, 81, 681, 328, 1169, 81, 25057, 32, 3494, 2262, 400, 415, 313, 893, 20, 328, 2830, 81, 681, 32, 5729, 346, 556, 313, 106, 1473, 20, 328, 2830, 81, 681, 32, 5729, 2262, 528, 13792, 81, 18021, 280, 1169, 81, 25057, 32, 371, 26, 2067, 81, 681, 30, 11544, 528, 415, 8476, 2], "prompt_token_count": 129, "reference_codepoints": 64, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [32, 313, 324, 313, 4282, 883, 2329, 793], "continuation_token_count": 8, "decoded": ". \"\n \"You can also use", "decoded_codepoints": 33, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:examples/rag_dynamic_tools_multi_turn/src/main.rs", "example_id": "000099966f304afa66a5c502122c2c00c38dc689c15047fccde6053fe4b27d21", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 407, 13012, 461, 312, 7094, 4559, 1914, 284, 1207, 37464, 81, 2453, 280, 2156, 3044, 81, 1580, 291, 638, 4867, 26, 1676, 3044, 403, 57, 3655, 81, 38, 27, 291, 638, 1001, 35758, 26, 324, 313, 4282, 884, 312, 37464, 2442, 372, 3049, 322, 1256, 4436, 34461, 7373, 32, 324, 4417, 322, 8684, 3943, 372, 7592, 3, 1409, 1346, 7744, 544, 1370, 4369, 4414, 291, 829, 291, 434, 2222, 312, 7094, 4559, 1914, 623, 312, 3964, 7692, 432, 225, 36, 308, 91, 32, 87, 21190, 1755, 291, 434, 225, 36, 5388, 4559, 1098, 526, 3640, 372, 29010, 1421, 27, 291, 638, 35063, 2236, 81, 4280, 26, 36, 30, 1650, 30, 4559, 470, 27, 291, 638, 1832, 473, 446, 434, 39626, 322, 7669, 461, 225, 2], "prompt_token_count": 126, "reference_codepoints": 32, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [25, 7007, 950, 225, 35, 1790, 434, 10388, 397, 638, 3613, 17923], "continuation_token_count": 12, "decoded": "'pay': 1 }) // pay\n .mockResolved", "decoded_codepoints": 38, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/bilibili/download.test.js", "example_id": "00009b70d9b014a4229eca917786eb4daa30fbbe77b938d7fea415fdb0e4bd26", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 3046, 944, 4993, 547, 37279, 26, 35, 293, 334, 1122, 719, 561, 463, 5117, 23132, 779, 81, 11844, 436, 5809, 31, 2585, 323, 742, 26241, 1412, 3497, 1401, 1289, 354, 639, 370, 2498, 1404, 532, 301, 284, 4395, 2551, 936, 397, 638, 3613, 17923, 882, 9297, 26, 1071, 7935, 1371, 4751, 44, 301, 10388, 44, 225, 35, 320, 16586, 434, 2202, 397, 638, 3613, 17923, 882, 9297, 1371, 225, 3, 1916, 434, 7394, 446, 2014, 1424, 26, 397, 2016, 32, 1298, 26, 1637, 30, 301, 323, 3843, 44, 330, 22891, 35, 2369, 38, 35, 35, 85, 41, 95, 54, 370, 1688, 44, 3005, 97, 370, 13090, 44, 330, 8773, 370, 7650, 44, 901, 7305, 284, 6804, 11592, 101, 32, 452, 42295, 107, 1162, 530, 27, 532, 1137, 5113, 27070, 924, 962, 1137, 32, 687, 1720, 330, 9607, 779, 81, 11844, 895, 284, 1424, 26, 3613, 7495, 4993, 547, 1206, 32, 452, 24554, 2], "prompt_token_count": 154, "reference_codepoints": 32, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [87, 1015, 313, 1726, 4568, 44, 517, 20, 372, 322, 5750, 203], "continuation_token_count": 12, "decoded": "e add \"Disallow: /\" to the rule\n", "decoded_codepoints": 32, "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:cmd/robots2policy/main.go", "example_id": "00009b883ad7e630ca41a5fefd782cb9459926225c09f31d782234cc9d45612d", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 265, 41141, 27, 848, 225, 34, 962, 786, 863, 3330, 301, 603, 202, 1700, 6668, 101, 280, 5489, 26, 1700, 6668, 101, 30, 786, 27, 355, 202, 111, 1314, 202, 1732, 313, 33982, 31, 7843, 563, 355, 202, 325, 2069, 26, 26395, 41141, 27, 848, 225, 34, 301, 603, 202, 325, 7808, 30, 1137, 1025, 12123, 11691, 26, 853, 293, 1137, 610, 1302, 301, 577, 202, 1700, 53, 17734, 8211, 280, 7808, 603, 202, 111, 355, 202, 111, 357, 202, 111, 203, 202, 111, 478, 202, 306, 12029, 25, 3, 203, 202, 325, 2069, 26, 26395, 41141, 27, 848, 225, 34, 301, 357, 202, 5275, 1025, 1487, 3842, 1792, 6067, 32670, 26, 26395, 41141, 30, 1550, 1726, 36497, 30, 1550, 6668, 101, 30, 1550, 53, 17734, 8211, 27, 357, 202, 7004, 280, 5489, 26, 7004, 30, 5750, 27, 203, 202, 111, 478, 202, 306, 7778, 6176, 29165, 1256, 25136, 308, 349, 2475, 623, 313, 1726, 4568, 44, 517, 657, 203, 202, 979, 595, 1025, 2155, 7019, 2], "prompt_token_count": 168, "reference_codepoints": 32, "repo": "TecharoHQ/anubis", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [47, 1181, 45, 397, 963, 280, 5980, 32, 1676, 4764, 26, 2995, 30, 5736, 293, 397, 442, 963, 45, 284, 320, 2368, 308, 87, 27, 301, 397, 442, 744, 45, 284, 320, 334, 320, 2368, 308, 87, 27, 301, 284, 442, 744, 45, 334, 320, 203, 111, 203, 203, 306, 358, 22109, 31, 4770, 5489, 32, 18993, 2935, 31, 1515, 474, 27625, 31, 1977, 7019, 619, 10061, 2538, 5260, 30, 203, 306, 1273, 28089, 623, 546, 81, 18472, 1259, 22493], "continuation_token_count": 80, "decoded": "= NULL;\n out = fs.openSync(fd, flags);\n return out;\n } catch (e) {\n return null;\n }\n } catch (e) {\n return null;\n }\n}\n\n// Symlink-safe append. Same parent-dir + symlink-target rules as safeWriteFlag,\n// but opens with O_APPEND so concurrent", "decoded_codepoints": 266, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/hooks/caveman-config.js", "example_id": "0000a012307d86631cf97ed5d3ef927a00d4a4b3b6a8b95309c923711644b58f", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 389, 744, 45, 446, 660, 546, 81, 2576, 38037, 280, 5940, 5980, 32, 9777, 32, 65, 81, 2576, 38037, 1720, 330, 2171, 25, 1018, 5980, 32, 9777, 32, 65, 81, 2576, 38037, 499, 225, 34, 45, 284, 660, 5736, 280, 5980, 32, 9777, 32, 65, 81, 12733, 13008, 523, 546, 81, 2576, 38037, 45, 284, 1207, 9899, 45, 284, 1207, 963, 45, 284, 1596, 301, 397, 9899, 280, 5980, 32, 1676, 4764, 26, 4555, 1215, 30, 5736, 293, 397, 660, 4845, 225, 3, 3836, 5915, 81, 48416, 32, 6411, 26, 1294, 490, 442, 744, 45, 284, 442, 5081, 45, 334, 320, 2368, 308, 87, 27, 301, 284, 442, 744, 45, 334, 320, 203, 111, 203, 203, 306, 358, 22109, 31, 4770, 5489, 32, 18993, 2935, 31, 1515, 474, 27625, 31, 1977, 7019, 619, 10061, 2538, 5260, 30, 203, 306, 1273, 28089, 623, 546, 81, 18472, 1259, 22493, 2870, 483, 645, 3449, 20996, 2800, 25, 2], "prompt_token_count": 156, "reference_codepoints": 256, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [283, 463, 7668, 44, 428, 301, 3835, 44, 861, 801, 301, 2287, 44, 330, 14554, 370, 1623, 81, 314, 44, 330, 35, 36, 37, 38, 39, 40, 41, 42, 43, 34, 35, 36, 370, 1984, 44, 330, 641, 555, 1499, 32, 41656, 13026, 32, 508, 33, 1094, 49, 314, 47, 35, 36, 37, 38, 39, 40, 41, 42, 43, 34, 35, 36, 25, 801], "continuation_token_count": 64, "decoded": "it('uses: [ { ok: true }, { status: 'published', item_id: '123456789012', url: 'https://www.goofish.com/item?id=123456789012' },", "decoded_codepoints": 128, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/xianyu/publish.test.js", "example_id": "0000ad40c66202fd12b203a339c2cd3a70f879cc3bf192af25fc1226526407b6", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 16370, 44, 2107, 1311, 370, 330, 2310, 370, 330, 4415, 370, 330, 4742, 2188, 5816, 44, 1605, 801, 400, 301, 3835, 44, 861, 801, 400, 301, 2287, 44, 330, 14554, 370, 1623, 81, 314, 44, 330, 35, 36, 37, 38, 39, 40, 41, 42, 43, 34, 35, 36, 370, 1984, 44, 330, 641, 555, 1499, 32, 41656, 13026, 32, 508, 33, 1094, 49, 314, 47, 35, 36, 37, 38, 39, 40, 41, 42, 43, 34, 35, 36, 25, 801, 324, 2505, 291, 1122, 11268, 3, 958, 1623, 81, 314, 44, 330, 35, 36, 37, 38, 39, 40, 41, 42, 43, 34, 35, 36, 370, 324, 1780, 44, 330, 7999, 6588, 1312, 370, 324, 7661, 44, 330, 143, 117, 39, 43, 43, 43, 32, 43, 43, 370, 324, 3700, 44, 330, 39211, 8876, 4690, 370, 324, 1984, 44, 330, 641, 555, 1499, 32, 41656, 13026, 32, 508, 33, 1094, 49, 314, 47, 35, 36, 37, 38, 39, 40, 41, 42, 43, 34, 35, 36, 370, 324, 1474, 44, 330, 26531, 11798, 370, 291, 41923, 284, 1122, 446, 561, 463, 7668, 2], "prompt_token_count": 181, "reference_codepoints": 128, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [20, 110, 2767, 636, 28664, 19452, 7945, 110, 89, 25, 3941, 5474, 20, 1276, 442, 225, 35, 397, 12109, 429, 91, 313], "continuation_token_count": 22, "decoded": "\"|where name=\"%USERNAME%\"|g' \"$asset\" || return 1\n sed -i \"", "decoded_codepoints": 64, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/answer.sh", "example_id": "0000af6b4b34f21a1d5dbd00fc6d7eff9ec6f1432c0ba962f1579ec72b28d089", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 225, 2196, 1256, 81, 2593, 397, 1256, 81, 2593, 9456, 11731, 5732, 69, 318, 3941, 496, 657, 1276, 442, 225, 35, 1687, 12109, 429, 91, 313, 101, 10183, 426, 4034, 11652, 1492, 10183, 426, 4034, 39779, 2121, 44, 19452, 1492, 110, 89, 20, 3941, 5474, 20, 1276, 442, 225, 35, 397, 12109, 429, 91, 330, 101, 110, 2767, 636, 347, 11652, 20, 110, 2767, 636, 28664, 19452, 7945, 110, 89, 25, 3941, 5474, 20, 1276, 442, 225, 35, 397, 12109, 429, 91, 313, 101, 16214, 558, 3, 264, 12109, 429, 91, 313, 101, 16214, 16058, 48, 11652, 377, 16058, 34890, 16058, 17124, 496, 81, 2593, 377, 16058, 25894, 89, 20, 3941, 5474, 20, 1276, 442, 225, 35, 397, 12109, 429, 91, 313, 101, 16214, 8650, 48, 11652, 377, 8650, 34890, 8650, 17124, 496, 81, 2593, 377, 8650, 25894, 89, 20, 3941, 5474, 20, 1276, 442, 225, 35, 284, 8058, 446, 2196, 3097, 9483, 13001, 5979, 2300, 3845, 284, 2196, 21959, 47927, 2], "prompt_token_count": 163, "reference_codepoints": 64, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [32, 203, 306, 203, 306, 886, 5750, 470, 438, 33714, 1755], "continuation_token_count": 11, "decoded": ".\n//\n// The ruleset is injected only", "decoded_codepoints": 36, "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:hooks/ponytail-subagent.js", "example_id": "0000b128a4b537563823c872fcdeb69a913133e1d2893e56b9ffcd0fa1c69381", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2130, 1619, 438, 2935, 31, 3426, 1755, 461, 7152, 38512, 1361, 22705, 30, 1259, 203, 306, 2876, 458, 3638, 4187, 31, 15697, 318, 7669, 9792, 298, 4359, 9793, 31, 311, 32811, 308, 7092, 588, 36, 39, 36, 547, 203, 306, 5076, 298, 4359, 9793, 2926, 438, 4523, 30, 12202, 322, 2432, 5750, 470, 1991, 2504, 1361, 4867, 32, 203, 306, 203, 306, 358, 331, 7075, 308, 2215, 31, 266, 30, 2427, 588, 39, 34, 40, 27, 3, 452, 312, 9667, 461, 203, 306, 322, 5750, 470, 438, 33714, 1755, 1991, 1361, 22705, 13696, 7669, 81, 681, 8001, 32, 886, 203, 306, 9667, 438, 707, 2638, 12837, 461, 1135, 31, 2372, 10467, 12011, 313, 34870, 110, 8304, 20, 8001, 3154, 30, 203, 306, 9044, 8304, 11033, 438, 7153, 32, 1683, 470, 6058, 12202, 1991, 3638, 1361, 4867, 30, 619, 2670, 32, 203, 203, 913, 301, 2], "prompt_token_count": 146, "reference_codepoints": 32, "repo": "DietrichGebert/ponytail", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [17770, 44, 529, 730, 312, 280, 5630, 26, 965, 547, 6240, 45, 1207, 323, 280, 5630, 26, 965, 547, 6240, 29017, 438, 36834, 19, 203, 48, 886, 3100, 10396, 6240, 82, 4163, 1330, 1477, 6222, 322, 1932, 44117, 32, 4417, 529, 2524, 44410, 556, 203, 48, 529, 15697, 82, 436, 35785, 32, 203, 203, 433, 12020, 37096, 44, 8091, 2563, 312, 677, 3280, 35548, 4851, 203, 203, 51, 4011, 31, 5860, 225, 36, 34, 35, 42, 31, 34, 42, 31, 36, 35, 203], "continuation_token_count": 83, "decoded": "trap: `let a = fetch(url).await; let b = fetch(url).await;` is sequential!\n> The second `.await` doesn't start until the first finishes. Use `join!` or\n> `spawn` for concurrency.\n\n## Case Study: Debugging a Hung Production Service\n\nA real-world 2018-08-21\n", "decoded_codepoints": 256, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:async-book/src/ch12-common-pitfalls.md", "example_id": "0000b262d7f3fa9e6ae5dc2587e54db72b2dd37850ac7b2f4cc265a4da153934", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 264, 1207, 323, 280, 5630, 440, 965, 81, 84, 1895, 6240, 45, 434, 225, 35, 3100, 308, 1684, 101, 436, 312, 372, 11361, 1932, 18728, 203, 111, 203, 203, 306, 41889, 2198, 13926, 44, 37212, 225, 35, 3100, 3380, 203, 4396, 2771, 8117, 346, 301, 284, 1207, 308, 83, 30, 323, 27, 280, 20008, 716, 403, 2524, 4482, 291, 5630, 440, 965, 81, 83, 2113, 434, 23730, 1477, 13282, 291, 5630, 440, 965, 81, 84, 2113, 284, 1093, 203, 111, 203, 203, 306, 41889, 225, 3, 914, 203, 203, 48, 1115, 38651, 4914, 529, 730, 312, 280, 5630, 26, 965, 547, 6240, 45, 1207, 323, 280, 5630, 26, 965, 547, 6240, 29017, 438, 36834, 19, 203, 48, 886, 3100, 10396, 6240, 82, 4163, 1330, 1477, 6222, 322, 1932, 44117, 32, 4417, 529, 2524, 44410, 556, 203, 48, 529, 15697, 82, 436, 35785, 32, 203, 203, 433, 12020, 37096, 44, 8091, 2563, 312, 677, 3280, 35548, 4851, 203, 203, 51, 4011, 31, 5860, 225, 2], "prompt_token_count": 165, "reference_codepoints": 256, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [264, 442, 313, 7075, 81, 2951, 866, 284, 320, 446, 2771, 3377, 1652, 784, 27, 967, 26024], "continuation_token_count": 17, "decoded": " return \"ping_empty\";\n }\n\n fn parameters(&self) -> serde", "decoded_codepoints": 65, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:tests/providers/openrouter/cassette/agent_tool_sessions.rs", "example_id": "0000b7423aef7f0f13943b93fd243d89c699e48b5a0d874ab98949b627b658fb", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 847, 440, 2848, 4559, 1048, 3830, 203, 1167, 6548, 3653, 924, 45, 203, 203, 3106, 10018, 436, 33694, 2766, 301, 284, 660, 8912, 44, 15068, 1574, 596, 280, 313, 7075, 81, 2951, 866, 284, 827, 3081, 280, 6548, 3653, 924, 45, 284, 827, 10460, 280, 14893, 3080, 45, 284, 827, 5582, 280, 892, 45, 446, 2771, 3048, 1652, 784, 27, 967, 892, 301, 275, 3, 284, 320, 446, 2771, 3377, 1652, 784, 27, 967, 26024, 81, 1260, 403, 882, 301, 291, 2361, 19, 1371, 324, 313, 681, 563, 313, 1473, 392, 324, 313, 4642, 563, 6663, 324, 313, 3648, 563, 1605, 291, 1790, 284, 320, 446, 2498, 2771, 1476, 26, 291, 549, 784, 30, 291, 617, 1819, 44, 549, 2278, 34315, 403, 3732, 403, 3653, 1222, 2], "prompt_token_count": 128, "reference_codepoints": 64, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [27, 355, 202, 32, 1286, 26, 55, 4047, 1394, 32, 1711, 32, 28442, 27, 355, 202, 32, 1286, 26, 55, 4047, 1394, 32, 1711, 32, 28442, 27, 355, 202, 32, 1286, 26, 55, 4047, 1394, 32, 1711, 32, 28442, 27, 355, 202, 32, 1286, 26, 55, 4047, 1394, 32, 1711, 32, 28442, 27, 355, 202, 32, 1286, 26, 55, 4047, 1394, 32, 1711, 32, 28442, 27, 355, 202, 32, 1286, 26, 55, 4047, 1394, 32, 1711, 32, 28442, 27, 355, 202, 32, 1286, 26, 55, 4047], "continuation_token_count": 86, "decoded": ")\n\t\t\t.content(ElicitResult.Action.ACCEPT)\n\t\t\t.content(ElicitResult.Action.ACCEPT)\n\t\t\t.content(ElicitResult.Action.ACCEPT)\n\t\t\t.content(ElicitResult.Action.ACCEPT)\n\t\t\t.content(ElicitResult.Action.ACCEPT)\n\t\t\t.content(ElicitResult.Action.ACCEPT)\n\t\t\t.content(Elicit", "decoded_codepoints": 260, "document_id": "modelcontextprotocol/java-sdk@fd004989b9484c9b81be6b03463396797b354804:mcp-test/src/main/java/io/modelcontextprotocol/client/AbstractMcpAsyncClientTests.java", "example_id": "0000be41e39c796fdf1c5f3f6922db37d1fe1731ed7c84bb8ee75c1cfccf716a", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1111, 473, 603, 202, 1916, 203, 202, 111, 478, 202, 50, 1006, 203, 202, 1117, 894, 9962, 1554, 55, 4047, 367, 19522, 346, 301, 357, 202, 1486, 17655, 18804, 280, 5675, 17655, 32, 4164, 922, 342, 295, 9982, 922, 1832, 473, 357, 202, 55, 4047, 1394, 709, 295, 283, 1394, 280, 516, 4047, 1394, 32, 4164, 26, 55, 4047, 1394, 32, 1711, 32, 28442, 27, 355, 202, 32, 1286, 26, 3, 403, 3780, 1883, 547, 6967, 7371, 473, 603, 202, 1916, 203, 202, 111, 478, 202, 50, 1006, 203, 202, 1117, 894, 9962, 1554, 1934, 17655, 346, 301, 357, 202, 869, 18804, 280, 5675, 17655, 32, 4164, 346, 355, 202, 32, 19561, 26, 1208, 32, 1028, 440, 3274, 392, 3516, 32, 1028, 440, 3274, 5260, 392, 861, 2610, 355, 202, 32, 32071, 26, 1508, 27, 355, 202, 32, 22979, 346, 355, 202, 32, 1832, 473, 1314, 202, 30617, 2], "prompt_token_count": 150, "reference_codepoints": 256, "repo": "modelcontextprotocol/java-sdk", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [293, 334, 24622, 2102, 473, 719, 24622, 5942, 440, 2538, 570, 2123, 3677, 1858, 724, 334, 345, 6449, 81, 2238, 81, 1821, 81, 1167, 26, 874, 88, 30, 485, 3434, 81, 4636, 30, 549, 1832, 32, 2111, 293, 334, 24622, 2102, 473, 719, 24622], "continuation_token_count": 44, "decoded": ");\n ProfEnd();\n\n ProfBegin(\"Write GSI hash table\");\n msf_stream_write_struct(msf, gsi_sn, &build.header);\n ProfEnd();\n\n Prof", "decoded_codepoints": 129, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/pdb_ext/pdb_builder.c", "example_id": "0000cbaf92b3f47bc0e7eb0d50ce4d5e32b6c6af53768f067889226e666767b5", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1246, 81, 6452, 81, 846, 77, 34, 1130, 319, 1968, 32, 15823, 81, 6452, 81, 998, 45, 334, 632, 40, 38, 485, 3434, 81, 891, 6019, 280, 3744, 26, 1832, 32, 2111, 27, 474, 3677, 81, 4133, 81, 846, 81, 891, 474, 15608, 81, 891, 474, 21331, 81, 6452, 81, 846, 81, 891, 45, 4059, 24622, 5942, 72, 440, 34581, 904, 63, 436, 570, 2123, 3677, 1858, 392, 485, 3434, 81, 891, 293, 334, 345, 6449, 81, 2238, 81, 19871, 26, 3, 19111, 81, 4636, 30, 1968, 32, 7010, 81, 605, 32, 891, 293, 334, 24622, 2102, 473, 719, 24622, 5942, 440, 2538, 570, 2123, 3338, 724, 334, 345, 6449, 81, 2238, 81, 1821, 81, 1167, 26, 874, 88, 30, 485, 3434, 81, 4636, 30, 549, 1832, 32, 2111, 293, 334, 24622, 2102, 473, 719, 24622, 5942, 440, 2538, 3677, 9212, 18025, 63, 9166, 3677, 81, 4133, 81, 846, 81, 891, 293, 334, 345, 6449, 81, 2238, 81, 1821, 81, 13449, 26, 491, 30, 345, 6449, 30, 485, 3434, 81, 2], "prompt_token_count": 172, "reference_codepoints": 128, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [601, 2361, 45, 284, 320, 284, 4247, 683, 284, 2014, 1420, 8453, 4901, 1517, 370, 11363, 1260, 2188, 301, 24390, 44, 1123, 9335, 30, 4533, 44, 40045, 6052, 1122, 284, 1424, 26, 1267, 32, 4775, 1227], "continuation_token_count": 36, "decoded": "return json;\n }\n ''')\n await runCLI(['status', '--json'], { cwd: appRepo, env: isolatedEnv });\n expect(result.exitCode", "decoded_codepoints": 130, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/commands/store-root-selection.test.ts", "example_id": "0000cec7bedcc3348c73f92ef3e17d37d4d3839bfdb11f60d592a65b5fae1a7b", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 262, 2417, 2121, 30, 291, 1593, 19771, 81, 4601, 81, 8439, 44, 1519, 32, 2524, 26, 1433, 2976, 30, 330, 605, 31, 2951, 1425, 397, 1472, 1687, 660, 1056, 280, 2014, 1420, 8453, 4901, 1517, 370, 11363, 1260, 2188, 301, 24390, 44, 1123, 9335, 30, 4533, 44, 40045, 6052, 1122, 397, 1424, 26, 1267, 32, 4775, 1227, 547, 5492, 26, 34, 293, 397, 660, 2361, 280, 3185, 2526, 26, 1267, 293, 1568, 3, 3780, 31, 17107, 370, 1404, 532, 301, 284, 561, 463, 25201, 2876, 312, 1539, 636, 4174, 432, 14937, 312, 26420, 370, 2498, 1404, 532, 301, 397, 1487, 1791, 26, 2157, 4058, 30, 330, 2157, 31, 2342, 895, 1687, 660, 1056, 280, 2014, 1420, 8453, 4901, 8929, 370, 11363, 2157, 370, 330, 5883, 31, 1819, 370, 11363, 1260, 2188, 301, 291, 24390, 44, 1123, 2], "prompt_token_count": 138, "reference_codepoints": 128, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [1468, 1858, 81, 2875, 1454, 225, 35, 446, 665, 894, 81, 1274, 81, 1793, 81, 2951, 81, 1286], "continuation_token_count": 18, "decoded": " table_idx += 1\n\n def test_table_with_empty_content", "decoded_codepoints": 65, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_pdf_tables.py", "example_id": "0000d1e7694c9f47766ff7758f90c54d77f3bd3b669ca20f8bb7945cb6039d0e", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2040, 821, 6225, 1591, 2623, 308, 7413, 31, 26398, 1795, 27, 400, 436, 2698, 81, 2875, 30, 2698, 328, 10703, 26, 1274, 711, 528, 1201, 308, 715, 2069, 26, 643, 27, 2377, 225, 35, 528, 2588, 296, 9588, 4682, 81, 761, 10696, 5548, 301, 1274, 81, 2875, 835, 2698, 301, 643, 81, 2875, 111, 1401, 1289, 6090, 20, 203, 3, 2071, 2698, 81, 1286, 280, 313, 4939, 2524, 26, 3376, 32, 7201, 346, 436, 4020, 328, 2698, 27, 528, 1201, 308, 715, 2069, 26, 643, 81, 1286, 32, 7201, 1157, 848, 225, 34, 528, 2588, 296, 9588, 4682, 81, 761, 10696, 5548, 301, 1274, 81, 2875, 835, 2698, 301, 643, 81, 2875, 111, 438, 3502, 20, 446, 665, 894, 81, 3478, 2274, 81, 2], "prompt_token_count": 125, "reference_codepoints": 64, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [18581, 1122, 397, 2014, 5980, 32, 3925, 26, 22324, 32, 371, 21366, 1215, 1026, 301, 18581, 44, 18581, 1122, 397, 2014, 5980, 32, 3925, 26, 22324, 32, 371, 21366], "continuation_token_count": 29, "decoded": " recursive });\n await fs.rm(installer.getInstallationPath(), { recursive: recursive });\n await fs.rm(installer.getInstallation", "decoded_codepoints": 136, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/completions/installers/powershell-installer.test.ts", "example_id": "0000dc082a8f0c8673a1d5edcf6af7a9c3dcc030814e922617f10951164d4f03", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 293, 397, 660, 1056, 280, 2014, 1869, 9000, 30608, 32, 3789, 26, 3613, 11932, 3206, 293, 1687, 1424, 26, 1267, 32, 3127, 547, 5492, 26, 1508, 293, 397, 1424, 26, 1267, 32, 18132, 1215, 547, 38047, 463, 11593, 897, 13106, 11390, 894, 895, 1687, 434, 31458, 397, 2014, 5980, 32, 3925, 26, 19985, 4625, 2976, 30, 301, 18581, 44, 3, 33, 4017, 5251, 27379, 101, 1510, 4004, 32, 754, 22264, 4163, 1330, 3498, 284, 561, 32, 5961, 2797, 26, 2416, 32, 5134, 1720, 330, 4463, 37, 36, 683, 463, 3163, 442, 7829, 544, 6501, 1048, 370, 2498, 1404, 532, 301, 397, 660, 1760, 1215, 280, 25079, 32, 371, 21366, 1215, 473, 397, 660, 1760, 2976, 280, 1519, 32, 7781, 26, 1349, 2], "prompt_token_count": 123, "reference_codepoints": 128, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [261, 2505, 291, 2298, 81, 1206, 81, 1017, 18278], "continuation_token_count": 9, "decoded": " ],\n must_not_include=[\"", "decoded_codepoints": 33, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/_test_vectors.py", "example_id": "0000dfd5628ca91e4d63717a64e69ad65c1ec21713c5ffc900d2b83fd44a4cc4", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 20, 858, 81, 17260, 32, 2593, 392, 291, 18346, 681, 347, 878, 33, 2593, 392, 291, 8485, 347, 3310, 31, 42, 392, 291, 1984, 47, 2521, 30, 291, 2298, 81, 1017, 6020, 324, 5100, 886, 43788, 564, 3787, 20019, 392, 324, 313, 433, 36458, 659, 225, 36, 34, 36, 38, 44, 16239, 37086, 225, 41, 34, 23, 432, 322, 36101, 6854, 225, 39, 34, 34, 2464, 793, 3787, 225, 37, 40, 39, 390, 48858, 392, 397, 3, 39364, 861, 688, 322, 29404, 438, 14089, 6971, 1092, 22065, 8117, 392, 291, 2505, 291, 2298, 81, 1206, 81, 1017, 18278, 46, 17260, 392, 3778, 6528, 3439, 284, 2588, 284, 2032, 1006, 2863, 26, 291, 4870, 347, 858, 81, 22451, 32, 21963, 392, 291, 18346, 681, 347, 3164, 33, 1260, 392, 291, 8485, 347, 14510, 392, 291, 1044, 2], "prompt_token_count": 137, "reference_codepoints": 32, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [1338, 280, 2075, 32, 13874, 7926, 32, 13874, 2019, 45, 334, 415, 1429, 1338, 27, 301, 284, 442, 45, 334, 320, 719, 660, 225, 1338, 280, 3099, 32, 13874, 7926, 32, 13874, 2019, 45, 334, 415, 1429, 1338, 27, 301, 284, 442, 45, 334, 320, 719, 660, 225, 1338, 280, 3099, 32, 13874, 7926, 32, 13874, 2019, 45, 334, 415, 1429, 1338, 27, 301, 284, 442, 45, 334, 320, 719, 660, 225, 1338, 280, 3099, 32, 13874], "continuation_token_count": 77, "decoded": "info = options.upgradePlan.upgradeCommand;\n if (!info) {\n return;\n }\n\n const info = info.upgradePlan.upgradeCommand;\n if (!info) {\n return;\n }\n\n const info = info.upgradePlan.upgradeCommand;\n if (!info) {\n return;\n }\n\n const info = info.upgrade", "decoded_codepoints": 262, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/commands/upgrade.ts", "example_id": "0000e7bde751744a602f62f3f34cbae28176fa611000b5122ea4e9c5045b3db3", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1667, 1970, 32, 14970, 26, 1338, 32, 13874, 7926, 32, 2751, 2019, 4370, 1801, 334, 6712, 334, 2014, 3634, 2333, 6253, 29059, 26, 1338, 32, 5323, 2062, 293, 334, 1245, 32, 5006, 473, 203, 111, 203, 203, 4396, 667, 10750, 2019, 26, 2184, 44, 23977, 2031, 711, 4664, 46, 1117, 48, 301, 334, 4562, 1151, 440, 2501, 392, 301, 636, 44, 313, 13874, 20, 1122, 719, 660, 225, 3, 225, 442, 45, 334, 320, 719, 415, 1429, 1338, 32, 1877, 8589, 27, 301, 284, 1245, 32, 3127, 4199, 2095, 41, 438, 973, 372, 2340, 36591, 1970, 32, 8570, 4199, 104, 1667, 4530, 20824, 1748, 9796, 284, 442, 45, 334, 320, 719, 1245, 32, 5006, 473, 334, 1245, 32, 1338, 26, 284, 529, 2333, 3304, 44, 2283, 1970, 32, 8570, 4199, 104, 1667, 1338, 32, 1700, 2062, 5325, 4370, 2283, 1970, 32, 3534, 440, 396, 25651, 2283, 1970, 32, 8570, 4199, 104, 1667, 1338, 32, 4474, 2], "prompt_token_count": 157, "reference_codepoints": 256, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [225, 1938, 280, 3692, 32, 371, 81, 1637, 26, 1637, 81, 314, 27, 291, 415, 1938, 438, 1665, 44, 324, 3636, 6012, 5965, 26, 1637, 81, 314, 27, 584, 588, 3456, 415, 322, 1938, 438, 3425, 328, 7652, 291, 415, 1938, 32, 297, 81, 266, 81, 5207, 44, 324, 3636, 6012, 16379, 383, 4764, 26, 1637, 81, 314, 27, 584, 588, 3456, 415, 322, 1938, 438, 23616], "continuation_token_count": 67, "decoded": " page = ctx.get_page(page_id)\n if page is None:\n raise PageNotFound(page_id)\n\n # Check if the page is already in sync\n if page.is_in_sync:\n raise PageAlreadyInSync(page_id)\n\n # Check if the page is blocked", "decoded_codepoints": 256, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/_browsers/_base.py", "example_id": "0000ee13063f41473104bb0659f9b21c7bd534336b0f06a668f105ada4c85ca7", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 97, 6369, 291, 1524, 936, 312, 537, 1938, 372, 793, 2993, 291, 588, 3139, 1849, 372, 1505, 415, 312, 1938, 438, 3304, 556, 646, 328, 7652, 1340, 3301, 322, 1340, 23616, 2670, 316, 9469, 2442, 12430, 322, 1938, 8777, 30, 432, 85, 32, 291, 3692, 280, 1619, 415, 1619, 438, 646, 1665, 813, 630, 32, 1819, 1568, 3, 81, 5078, 27, 584, 415, 7378, 81, 5379, 556, 23616, 81, 20798, 44, 324, 1938, 32, 4351, 440, 326, 1109, 392, 1487, 81, 25946, 81, 4531, 26, 5820, 81, 5379, 30, 23616, 81, 20798, 490, 291, 1938, 81, 1338, 280, 630, 32, 1637, 81, 5178, 32, 669, 81, 1637, 26, 1637, 27, 291, 1938, 81, 1338, 32, 1826, 81, 20227, 346, 291, 442, 1938, 81, 5267, 2], "prompt_token_count": 126, "reference_codepoints": 256, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [1382, 2432, 619, 322, 11668, 328, 322, 529, 7421], "continuation_token_count": 9, "decoded": "the same as the ones in the `rust", "decoded_codepoints": 33, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:c-cpp-book/src/ch05-data-structures.md", "example_id": "0000f0f14f75a0308e863838f42d9a34b3d35f52b3ae48eaa07bdab1d818fdbb", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 340, 293, 664, 1207, 1044, 499, 308, 103, 37, 36, 30, 1560, 27, 280, 308, 38, 37, 30, 901, 293, 664, 11662, 9170, 6807, 12263, 273, 32, 34, 30, 273, 32, 35, 293, 664, 11662, 9170, 6807, 12263, 1044, 32, 34, 30, 1044, 32, 35, 293, 664, 1207, 308, 1516, 30, 4655, 27, 280, 622, 81, 7288, 473, 434, 11713, 42670, 4093, 664, 11662, 9170, 109, 1516, 835, 301, 4555, 13626, 203, 111, 203, 914, 203, 203, 1482, 19281, 10647, 203, 31, 30268, 328, 19281, 884, 45931, 225, 3, 1629, 1202, 21005, 284, 429, 2030, 438, 23452, 372, 1159, 1346, 1451, 432, 1491, 31, 2585, 308, 28719, 27, 10647, 372, 312, 2677, 821, 1346, 2260, 432, 1133, 32, 399, 4121, 4881, 963, 9732, 322, 2677, 4576, 308, 578, 438, 312, 1202, 10243, 3823, 1115, 30179, 326, 45, 23188, 328, 9355, 6125, 27, 284, 429, 2704, 2], "prompt_token_count": 147, "reference_codepoints": 32, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [6558, 280, 24930, 2108, 6577, 203, 203, 433, 6988, 10884, 23496, 203, 203, 1482, 48172, 44, 13907], "continuation_token_count": 17, "decoded": "delta = `# Test Spec\n\n## ADDED Requirements\n\n### Requirement: Notes", "decoded_codepoints": 67, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/validation.test.ts", "example_id": "0000fe36cc7630ff8bfd59e0cd9b1ed99807ad1def552f0378cf107da37b57f3", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 261, 660, 7715, 280, 24930, 2108, 6577, 203, 203, 433, 6988, 10884, 23496, 203, 203, 1482, 48172, 44, 13907, 619, 13174, 203, 1318, 2664, 10184, 5514, 1346, 3193, 31, 38, 2838, 30, 9215, 322, 1374, 1519, 32, 203, 203, 765, 13907, 203, 1318, 1374, 1519, 9643, 1966, 3638, 3193, 31, 38, 2838, 432, 312, 20066, 619, 312, 13174, 32, 7839, 1687, 660, 225, 3, 397, 660, 3639, 280, 2014, 537, 19526, 26, 1508, 547, 4635, 1791, 9189, 27489, 26, 2342, 2976, 293, 1687, 434, 886, 1374, 1519, 308, 2208, 2374, 30850, 27, 15172, 3638, 3193, 31, 38, 2838, 623, 1795, 397, 434, 619, 312, 13174, 30, 1259, 322, 7715, 7022, 10707, 690, 12225, 1957, 322, 2432, 32, 397, 1424, 26, 6426, 2], "prompt_token_count": 123, "reference_codepoints": 64, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [45, 284, 1424, 26, 4788, 32, 42031, 26, 5140, 547, 3613, 32, 13842, 77, 34, 1674, 35, 8492, 24677, 959, 1371, 397, 4826, 44, 1424, 32, 1473, 32135, 1371, 17784, 44, 313, 1956, 4533], "continuation_token_count": 34, "decoded": ";\n expect(vi.mocked(fetch).mock.calls[0][1]).toMatchObject({\n headers: expect.objectContaining({ Authorization: \"token env", "decoded_codepoints": 130, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/github.test.ts", "example_id": "0001003a66a029649aef2acc0d8701f8fa6f4e5ec3be81580e57104747df27c8", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 446, 1424, 26, 2493, 18549, 547, 1206, 32, 17350, 473, 284, 1424, 26, 1267, 547, 7285, 1371, 2287, 44, 313, 1253, 392, 22728, 44, 1605, 1122, 284, 1424, 26, 4788, 32, 42031, 26, 5140, 547, 3613, 32, 13842, 77, 34, 1674, 35, 8492, 24677, 959, 1371, 397, 4826, 44, 1424, 32, 1473, 32135, 1371, 17784, 44, 313, 1956, 4533, 31, 1956, 20, 7305, 284, 1122, 3, 261, 660, 1056, 280, 2014, 1149, 30834, 1792, 11663, 440, 417, 23392, 33, 1819, 41, 724, 446, 1424, 26, 2493, 18549, 547, 1206, 32, 17350, 473, 284, 1424, 26, 1267, 547, 7285, 1371, 2287, 44, 313, 1253, 392, 22728, 44, 1605, 1122, 284, 1424, 26, 4788, 32, 42031, 26, 5140, 547, 3613, 32, 13842, 77, 34, 1674, 35, 8492, 24677, 959, 1371, 397, 4826, 44, 538, 897, 2], "prompt_token_count": 135, "reference_codepoints": 128, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [1297, 32, 1851, 81, 1132, 284, 1201, 1476, 81, 1132, 77, 34, 1674, 34, 79, 610, 313, 858, 32, 40329, 106, 20, 284, 1201, 1476, 81, 1132, 77, 34, 1674, 35, 79, 610, 313, 858, 32, 40329, 106, 20, 284, 1201, 1476, 81, 1132, 77, 34, 1674, 36, 79, 610], "continuation_token_count": 50, "decoded": "create.call_args\n assert call_args[0][0] == \"test.pptx\"\n assert call_args[0][1] == \"test.pptx\"\n assert call_args[0][2] ==", "decoded_codepoints": 130, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_module_misc.py", "example_id": "0001014694996590991e4e9376e3cc59509f33e341c85df633c8bdffffffec04", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 66, 3655, 74, 803, 284, 3634, 283, 1746, 32, 5954, 26, 500, 32, 983, 32, 2524, 26, 3765, 81, 14137, 81, 3197, 30, 313, 858, 32, 40329, 106, 2131, 446, 588, 12072, 322, 13012, 1597, 5403, 372, 322, 3927, 6218, 2330, 436, 447, 3655, 74, 5703, 5133, 284, 1201, 4395, 81, 1580, 32, 6172, 32, 980, 31016, 32, 1297, 32, 10910, 284, 1476, 81, 1132, 280, 4395, 81, 1580, 32, 6172, 32, 980, 31016, 32, 1297, 32, 3, 858, 81, 13232, 478, 203, 50, 12408, 32, 1826, 32, 5961, 325, 26, 284, 7116, 81, 611, 95, 30, 284, 5966, 347, 1409, 646, 1420, 9586, 95, 3312, 2876, 312, 1202, 392, 203, 27, 203, 589, 894, 81, 1826, 283, 1746, 81, 611, 95, 346, 967, 1665, 44, 284, 2043, 280, 2156, 3044, 32, 2961, 6218, 346, 284, 3634, 283, 1746, 280, 7778, 1011, 3211, 26, 611, 95, 81, 1580, 47, 1580, 30, 9586, 95, 81, 1160, 347, 89, 385, 31, 38, 97, 657, 446, 1056, 280, 3634, 283, 1746, 32, 2], "prompt_token_count": 171, "reference_codepoints": 128, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [862, 1476, 81, 1132, 32, 5321, 1365, 14639, 681, 1446, 610, 313, 3164, 33, 4682, 20, 276], "continuation_token_count": 17, "decoded": "assert call_args.kwargs[\"mimetype\"] == \"application/pdf\"\n ", "decoded_codepoints": 65, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_cu_converter.py", "example_id": "000104b36b518663e0912134d36371f44ef3c447e8728199fa96cde5ea10f84e", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 100, 584, 623, 7841, 440, 1826, 283, 1746, 32, 45256, 1114, 9802, 81, 13956, 32, 452, 81, 611, 95, 81, 1131, 392, 442, 81, 853, 347, 10280, 324, 11492, 32, 5954, 26, 400, 3363, 32, 3644, 2338, 26, 84, 20, 9539, 17117, 2113, 400, 7537, 1120, 26, 6728, 26328, 4682, 392, 18346, 681, 347, 3164, 33, 4682, 2113, 324, 829, 11268, 3, 862, 1476, 81, 1132, 32, 5321, 1365, 23125, 81, 314, 1446, 610, 313, 1001, 8282, 31, 2812, 3192, 20, 446, 477, 12408, 32, 1826, 32, 28913, 26, 291, 2884, 14639, 681, 392, 313, 3140, 81, 23125, 2113, 291, 428, 324, 2884, 5000, 33, 317, 38, 392, 313, 1001, 8282, 31, 5000, 3192, 2113, 324, 2884, 5000, 33, 106, 31, 95, 38, 104, 392, 313, 1001, 8282, 31, 5000, 3192, 2113, 203, 2], "prompt_token_count": 135, "reference_codepoints": 64, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [328, 18281, 81, 2516, 44, 324], "continuation_token_count": 6, "decoded": " in challenge_types:\n ", "decoded_codepoints": 32, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/_browsers/_base.py", "example_id": "000113965b6ae5f3778f5de690a09b33c14310118a8067f85aeb9c36ca80906a", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 299, 322, 14098, 7578, 17403, 18281, 827, 30, 415, 400, 2431, 32, 3759, 1665, 415, 1289, 18281, 8001, 32, 291, 1524, 291, 18281, 81, 2516, 280, 308, 324, 313, 3780, 31, 17107, 392, 324, 313, 12262, 392, 324, 313, 17107, 392, 291, 829, 291, 436, 281, 681, 3, 415, 296, 20, 85, 620, 44, 8930, 12758, 111, 7362, 328, 1938, 81, 1286, 44, 400, 442, 281, 681, 584, 588, 3456, 415, 6927, 270, 414, 7135, 5755, 438, 17703, 6517, 322, 1938, 308, 2337, 3405, 6517, 312, 8777, 30704, 27662, 27, 291, 9182, 280, 27556, 26, 1286, 47, 1637, 81, 1286, 27, 291, 415, 9182, 32, 2079, 463, 796, 98, 2], "prompt_token_count": 111, "reference_codepoints": 32, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [261, 34066, 32, 1689, 440, 3164, 33, 12336, 32, 874, 31, 15138, 657, 291, 4348, 827, 81, 610, 6211, 1428, 21488, 18811, 32, 74, 4900, 44, 324, 34066, 32, 1689, 440, 3164, 33, 12336, 32, 874, 31, 15138, 657, 291, 4348, 827, 81, 610, 6211, 1428, 21488, 18811, 32, 74, 4900, 74, 44, 324, 34066, 32, 1689, 440, 3164], "continuation_token_count": 59, "decoded": " prefixes.append(\"application/vnd.ms-excel\")\n elif type_ == DocumentIntelligenceFileType.XLS:\n prefixes.append(\"application/vnd.ms-excel\")\n elif type_ == DocumentIntelligenceFileType.XLSX:\n prefixes.append(\"application", "decoded_codepoints": 256, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_doc_intel_converter.py", "example_id": "00011bf120324cbfa079b0275b14017958321f2bf9e0199fa2424a040d0b598f", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 263, 829, 291, 4348, 827, 81, 610, 6211, 1428, 21488, 18811, 32, 66, 3655, 74, 44, 324, 34066, 32, 1689, 26, 400, 313, 3164, 33, 12336, 32, 1676, 18974, 48869, 1966, 31, 1719, 13350, 1107, 32, 7828, 696, 20, 324, 829, 291, 4348, 827, 81, 610, 6211, 1428, 21488, 18811, 32, 74, 4900, 74, 44, 616, 3, 33, 17193, 29, 2593, 657, 291, 4348, 827, 81, 610, 6211, 1428, 21488, 18811, 32, 14960, 44, 324, 34066, 32, 1689, 440, 3164, 33, 4682, 657, 324, 34066, 32, 1689, 440, 3164, 33, 106, 31, 4682, 657, 291, 4348, 827, 81, 610, 6211, 1428, 21488, 18811, 32, 30671, 44, 324, 34066, 32, 1689, 440, 893, 2], "prompt_token_count": 114, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [647, 1201, 1056, 438, 1665, 446], "continuation_token_count": 6, "decoded": " assert result is None\n\n ", "decoded_codepoints": 32, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/parser/test_ancestor_navigation.py", "example_id": "00011dd1b5ef84cfa78a0097f8e329ac69aaa7ec50e98b96f6e058586c070726", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 271, 81, 3255, 81, 4108, 81, 6036, 81, 1206, 81, 6264, 26, 784, 30, 11815, 81, 1637, 711, 291, 1524, 1809, 81, 43570, 346, 1395, 442, 1665, 415, 1289, 39285, 8001, 2993, 291, 1760, 280, 11815, 81, 1637, 32, 2079, 4120, 1977, 16050, 34, 79, 291, 1056, 280, 1760, 32, 1809, 81, 43570, 26, 5962, 709, 44, 709, 32, 2040, 81, 823, 440, 3780, 29801, 31, 823, 2131, 664, 3, 665, 894, 81, 1731, 723, 31905, 81, 267, 81, 878, 81, 1251, 81, 297, 81, 2951, 26, 784, 30, 11815, 81, 1637, 711, 291, 1524, 1731, 723, 31905, 346, 544, 312, 1344, 1541, 1395, 6761, 7553, 308, 1206, 3636, 27, 2993, 291, 1344, 81, 1251, 280, 11815, 81, 1637, 32, 2079, 4120, 1977, 403, 878, 16050, 34, 79, 291, 600, 48023, 280, 1149, 26, 878, 81, 1251, 32, 1731, 723, 31905, 1157, 275, 2], "prompt_token_count": 145, "reference_codepoints": 32, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [30, 3752, 30, 3752, 32, 558, 1026, 600, 356, 297, 32, 2044, 31009, 30, 313, 1338, 392, 901, 293, 1137, 863, 1302, 301, 577, 202, 102, 32, 8038, 26, 530, 27, 603, 202, 111, 355, 202, 1748, 357, 202, 111, 203, 111, 203, 203, 1298, 2108, 8418, 1063, 26, 102, 319, 4266, 32, 70, 27, 225], "continuation_token_count": 56, "decoded": ", fin, fin.Name(), anubis.DefaultDifficulty, \"info\", false); err != nil {\n\t\t\t\t\tt.Fatal(err)\n\t\t\t\t}\n\t\t\t})\n\t\t}\n}\n\nfunc TestBadConfig(t *testing.T) ", "decoded_codepoints": 144, "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:lib/policy/policy_test.go", "example_id": "00011e85a1cc0115905936da60a0d70aa2f25d0c4d6819bcd0ac25ab633ede00", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 319, 4266, 32, 70, 27, 301, 603, 202, 3507, 30, 1137, 1025, 2322, 32, 2961, 26, 13425, 32, 6249, 440, 497, 392, 313, 1163, 392, 313, 33003, 392, 313, 7127, 392, 376, 32, 558, 5156, 603, 202, 325, 1137, 863, 1302, 301, 577, 202, 102, 32, 8038, 26, 530, 27, 603, 202, 111, 603, 202, 7353, 3752, 32, 4173, 346, 434, 47467, 410, 44, 530, 1553, 5023, 202, 2095, 1025, 361, 8935, 3613, 32, 1554, 3660, 1027, 8935, 26, 102, 27, 603, 202, 325, 4950, 1137, 1025, 8661, 1063, 26, 2095, 3, 109, 577, 202, 102, 32, 8038, 26, 530, 27, 603, 202, 111, 603, 202, 7353, 3752, 32, 4173, 346, 434, 47467, 410, 44, 530, 1553, 5023, 202, 325, 4950, 1137, 1025, 8661, 1063, 26, 102, 32, 1222, 1026, 3752, 30, 3752, 32, 558, 1026, 600, 356, 297, 32, 2044, 31009, 30, 313, 1338, 392, 901, 293, 1137, 863, 1302, 301, 577, 202, 102, 32, 8038, 26, 530, 27, 603, 202, 111, 355, 202, 1748, 357, 202, 1748, 203, 202, 111, 203, 111, 203, 203, 1298, 2108, 8418, 18164, 26, 102, 319, 4266, 32, 70, 27, 225, 2], "prompt_token_count": 190, "reference_codepoints": 256, "repo": "TecharoHQ/anubis", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [285, 301, 334, 1207, 6207, 2019, 26, 2184, 27, 284, 638, 2501, 440, 3615, 657, 284, 638, 2310, 440, 1335, 328, 372, 7049, 41, 657, 284, 638, 1762, 13692, 1347, 31, 7128, 392, 313, 15494, 1330], "continuation_token_count": 36, "decoded": "ion {\n let loginCommand(options)\n .command(\"login\")\n .description(\"Log in to Context7\")\n .option(\"--no-browser\", \"Don't", "decoded_codepoints": 129, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/commands/auth.ts", "example_id": "0001282a42f3b25b647fffda076f3eedd359e57cc84b5cc1fc78ba1cda19b704", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2896, 81, 10539, 81, 45077, 81, 22812, 81, 18382, 30, 203, 111, 645, 6910, 2304, 33, 2393, 32, 754, 866, 203, 203, 465, 301, 4562, 1151, 320, 645, 6910, 2304, 33, 17095, 32, 754, 866, 203, 465, 301, 10070, 81, 10923, 81, 779, 320, 645, 6910, 9777, 32, 754, 866, 203, 465, 301, 622, 29345, 320, 645, 6910, 2304, 33, 1237, 32, 754, 866, 203, 203, 730, 27393, 280, 313, 641, 555, 1819, 41, 32, 508, 866, 203, 203, 1358, 3, 334, 3460, 284, 638, 2501, 440, 3615, 657, 284, 638, 2310, 440, 1335, 328, 372, 7049, 41, 657, 284, 638, 1762, 13692, 1347, 31, 7128, 392, 313, 15494, 1330, 2156, 5427, 6924, 657, 284, 638, 1141, 26, 4396, 308, 2184, 27, 532, 301, 397, 2014, 6207, 2019, 26, 2184, 293, 284, 1122, 719, 3460, 284, 638, 2501, 440, 12646, 657, 284, 638, 24693, 2], "prompt_token_count": 146, "reference_codepoints": 128, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [225, 638, 426, 26, 371, 558, 1157, 284, 638, 681, 26, 371, 620, 1157, 284, 638, 3963, 26, 371, 6751, 1157, 284, 638, 2816, 26, 371, 2101, 1157, 284, 638, 2859, 26, 371, 4232, 1157, 284, 638, 1832, 473, 334, 320, 719, 477, 1788], "continuation_token_count": 44, "decoded": " .name(getName())\n .type(getType())\n .tags(getTags())\n .mode(getMode())\n .meta(getMeta())\n .build();\n }\n\n @Override", "decoded_codepoints": 133, "document_id": "Netflix/maestro@abdbdadf8f075b8fa488c9efb386b468c709a63c:maestro-common/src/main/java/com/netflix/maestro/models/parameter/BooleanParamDefinition.java", "example_id": "000141386a968b123eb8bbb48a9543cb8c9462ed8ca92cee5296ebd99e09ece6", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 111, 719, 477, 1788, 334, 562, 16990, 620, 24115, 346, 301, 284, 442, 16990, 620, 32, 24843, 45, 334, 320, 719, 477, 1788, 334, 562, 5069, 3180, 3373, 619, 4709, 3180, 1350, 346, 301, 284, 442, 458, 45, 334, 320, 719, 477, 1788, 334, 562, 10901, 372, 3012, 346, 301, 284, 442, 5069, 3012, 32, 4164, 346, 664, 3, 225, 638, 3963, 26, 371, 6751, 1157, 291, 638, 2816, 26, 371, 2101, 1157, 291, 638, 2859, 26, 371, 4232, 1157, 291, 638, 1832, 473, 334, 320, 719, 477, 1788, 334, 562, 16990, 3373, 1933, 43141, 26, 397, 2194, 4459, 882, 30, 397, 892, 6101, 30, 397, 16990, 2101, 2926, 30, 397, 3516, 46, 652, 30, 2194, 48, 6089, 30, 1568, 2], "prompt_token_count": 122, "reference_codepoints": 128, "repo": "Netflix/maestro", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [202, 111, 813, 301, 603, 202, 325, 3099, 32, 1215, 6901, 313, 761, 35, 32, 2760, 20, 962, 3099, 32, 1215, 6901, 313, 761, 36, 32, 2760], "continuation_token_count": 27, "decoded": "\t} else {\n\t\t\t\tif info.Path!= \"file1.txt\" && info.Path!= \"file2.txt", "decoded_codepoints": 66, "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/filesystem/backend_inmemory_test.go", "example_id": "000146366d8ee634ef0a0f23589de11c54e752c3b8cb7379791c78862011191d", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 30, 1137, 1025, 9161, 32, 35165, 1120, 26, 2095, 30, 549, 35165, 1120, 1104, 109, 1215, 44, 13189, 1748, 357, 202, 325, 1137, 863, 1302, 301, 355, 202, 102, 32, 14616, 440, 35165, 1120, 3803, 44, 904, 104, 392, 1137, 27, 357, 202, 111, 1314, 202, 979, 4950, 3099, 1025, 2155, 36701, 301, 355, 202, 325, 5852, 32, 7274, 26, 1338, 32, 1215, 30, 44332, 301, 603, 202, 102, 32, 5497, 440, 1215, 1395, 526, 4870, 1755, 30, 5424, 44, 904, 101, 392, 3099, 32, 1215, 27, 355, 3, 440, 7700, 3362, 636, 330, 1515, 35, 370, 5424, 44, 904, 101, 392, 3099, 32, 1215, 27, 603, 202, 111, 355, 202, 111, 813, 301, 603, 202, 325, 3099, 32, 1215, 863, 313, 761, 35, 32, 2760, 20, 962, 3099, 32, 1215, 863, 313, 761, 36, 32, 2760, 20, 301, 577, 202, 102, 32, 5497, 440, 7700, 4870, 330, 761, 35, 32, 2760, 25, 556, 330, 761, 36, 32, 2760, 370, 5424, 44, 904, 101, 392, 3099, 32, 1215, 27, 603, 202, 111, 355, 202, 111, 357, 202, 111, 203, 202, 1748, 478, 202, 102, 32, 2529, 440, 1721, 31570, 2], "prompt_token_count": 191, "reference_codepoints": 64, "repo": "cloudwego/eino", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [6016, 81, 35, 36, 37, 38, 39, 78, 96, 77, 2102, 546, 3754, 6603, 78, 96, 78, 96, 20, 291], "continuation_token_count": 20, "decoded": "TEXT_12345\\n[End OCR]*\\n\\n\"\n ", "decoded_codepoints": 35, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/tests/test_xlsx_converter.py", "example_id": "00014bbf9f72cdb209ce5a5e54de64cda5d73498e6b6cb23e85d4b0867182a20", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 78, 96, 77, 2102, 546, 3754, 6603, 78, 96, 78, 96, 20, 291, 11570, 77, 1658, 546, 3754, 10854, 96, 45878, 81, 43416, 81, 6016, 81, 35, 36, 37, 38, 39, 78, 96, 77, 2102, 546, 3754, 6603, 78, 96, 78, 96, 20, 291, 313, 433, 13565, 78, 96, 78, 96, 20, 291, 29425, 475, 2281, 1921, 25815, 29342, 96, 20, 291, 29425, 5094, 29342, 96, 20, 291, 29425, 1171, 19256, 29342, 96, 78, 96, 20, 291, 313, 1482, 27648, 328, 458, 13063, 3491, 96, 78, 96, 20, 291, 11570, 77, 1658, 546, 3754, 10854, 96, 45878, 81, 3, 351, 313, 433, 15591, 78, 96, 78, 96, 20, 291, 29425, 5599, 18159, 15591, 29342, 96, 20, 291, 29425, 5094, 29342, 96, 20, 291, 29425, 47803, 23016, 29342, 96, 78, 96, 20, 291, 313, 1482, 27648, 328, 458, 13063, 3491, 96, 78, 96, 20, 291, 11570, 77, 1658, 546, 3754, 10854, 96, 45878, 81, 43416, 81, 6016, 81, 35, 36, 37, 38, 39, 78, 96, 77, 2102, 546, 3754, 6603, 20, 284, 829, 284, 1201, 617, 5954, 440, 22733, 81, 12565, 81, 17792, 2], "prompt_token_count": 184, "reference_codepoints": 32, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [284, 632, 37, 36, 1550, 81, 42, 4980, 280, 2385, 81, 42, 4980, 77, 91, 429, 225, 35, 970, 284, 2385, 81, 42, 315, 77, 91, 429, 225, 35, 79, 280, 3401, 81, 42, 315, 45, 284, 3401, 81, 42, 315, 1454, 1550, 81, 42, 315, 45, 334, 320, 334, 24622, 2102, 473, 719, 2385, 81, 42, 315, 77, 34, 79, 280, 225, 34, 45, 334, 2385, 81, 42, 4980, 77, 34, 79, 280, 225, 34, 45, 334, 2385, 81, 35, 40, 77, 34, 79, 280, 225, 34, 45, 719, 24622, 5942, 440, 2871, 225, 42, 6778, 724, 334, 436, 308, 71, 40, 38, 595, 280, 225, 34, 45, 595, 333, 2197, 81, 998, 45, 595, 1454, 225, 35, 27, 301, 284], "continuation_token_count": 122, "decoded": "\n U32 current_8hi = count_8hi[i - 1];\n count_8lo[i - 1] = offset_8lo;\n offset_8lo += current_8lo;\n }\n ProfEnd();\n\n count_8lo[0] = 0;\n count_8hi[0] = 0;\n count_16[0] = 0;\n\n ProfBegin(\"Order 8 Hi\");\n for (U64 i = 0; i < sc_count; i += 1) {\n ", "decoded_codepoints": 257, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/pdb_ext/pdb_builder.c", "example_id": "00015101db4aec4a7bd989d0c13ed65f090ff77751cb810305f57307e6994ee6", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1454, 225, 35, 45, 284, 2385, 81, 35, 40, 77, 15125, 81, 35, 40, 79, 1454, 225, 35, 45, 334, 320, 334, 24622, 2102, 473, 719, 434, 334, 434, 3844, 544, 4169, 3401, 334, 434, 719, 24622, 5942, 440, 23047, 724, 334, 632, 37, 36, 3401, 81, 42, 315, 280, 225, 34, 45, 334, 632, 37, 36, 3401, 81, 42, 4980, 280, 225, 34, 45, 334, 436, 308, 71, 40, 38, 595, 280, 225, 35, 45, 595, 2511, 2629, 1534, 26, 998, 81, 42, 315, 293, 595, 1454, 225, 35, 27, 301, 284, 632, 37, 36, 1550, 81, 42, 315, 280, 2385, 81, 42, 315, 77, 91, 429, 225, 35, 970, 3, 225, 632, 37, 36, 1550, 81, 35, 40, 280, 2385, 81, 35, 40, 77, 91, 429, 225, 35, 970, 284, 2385, 81, 35, 40, 77, 91, 429, 225, 35, 79, 280, 3401, 81, 35, 40, 45, 284, 3401, 81, 35, 40, 1454, 1550, 81, 35, 40, 45, 334, 320, 334, 24622, 2102, 473, 719, 2385, 81, 42, 315, 77, 34, 79, 280, 225, 34, 45, 334, 2385, 81, 42, 4980, 77, 34, 79, 280, 225, 34, 45, 334, 2385, 81, 35, 40, 77, 34, 79, 280, 225, 34, 45, 719, 24622, 5942, 440, 2871, 225, 42, 4035, 724, 334, 436, 308, 71, 40, 38, 595, 280, 225, 34, 45, 595, 333, 2197, 81, 998, 45, 595, 1454, 225, 35, 27, 301, 284, 447, 1996, 81, 5141, 91, 2], "prompt_token_count": 241, "reference_codepoints": 256, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [1010, 291, 2599, 17094, 1664, 3207, 326, 5321, 27, 291, 630, 1114, 496, 81, 605, 81, 1515, 280, 10306, 32, 3235, 14715, 496, 81, 605, 81, 1515, 392, 1665, 27, 291, 630, 1114, 5078, 81, 3494], "continuation_token_count": 36, "decoded": "\"\"\n super().__init__(**kwargs)\n self._user_data_dir = kwargs.pop(\"_user_data_dir\", None)\n self._headers_keys", "decoded_codepoints": 129, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/_browsers/_controllers.py", "example_id": "00015603170a7be7ddcf713cc092cef91b1e0e368d304e44cc5dfb68029d61f7", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 105, 509, 81, 2184, 392, 291, 7286, 496, 81, 605, 81, 1515, 392, 291, 7286, 5078, 81, 3494, 392, 291, 313, 1449, 81, 5646, 392, 291, 313, 1637, 81, 5178, 392, 291, 7286, 1449, 81, 1684, 81, 979, 81, 1637, 392, 291, 313, 1066, 105, 990, 392, 291, 313, 1819, 392, 284, 829, 446, 665, 1156, 1664, 3207, 784, 30, 1115, 5321, 44, 1683, 2423, 77, 5195, 105, 990, 3135, 10794, 291, 313, 3, 5660, 32, 584, 499, 753, 5759, 2274, 44, 4489, 322, 5427, 328, 5759, 2274, 33, 3864, 308, 1536, 471, 556, 5759, 2790, 33, 7891, 2926, 32, 291, 499, 753, 7378, 81, 5379, 44, 14105, 5167, 436, 25084, 6086, 436, 312, 8227, 9760, 32, 324, 25333, 23126, 884, 432, 827, 529, 2186, 1801, 529, 893, 2], "prompt_token_count": 130, "reference_codepoints": 128, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [1637, 4099, 1162, 7986, 81, 1637, 517, 225, 36, 490, 334, 428, 3941, 7986, 81, 1637, 20, 429, 2159, 225, 35, 1481, 962, 6998, 81, 1637, 47, 35, 334, 428, 3941, 7986, 81, 1637, 20, 429, 2159, 225, 35, 1481, 962, 6998, 81, 1637, 47, 35, 334, 428, 3941, 7986, 81, 1637, 20, 429, 2159, 225, 35, 1481, 962, 6998, 81, 1637, 47, 35, 334, 428, 3941, 7986, 81, 1637, 20, 429, 2159, 225, 35, 1481, 962, 6998, 81, 1637, 47, 35, 334, 428, 3941, 7986, 81, 1637, 20, 429, 2159, 225, 35, 1481, 962, 6998], "continuation_token_count": 96, "decoded": "page=$((endpoint_page / 2))\n [ \"$endpoint_page\" -lt 1 ] && endpoint_page=1\n [ \"$endpoint_page\" -lt 1 ] && endpoint_page=1\n [ \"$endpoint_page\" -lt 1 ] && endpoint_page=1\n [ \"$endpoint_page\" -lt 1 ] && endpoint_page=1\n [ \"$endpoint_page\" -lt 1 ] && endpoint", "decoded_codepoints": 260, "document_id": "steipete/agent-scripts@bb3688355a4c1894dd53b4ed867d1600918fadf0:skills/clawsweeper-status/scripts/clawsweeper-status.sh", "example_id": "00015d53dcaa0868a7c835242732849bc891590f66c5c717751aef6ac9afe7e9", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 81, 1637, 9104, 1517, 81, 1637, 81, 891, 3845, 766, 284, 769, 13841, 5608, 9874, 81, 19245, 523, 1992, 1371, 397, 3500, 606, 44, 638, 314, 30, 397, 636, 30, 397, 1692, 30, 397, 2287, 30, 397, 457, 13715, 30, 397, 25463, 44, 638, 4524, 81, 269, 30, 397, 1984, 44, 638, 916, 81, 965, 284, 1790, 25, 848, 25526, 2024, 20, 203, 111, 203, 203, 5140, 81, 6891, 81, 1637, 346, 301, 334, 2196, 6998, 81, 3, 1637, 81, 891, 20, 429, 3685, 225, 35, 4028, 1615, 397, 10501, 3941, 731, 81, 761, 20, 25228, 36, 397, 442, 225, 35, 284, 8058, 284, 1938, 81, 891, 4099, 1162, 1637, 81, 891, 517, 225, 36, 490, 284, 428, 3941, 1637, 81, 891, 20, 429, 2159, 225, 35, 1481, 962, 1938, 81, 891, 47, 35, 334, 3390, 203, 111, 203, 203, 44, 848, 25526, 464, 81, 19245, 81, 1260, 94, 20, 203, 3141, 1420, 1149, 769, 6426, 3941, 573, 812, 1586, 21603, 81, 6426, 20, 769, 3248, 3941, 1945, 81, 3248, 20, 766, 334, 769, 1260, 706, 2], "prompt_token_count": 178, "reference_codepoints": 256, "repo": "steipete/agent-scripts", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [878, 81, 1286, 77, 2111, 79, 584, 588, 12888], "continuation_token_count": 9, "decoded": "text_content[header]\n\n # Validate", "decoded_codepoints": 40, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_pdf_tables.py", "example_id": "000165c985a3d908d55e45d6a3383cf49ffad5172c69a37662d33ab7e60dde84", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 3666, 291, 3100, 81, 1274, 81, 5078, 280, 428, 324, 313, 4220, 392, 324, 313, 3010, 28729, 392, 324, 313, 4754, 3846, 392, 324, 313, 3267, 25547, 392, 324, 313, 11438, 392, 291, 1481, 291, 436, 3338, 328, 3100, 81, 1274, 81, 5078, 44, 324, 1201, 3338, 328, 1344, 81, 1286, 30, 225, 3, 111, 7362, 584, 588, 12888, 3100, 1858, 1401, 1169, 2799, 17227, 2337, 308, 35, 34, 10052, 27, 291, 3100, 81, 1274, 81, 1990, 352, 280, 428, 324, 313, 9718, 71, 31, 42, 42, 38, 41, 392, 324, 313, 9718, 71, 31, 43, 36, 34, 35, 392, 324, 313, 9718, 71, 31, 38, 39, 40, 37, 392, 324, 313, 9718, 71, 31, 41, 41, 36, 42, 392, 324, 313, 9718, 71, 31, 37, 37, 38, 39, 392, 324, 313, 9718, 71, 31, 39, 39, 35, 36, 392, 616, 2], "prompt_token_count": 143, "reference_codepoints": 32, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [983, 293, 397, 2014, 5980, 32, 10174, 26, 983, 32, 983, 474, 3056, 1286, 895, 397, 2014, 5980, 32, 10174, 26, 983, 32, 983, 474, 3056, 1286, 33, 1286, 895, 397, 2014, 5980, 32, 10174, 26, 983, 32, 983, 474, 3056, 1286, 33, 1286, 33, 1286, 895, 397, 2014, 5980, 32, 10174, 26, 983, 32, 983, 474, 3056, 1286, 33, 1286, 33, 1286, 33, 1286, 895, 397, 2014, 5980, 32, 10174], "continuation_token_count": 71, "decoded": "path);\n await fs.mkdir(path.path + '/content');\n await fs.mkdir(path.path + '/content/content');\n await fs.mkdir(path.path + '/content/content/content');\n await fs.mkdir(path.path + '/content/content/content/content');\n await fs.mkdir", "decoded_codepoints": 259, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/completions/installers/powershell-installer.test.ts", "example_id": "000167092350f415d0d6b029b89213baa297a4ef33890f6427335fc8bd6f4f78", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2548, 32, 32263, 26, 3959, 1215, 30, 330, 3310, 31, 42, 895, 397, 1424, 26, 1286, 547, 5492, 3609, 4300, 3115, 1359, 78, 96, 2538, 31, 3663, 313, 8279, 20, 895, 284, 1122, 446, 561, 463, 3163, 3345, 1795, 3733, 24146, 370, 2498, 1404, 532, 301, 397, 660, 6274, 1215, 280, 25079, 32, 371, 4290, 1215, 473, 397, 2014, 5980, 32, 10174, 26, 983, 32, 3, 225, 5307, 4300, 1359, 370, 397, 13819, 2524, 9442, 96, 895, 1687, 2014, 5980, 32, 39052, 26, 3959, 1215, 30, 2815, 1777, 293, 1687, 660, 1056, 280, 2014, 25079, 32, 2546, 4290, 1063, 473, 1687, 1424, 26, 1267, 547, 5492, 26, 1508, 293, 397, 660, 1795, 280, 2014, 5980, 32, 32263, 26, 3959, 1215, 30, 330, 3310, 31, 42, 895, 397, 2], "prompt_token_count": 129, "reference_codepoints": 256, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [102, 203, 111, 203, 111, 203, 203, 1298, 537, 1006, 4599, 26, 102, 319, 4266, 32, 70, 27, 319, 11397, 17423, 4882, 32, 1006, 4599, 301, 203, 202, 102, 32, 2762, 346, 203, 202, 725, 30, 1137, 1025, 16456, 17423, 4882, 32, 1812, 1006, 4599, 26, 102, 32, 44964, 1157, 203, 202, 1981, 32, 15109, 26, 102, 30, 1137, 27, 203, 202, 102, 32, 20253, 26, 725, 32, 20253, 27, 203, 202, 601, 225, 34, 203, 111, 203, 203, 1298, 537, 1006, 4599, 26, 102, 319, 4266, 32, 70, 27, 319, 11397, 17423, 4882, 32, 1006, 4599, 301, 203, 202, 102, 32, 2762, 346, 203, 202, 725, 30, 1137], "continuation_token_count": 109, "decoded": "t\n}\n}\n\nfunc newTestHub(t *testing.T) *beszeltests.TestHub {\n\tt.Helper()\n\tapp, err := beszeltests.NewTestHub(t.TempDir())\n\trequire.NoError(t, err)\n\tt.Cleanup(app.Cleanup)\n\treturn 0\n}\n\nfunc newTestHub(t *testing.T) *beszeltests.TestHub {\n\tt.Helper()\n\tapp, err", "decoded_codepoints": 257, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/hub/heartbeat/heartbeat_test.go", "example_id": "0001683de5c2998da4db924d0317f7c2b53d56c1f8d2a3adff377a8d1b202d51", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 28263, 27, 355, 202, 862, 32, 1324, 26, 102, 30, 11944, 32, 2358, 10708, 30, 3616, 32, 6263, 32, 28631, 32, 10708, 27, 357, 202, 1748, 203, 202, 111, 203, 111, 203, 203, 1298, 537, 1006, 4599, 26, 102, 319, 4266, 32, 70, 27, 319, 11397, 17423, 4882, 32, 1006, 4599, 301, 203, 202, 102, 32, 2762, 346, 203, 202, 725, 30, 1137, 1025, 16456, 17423, 4882, 32, 1812, 1006, 4599, 26, 102, 32, 44964, 1157, 203, 202, 1981, 32, 15109, 26, 102, 30, 1137, 27, 203, 202, 102, 32, 20253, 26, 725, 32, 20253, 27, 203, 202, 601, 225, 3, 319, 11397, 17423, 4882, 32, 1006, 4599, 30, 35336, 30, 636, 30, 3408, 30, 2287, 802, 27, 319, 1262, 32, 3157, 301, 203, 202, 102, 32, 2762, 346, 203, 202, 2946, 30, 1137, 1025, 16456, 17423, 4882, 32, 1922, 3157, 26, 725, 32, 1290, 30, 313, 17579, 392, 1992, 77, 800, 79, 1813, 109, 357, 202, 20, 426, 563, 261, 636, 30, 357, 202, 20, 2035, 563, 261, 3408, 30, 357, 202, 20, 625, 563, 261, 313, 38, 39, 42, 41, 40, 392, 357, 202, 20, 3707, 563, 225, 1605, 800, 109, 28385, 835, 357, 202, 20, 4597, 2], "prompt_token_count": 201, "reference_codepoints": 256, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [261, 442, 301, 324, 2074, 81, 1517, 81, 8539, 26, 7815, 471, 324], "continuation_token_count": 13, "decoded": " return {\n project_status_marker(failed),\n ", "decoded_codepoints": 66, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/run/run.rs", "example_id": "00016f52ac0b0c13e6300f3c841ecf64b573622101db8ed156559eaae5db9011", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 351, 9541, 30, 324, 3117, 44, 861, 30, 324, 803, 81, 10454, 44, 901, 30, 291, 320, 284, 320, 446, 2771, 2908, 81, 2250, 81, 2111, 26, 291, 549, 2278, 630, 30, 291, 2074, 44, 549, 3196, 30, 291, 3803, 44, 1560, 30, 291, 2519, 81, 2250, 81, 5078, 44, 1560, 30, 284, 829, 967, 4703, 31012, 301, 397, 3, 320, 584, 630, 32, 24124, 32, 34303, 40130, 301, 324, 2870, 43166, 4482, 400, 630, 32, 1517, 81, 21201, 32, 21201, 922, 9362, 1026, 400, 19436, 12263, 400, 2074, 81, 1517, 81, 8539, 26, 7815, 471, 400, 2074, 32, 2751, 81, 426, 922, 31182, 922, 8570, 346, 324, 829, 203, 2], "prompt_token_count": 112, "reference_codepoints": 64, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [264, 2615, 397, 829, 397, 5576, 1279, 291, 313, 2951, 31, 2310, 563, 313, 2766, 3048, 392, 291, 313, 2951, 31, 1286, 563, 313, 2766, 1795, 392, 291], "continuation_token_count": 28, "decoded": " className\n )\n props={\n \"empty-description\": \"Empty description\",\n \"empty-content\": \"Empty content\",\n ", "decoded_codepoints": 135, "document_id": "OpenCut-app/OpenCut@4d8c49ed0706c4dc145361e01c6b1f1a87cbb863:apps/web/src/components/ui/empty.tsx", "example_id": "00017099ee46aa49286ac4bb0183714c0c5ab33ee328bf702a9b219d89bf4572", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 467, 1371, 2615, 30, 2417, 2962, 23557, 3475, 32, 42258, 46, 20, 98, 413, 27, 301, 334, 442, 308, 284, 333, 507, 397, 706, 31, 9040, 347, 2951, 31, 2310, 20, 397, 2615, 1279, 4977, 26, 291, 313, 878, 31, 4895, 33, 31690, 318, 1344, 31, 16120, 31, 29242, 22092, 48, 83, 2786, 26462, 22092, 48, 83, 2786, 26462, 31, 2881, 31, 38, 22092, 48, 83, 44, 6413, 2786, 878, 31, 4457, 392, 275, 3, 27, 301, 334, 442, 308, 284, 333, 507, 397, 706, 31, 9040, 347, 2951, 31, 1286, 20, 397, 2615, 1279, 4977, 26, 291, 313, 5636, 341, 31, 2620, 1769, 31, 105, 31, 1745, 1847, 31, 105, 31, 34, 5463, 31, 748, 3946, 31, 2390, 15948, 31, 36, 1344, 31, 4895, 33, 31690, 318, 1344, 31, 10401, 392, 291, 2615, 397, 14301, 397, 12399, 2962, 111, 284, 1681, 334, 829, 203, 111, 203, 203, 1358, 301, 334, 14893, 30, 334, 516, 6310, 2], "prompt_token_count": 158, "reference_codepoints": 128, "repo": "OpenCut-app/OpenCut", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [9159, 86, 25, 397, 429, 87, 3056, 46, 7203, 1792, 48, 3424, 46], "continuation_token_count": 13, "decoded": ">/d'\n -e '/.*<", "decoded_codepoints": 32, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/answer.sh", "example_id": "0001712825d1b6446f145e2bdc1ff8f3c97e7d145bbaa58bf4bb0e135a700835", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 5501, 719, 415, 653, 3691, 9456, 4765, 1433, 429, 98, 517, 1945, 33, 3512, 4939, 1667, 314, 4009, 13083, 2915, 724, 1615, 284, 1048, 313, 5288, 372, 1487, 312, 14016, 398, 681, 7592, 803, 11555, 284, 442, 225, 35, 334, 8058, 719, 2196, 15866, 719, 415, 428, 3941, 681, 20, 280, 313, 22574, 20, 4028, 1615, 284, 15866, 4310, 397, 429, 87, 3056, 46, 3409, 953, 48, 3424, 46, 5272, 3409, 953, 3, 5272, 3409, 953, 9159, 86, 25, 284, 829, 334, 813, 284, 15866, 4310, 397, 429, 87, 3056, 46, 7203, 1792, 48, 3424, 46, 5272, 7203, 1792, 9159, 86, 25, 397, 429, 87, 3056, 46, 3409, 953, 48, 3424, 46, 5272, 3409, 953, 9159, 86, 25, 397, 429, 87, 3056, 46, 7203, 1792, 9159, 30, 14617, 5272, 7203, 1792, 9159, 86, 25, 397, 429, 87, 3056, 46, 3409, 953, 9159, 30, 14617, 5272, 3409, 953, 9159, 86, 25, 284, 829, 334, 8058, 719, 415, 653, 12109, 6313, 3385, 2], "prompt_token_count": 162, "reference_codepoints": 32, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [284, 6594, 1599, 1120, 12913, 32, 1297, 8384, 10728, 318, 1599, 26, 397, 6594, 1599, 1120, 12913, 32, 6173, 1599, 1120, 32, 6173, 10728, 953, 30, 397], "continuation_token_count": 27, "decoded": "\n externalTableInfoDAO.createExternalPartitionedTable(\n externalTableInfoDAO.externalTableInfo.externalPartitionKey,\n ", "decoded_codepoints": 130, "document_id": "unitycatalog/unitycatalog@ed504deea31b30c3e7d27e360372077cce04a509:server/src/test/java/io/unitycatalog/server/utils/PopulateTestDatabase.java", "example_id": "000172aa9e564556ec61b54a66db7ca8ea064c9e9855002a82eb224fd117f9f0", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 96, 3523, 280, 7763, 32, 1676, 3135, 1157, 301, 397, 11725, 6486, 280, 3523, 32, 39160, 473, 397, 3523, 32, 20307, 26, 6173, 1599, 1120, 12913, 293, 397, 3523, 32, 20307, 26, 98, 35, 35, 293, 397, 3523, 32, 20307, 26, 98, 36, 35, 293, 397, 6486, 32, 3375, 473, 284, 320, 446, 434, 2648, 6594, 9778, 318, 1858, 32, 3, 33, 429, 1932, 81, 426, 284, 434, 429, 11442, 284, 434, 429, 10769, 308, 11458, 2623, 27, 284, 434, 3367, 322, 706, 328, 458, 1858, 884, 11152, 461, 4528, 4723, 810, 4559, 43071, 32, 284, 434, 24607, 2623, 1401, 8019, 5799, 2078, 517, 25164, 32, 284, 434, 2398, 438, 7107, 328, 33414, 5794, 2179, 32, 284, 1171, 32, 541, 2], "prompt_token_count": 122, "reference_codepoints": 128, "repo": "unitycatalog/unitycatalog", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [45, 584, 660, 1326, 1222, 280], "continuation_token_count": 6, "decoded": ";\n\n const requestContext =", "decoded_codepoints": 33, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/mcp/src/index.ts", "example_id": "0001739d015ba3bcadf92562d7a7f3f98116b9699e3013f3ac1d69c2c04b6347", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 434, 4826, 30, 4444, 8415, 322, 1292, 31, 3732, 5868, 438, 5610, 12224, 32, 291, 660, 11337, 280, 537, 7537, 444, 5068, 2059, 9998, 1371, 616, 32995, 4815, 44, 3469, 30, 616, 5352, 42959, 44, 901, 30, 291, 1122, 584, 660, 2145, 280, 1487, 63, 2219, 2059, 473, 3, 616, 11337, 32, 2679, 473, 616, 2145, 32, 2679, 473, 291, 1122, 584, 2443, 9998, 1765, 7886, 299, 26, 9613, 293, 291, 2014, 2145, 32, 3517, 26, 9613, 293, 584, 2014, 1326, 1222, 32, 1945, 26, 1819, 30, 2498, 1404, 532, 301, 616, 2014, 11337, 32, 2956, 1104, 26, 100, 2], "prompt_token_count": 101, "reference_codepoints": 32, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [44, 6204, 203, 202, 27, 967, 16090, 8731, 11932, 77, 70, 2786, 357, 202, 325, 1688, 81, 1643, 438, 1665, 44, 355, 202, 1986, 280, 2014, 630, 32, 371, 81, 1580, 922, 6172, 26, 603, 202, 1160, 47, 784, 32, 1160], "continuation_token_count": 41, "decoded": ": Any\n\t) -> ChatInvokeCompletion[T]:\n\t\tif output_format is None:\n\t\t\tresponse = await self.get_client().chat(\n\t\t\t\tmodel=self.model", "decoded_codepoints": 129, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/llm/ollama/chat.py", "example_id": "000175a91c1b6d96ff044222fe9f410a4e8407f9c3e849a90954b84912bdb192", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 9084, 77, 466, 2786, 2417, 478, 202, 50, 33371, 203, 202, 4396, 665, 312, 7844, 26, 784, 30, 5218, 44, 1149, 77, 1761, 1175, 614, 1688, 81, 1643, 44, 827, 77, 70, 614, 1115, 5321, 44, 6204, 27, 967, 16090, 8731, 11932, 77, 70, 2786, 2417, 478, 202, 4396, 665, 312, 7844, 26, 357, 202, 784, 30, 5218, 44, 1149, 77, 1761, 1175, 614, 1688, 81, 1643, 44, 827, 77, 70, 79, 523, 1665, 280, 1665, 30, 1115, 5321, 3, 6286, 27, 1314, 202, 1270, 44, 355, 202, 325, 1688, 81, 1643, 438, 1665, 44, 603, 202, 1986, 280, 2014, 630, 32, 371, 81, 1580, 922, 6172, 26, 577, 202, 1160, 47, 784, 32, 1160, 30, 577, 202, 6286, 47, 5812, 4478, 81, 6286, 30, 577, 202, 2184, 47, 784, 32, 5812, 4478, 81, 2184, 30, 603, 202, 27, 5023, 202, 601, 16090, 8731, 11932, 26, 15825, 47, 1986, 32, 1436, 32, 1286, 337, 2], "prompt_token_count": 156, "reference_codepoints": 128, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [225, 3114, 309, 3246, 81, 1174, 81, 2632, 848, 309, 3246, 81, 19632, 81, 2632, 45, 203, 203, 287, 3456, 2398, 12184, 15299, 44, 25573, 280, 37585, 319, 20754, 203, 287, 9177, 367, 44, 3139, 19677, 203, 4620, 46781, 3701, 309, 3246, 81, 13497, 30, 284, 309, 3246, 81, 10954, 30, 284, 309, 3246, 81, 4415, 225, 203, 9067, 39279, 32, 33109, 81, 13497, 81, 3958, 203, 16995, 309, 3246, 81, 13497, 6901, 309, 3246, 81, 10954, 319, 309, 3246, 81, 4415, 334, 3114], "continuation_token_count": 84, "decoded": " AND sls_order_dt > sls_due_dt;\n\n-- Check Data Consistency: Sales = Quantity * Price\n-- Expectation: No Results\nSELECT DISTINCT \n sls_sales,\n sls_quantity,\n sls_price \nFROM silver.crm_sales_details\nWHERE sls_sales!= sls_quantity * sls_price\n AND", "decoded_codepoints": 256, "document_id": "DataWithBaraa/sql-data-warehouse-project@92406686380cde6eca208c8b43e6fa40ecd26344:tests/quality_checks_silver.sql", "example_id": "0001775bb70543fc89ed13821fe3f7b64ec5b3b2c394996c08877f61a5b45c47", "language": "sql", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 102, 9068, 1878, 309, 3246, 81, 1174, 81, 2632, 848, 309, 3246, 81, 19632, 81, 2632, 45, 203, 203, 287, 3456, 2398, 12184, 15299, 44, 25573, 280, 37585, 319, 20754, 203, 287, 9177, 367, 44, 3139, 19677, 203, 4620, 46781, 3701, 309, 3246, 81, 13497, 30, 284, 309, 3246, 81, 10954, 30, 284, 309, 3246, 81, 4415, 225, 203, 9067, 39279, 32, 33109, 81, 13497, 81, 3958, 203, 16995, 309, 3246, 81, 13497, 863, 309, 3246, 81, 10954, 319, 309, 3246, 81, 4415, 334, 3, 18444, 203, 287, 32086, 330, 41190, 32, 22083, 81, 26518, 81, 1373, 35, 36, 25, 203, 287, 12057, 5849, 203, 287, 17492, 1147, 4306, 31, 1028, 31, 3198, 475, 1196, 203, 287, 9177, 367, 44, 551, 11018, 4419, 3733, 225, 35, 43, 36, 38, 31, 34, 35, 31, 34, 35, 461, 46097, 203, 4620, 46781, 3701, 323, 770, 225, 203, 9067, 39279, 32, 22083, 81, 26518, 81, 1373, 35, 36, 203, 11990, 2], "prompt_token_count": 159, "reference_codepoints": 256, "repo": "DataWithBaraa/sql-data-warehouse-project", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [630, 1114, 3483, 280, 630, 1114, 3483, 81, 5792, 26, 784, 32, 4073, 30, 630, 32, 5136, 30, 630], "continuation_token_count": 19, "decoded": " self._engine = self._engine_factory(self.logger, self.stats, self", "decoded_codepoints": 66, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/spiders/spider.py", "example_id": "000177a09b46001bbc4ffbcc85129b78c6775fee0f77d4ba39905b7404ef0775", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1591, 619, 2953, 884, 32714, 318, 32, 291, 8258, 529, 35585, 32, 5136, 82, 5929, 13330, 436, 4011, 31, 1003, 14564, 32, 584, 5830, 44, 18760, 1844, 9933, 436, 15263, 33, 14957, 438, 646, 3304, 328, 3443, 2926, 32, 291, 1524, 291, 2404, 280, 739, 81, 4073, 26, 784, 32, 4073, 27, 291, 1596, 44, 324, 3, 85, 1294, 1381, 476, 30, 630, 1114, 7568, 27, 324, 2498, 436, 1623, 328, 630, 1114, 3483, 44, 400, 6761, 1623, 291, 8295, 44, 324, 630, 1114, 3483, 280, 1665, 324, 5657, 81, 4073, 26, 1956, 27, 324, 415, 630, 32, 751, 81, 761, 44, 400, 436, 4899, 328, 630, 32, 4073, 32, 4668, 94, 2], "prompt_token_count": 114, "reference_codepoints": 64, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [423, 2430, 2215, 33, 36131, 33, 1696, 33, 1771, 392, 1014, 2430, 2215, 33, 36131, 33, 36131, 33, 1771, 392, 1014, 2430, 2215, 33, 36131, 33, 36131, 33, 1696, 33, 1771, 392, 1014, 2430, 2215, 33, 36131, 33, 36131, 33, 36131, 33, 1771, 392, 1014], "continuation_token_count": 45, "decoded": " \"/opt/homebrew/local/bin\",\n \"/opt/homebrew/homebrew/bin\",\n \"/opt/homebrew/homebrew/local/bin\",\n \"/opt/homebrew/homebrew/homebrew/bin\",\n ", "decoded_codepoints": 260, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/_markitdown.py", "example_id": "00017b1d02d1c4743fbc3129855d720001a6bb61c6a57d3d6468a1746beea603", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2071, 2430, 3381, 33, 1771, 392, 1014, 2430, 3381, 33, 1696, 33, 1771, 392, 1014, 2430, 2215, 392, 1014, 2430, 2215, 33, 1771, 392, 1014, 2430, 2215, 33, 1696, 33, 1771, 392, 1014, 2430, 2215, 33, 36131, 33, 1771, 392, 324, 3, 351, 588, 7013, 17675, 101, 436, 10149, 323, 34520, 7373, 324, 588, 498, 1651, 9416, 31474, 884, 8855, 1932, 517, 4818, 12224, 9958, 2784, 17083, 9416, 31474, 324, 588, 2614, 458, 943, 30, 322, 4630, 2818, 17675, 101, 1395, 9250, 4794, 322, 4630, 1797, 91, 2], "prompt_token_count": 89, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [1567, 81, 4891, 32, 3517, 346, 1314, 202, 21, 2648, 312, 9755, 14612, 357, 202, 6589, 14612, 280, 7337, 9417, 14612, 26, 1567, 81, 4891, 27, 1314, 202, 21, 3456, 688, 322, 3051, 5880, 438, 646, 312, 3051, 5880, 357, 202, 862, 9755, 14612, 1114, 297, 81, 2388, 81, 4116, 463, 2763, 32, 508, 683, 438, 3177, 357, 202, 862, 9755, 14612, 1114, 297, 81, 2388, 81, 4116, 463, 2200, 32, 2763, 32, 508, 683, 438, 3177], "continuation_token_count": 77, "decoded": "event_bus.connect()\n\n\t\t# Create a watchdog\n\t\twatchdog = SecurityWatchdog(event_bus)\n\n\t\t# Check that the root domain is not a root domain\n\t\tassert watchdog._is_root_domain('example.com') is False\n\t\tassert watchdog._is_root_domain('mail.example.com') is False", "decoded_codepoints": 257, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/security/test_domain_filtering.py", "example_id": "000180a1d5f05bb2521618cf29f2bb4c4ba94ffbb10c92d513f9432753bc2d46", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 105, 509, 32, 6589, 14612, 101, 32, 4373, 81, 6589, 14612, 1188, 7337, 9417, 14612, 1314, 202, 7128, 81, 3959, 280, 14161, 4290, 26, 11327, 81, 20798, 11414, 2763, 32, 508, 2188, 5759, 2274, 47, 1815, 30, 1256, 81, 605, 81, 1515, 47, 2521, 27, 357, 202, 7128, 81, 2848, 280, 14161, 3135, 26, 7128, 81, 3959, 47, 7128, 81, 3959, 27, 357, 202, 1567, 81, 4891, 280, 3903, 5990, 346, 355, 3, 6589, 14612, 1114, 297, 81, 2388, 81, 4116, 463, 2851, 32, 1299, 683, 438, 2933, 1314, 202, 21, 3725, 20798, 308, 7026, 2784, 225, 35, 8057, 27, 429, 1395, 442, 3177, 357, 202, 862, 9755, 14612, 1114, 297, 81, 2388, 81, 4116, 463, 1499, 32, 2763, 32, 508, 683, 438, 3177, 357, 202, 862, 9755, 14612, 1114, 297, 81, 2388, 81, 4116, 463, 2200, 32, 2763, 32, 508, 683, 438, 3177, 357, 202, 862, 9755, 14612, 1114, 297, 81, 2388, 81, 4722, 2], "prompt_token_count": 157, "reference_codepoints": 256, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [263, 436, 3338, 30, 786, 328, 4826, 32, 3028, 2262, 400, 11451, 81, 5078, 77, 2111, 79, 280, 786, 1064, 11451, 81, 5078, 280, 301, 93, 44, 354, 436, 831, 30, 354, 328, 11451, 81, 5078, 32, 3028, 346, 415, 354, 438, 646, 1665, 111, 324, 11451, 81, 5078, 280, 301, 93, 44, 354, 436, 831, 30, 354, 328, 11451, 81, 5078], "continuation_token_count": 62, "decoded": " for header, value in headers.items():\n processed_headers[header] = value\n\n processed_headers = {k: v for k, v in processed_headers.items() if v is not None}\n processed_headers = {k: v for k, v in processed_headers", "decoded_codepoints": 259, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/spiders/request.py", "example_id": "0001811e37ea493f535528d8c25796a94d260f0bc98281a3f2e18ec5ee56b7b8", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 8825, 26, 11939, 26, 15688, 81, 5321, 32, 3028, 5156, 584, 415, 2305, 81, 5078, 44, 324, 4826, 280, 630, 1114, 2848, 81, 5321, 32, 371, 440, 5078, 657, 556, 630, 1114, 2848, 81, 5321, 32, 371, 440, 7615, 81, 5078, 657, 556, 2149, 324, 11451, 81, 5078, 280, 2149, 324, 588, 4185, 3338, 32360, 284, 3, 30, 2470, 47, 271, 1260, 32, 14566, 81, 29639, 81, 21800, 471, 1654, 979, 4373, 47, 2700, 547, 13995, 346, 291, 630, 1114, 4426, 280, 11828, 291, 442, 11828, 446, 665, 1156, 13707, 3207, 784, 27, 967, 596, 44, 291, 3309, 81, 426, 280, 18623, 26, 784, 32, 4383, 30, 9602, 426, 41501, 1665, 27, 556, 313, 2521, 20, 291, 442, 296, 13950, 1104, 1371, 784, 32, 965, 1748, 41585, 2], "prompt_token_count": 129, "reference_codepoints": 256, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [27, 324, 638, 1110, 26, 4396, 5169, 523, 26, 426, 30, 1519, 6488, 38428, 27, 324, 638, 1110, 26, 4396, 5169, 523, 26, 426, 30, 1519, 6488, 38428, 27, 324, 638, 1110, 26, 4396, 5169, 523, 26, 426, 30, 1519, 6488, 38428, 27, 324, 638, 1110, 26, 4396, 5169, 523, 26, 426, 30, 1519, 6488, 38428, 27, 324, 638, 1110, 26, 4396, 5169, 523, 26, 426, 30, 1519], "continuation_token_count": 68, "decoded": ")\n .map(async move |(name, path)| toolchain)\n .map(async move |(name, path)| toolchain)\n .map(async move |(name, path)| toolchain)\n .map(async move |(name, path)| toolchain)\n .map(async move |(name, path", "decoded_codepoints": 258, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/languages/rust/rustup.rs", "example_id": "000188316784aa08c87f73e9d054ca26a2b1516ed2702b8f7d04b870b7ef6901", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 48, 280, 596, 403, 1070, 81, 3310, 42, 1652, 2024, 32, 9362, 6505, 324, 638, 4446, 346, 324, 638, 2029, 81, 1110, 26, 2208, 81, 44695, 81, 928, 27, 324, 638, 6174, 473, 584, 1207, 36701, 44, 7479, 46, 3653, 5074, 1120, 48, 280, 35133, 81, 1040, 403, 2238, 403, 1731, 26, 9150, 27, 324, 638, 1110, 26, 4396, 5169, 523, 26, 426, 30, 1519, 6488, 38428, 3, 2407, 1665, 400, 320, 324, 1790, 324, 638, 6174, 346, 324, 638, 6240, 45, 584, 6311, 26, 15572, 27, 284, 320, 446, 889, 1682, 2664, 31, 18132, 19281, 4559, 28475, 32, 284, 2547, 26, 9822, 27, 2498, 2771, 1149, 81, 2946, 81, 3732, 28475, 1652, 784, 27, 967, 4703, 46, 5970, 46, 3653, 5074, 1120, 2005, 301, 284, 2], "prompt_token_count": 128, "reference_codepoints": 256, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [30, 330, 4635, 81, 965, 2188, 2107, 641, 555, 2763, 32, 508, 370, 330, 4635, 81, 965, 24990, 284, 428, 330, 641, 555, 2763, 32, 508, 370, 330, 4635, 81, 965, 370, 330, 297, 81, 1327, 81, 965, 370, 330, 297, 81, 965, 370, 330, 4635, 370, 330, 297, 81, 1327, 2188, 284, 428, 330, 641, 555, 2763, 32, 508, 370, 330, 4635, 81, 965, 370, 330, 297, 81, 1327, 81, 965, 370, 330, 297, 81, 965, 370, 330, 4635, 370, 330, 297, 81, 1327, 2188, 284], "continuation_token_count": 87, "decoded": ", 'validate_url'], ['https://example.com', 'validate_url']],\n [ 'https://example.com', 'validate_url', 'is_valid_url', 'is_url', 'validate', 'is_valid'],\n [ 'https://example.com', 'validate_url', 'is_valid_url', 'is_url', 'validate', 'is_valid'],\n ", "decoded_codepoints": 256, "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:benchmarks/robustness-audit.js", "example_id": "00018c19ec6cd6268ff622433c230273c65d27194fc99ef1c2c01ba172f8ddaa", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 461, 6640, 20, 328, 312, 25, 801, 334, 301, 636, 44, 330, 965, 370, 2099, 543, 44, 225, 35, 30, 4467, 44, 2107, 4635, 81, 965, 370, 330, 297, 81, 1327, 81, 965, 370, 330, 297, 81, 965, 370, 330, 4635, 370, 330, 297, 81, 1327, 2188, 284, 13012, 44, 330, 2538, 312, 4865, 667, 688, 28896, 4946, 312, 802, 438, 312, 2080, 4808, 556, 24859, 3834, 6418, 284, 6792, 44, 3813, 710, 641, 555, 2763, 32, 508, 25, 3, 225, 298, 280, 1984, 2208, 26, 103, 5421, 96, 264, 442, 298, 32, 13627, 328, 2884, 525, 1461, 641, 657, 461, 1560, 26, 98, 32, 1299, 881, 7243, 284, 6658, 44, 330, 1070, 22045, 32, 2208, 1188, 1984, 2208, 78, 5441, 6042, 81, 965, 26, 103, 48775, 96, 264, 442, 1560, 26, 965, 2208, 26, 103, 490, 25, 801, 334, 301, 636, 44, 330, 15237, 2294, 370, 2099, 543, 44, 225, 35, 30, 4467, 44, 2107, 4635, 81, 15237, 81, 2294, 370, 330, 297, 81, 1327, 81, 2], "prompt_token_count": 169, "reference_codepoints": 256, "repo": "DietrichGebert/ponytail", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [20, 291, 313, 1819, 31, 3039, 31, 18006, 20, 291, 313, 1819, 31, 3039, 31, 18006], "continuation_token_count": 16, "decoded": "\"\n \"context-menu-shortcut\"\n \"context-menu-shortcut", "decoded_codepoints": 64, "document_id": "OpenCut-app/OpenCut@4d8c49ed0706c4dc145361e01c6b1f1a87cbb863:apps/web/src/components/ui/context-menu.tsx", "example_id": "000194e11e98367a2ae854875177155019195656bb34855ce2de06a7b759ec20", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 87, 4370, 397, 12399, 2962, 111, 284, 1681, 334, 829, 203, 111, 203, 203, 1126, 7049, 2672, 22229, 1371, 334, 2615, 30, 334, 2417, 2962, 203, 10696, 3475, 32, 42258, 46, 20, 662, 413, 27, 301, 334, 442, 308, 284, 333, 662, 397, 706, 31, 9040, 347, 1819, 31, 3039, 31, 18006, 20, 397, 2615, 1279, 4977, 26, 291, 313, 696, 31, 2837, 1344, 25743, 34, 32, 40, 36, 39, 3546, 79, 15555, 31, 15216, 270, 225, 3, 29242, 392, 291, 2615, 397, 14301, 397, 12399, 2962, 111, 284, 1681, 334, 829, 203, 111, 203, 203, 1358, 301, 334, 7049, 2672, 30, 334, 7049, 2672, 7897, 30, 334, 7049, 2672, 1777, 30, 334, 7049, 6348, 30, 334, 7049, 2672, 17786, 1097, 30, 334, 7049, 2672, 11891, 1097, 30, 334, 7049, 2672, 2168, 30, 334, 7049, 2672, 11145, 30, 334, 390, 2], "prompt_token_count": 142, "reference_codepoints": 64, "repo": "OpenCut-app/OpenCut", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [35, 657, 614, 324, 4712, 2513, 496, 440, 36, 2113], "continuation_token_count": 10, "decoded": "1\")],\n vec![user(\"2\"),", "decoded_codepoints": 33, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:crates/rig-core/src/memory.rs", "example_id": "000196ae625e1c188bef211ccbd45fb06f6d0747f15d06d9c601fe1ffdd245cf", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2029, 81, 24472, 81, 5893, 81, 6286, 346, 301, 291, 1207, 2349, 280, 701, 5017, 21178, 5017, 403, 890, 346, 324, 638, 1793, 81, 2029, 12143, 12617, 44, 7479, 46, 1175, 25894, 34373, 32, 8005, 81, 1731, 922, 9882, 922, 11814, 26, 36, 547, 6174, 1035, 584, 2349, 32, 1689, 26, 324, 313, 85, 392, 324, 4712, 2513, 496, 440, 35, 2113, 47330, 440, 3, 291, 829, 291, 638, 6240, 291, 638, 7513, 473, 584, 1207, 3892, 280, 2349, 32, 944, 440, 85, 1895, 6240, 32, 7513, 473, 291, 1201, 81, 3685, 4482, 5893, 32, 1657, 1026, 225, 36, 30, 313, 2029, 1395, 13771, 1755, 225, 36, 5218, 724, 284, 320, 446, 5496, 13586, 716, 403, 858, 79, 284, 2498, 2771, 20507, 81, 26017, 81, 5566, 81, 7543, 101, 81, 452, 81, 3369, 346, 2], "prompt_token_count": 136, "reference_codepoints": 32, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [81, 1267, 30, 1509, 30, 803, 81, 1055, 30, 5063, 81, 23469, 27, 291, 320, 291, 415, 4719, 81, 5483, 81, 2649, 301, 324, 1626, 45, 291, 320, 284, 320, 446, 2771, 537, 26, 7297, 44, 15068, 83, 428, 8776, 46, 3196, 48, 1130, 967, 6609, 301, 291, 6609, 301, 8528, 30, 5417, 44, 225, 34, 320, 284, 320, 203, 111, 203, 203, 3106, 6982, 83, 48, 14743, 436, 5412, 8028, 7332, 6982], "continuation_token_count": 73, "decoded": "_result, input, file_index, clean_baseline)\n }\n if stop_after_level {\n break;\n }\n }\n\n fn new(projects: &'a [Arc]) -> Self {\n Self { projects, idx: 0 }\n }\n}\n\nimpl<'a> Iterator for ProjectDepthGroups<'", "decoded_codepoints": 256, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/run/run.rs", "example_id": "00019a2493031a63656d1fc1b4f92d8efb41c709fe8d74beb7453705ca5e1a54", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2033, 638, 1945, 81, 2250, 81, 2649, 26, 2250, 81, 19245, 30, 1509, 30, 803, 81, 1055, 30, 5063, 81, 23469, 27, 324, 638, 6240, 12370, 291, 1207, 4031, 4719, 81, 5483, 81, 2649, 280, 901, 45, 584, 436, 2074, 81, 1267, 328, 2074, 81, 4295, 301, 324, 4719, 81, 5483, 81, 2649, 6592, 3523, 32, 11333, 81, 2250, 81, 1945, 26, 2250, 3, 3106, 6982, 83, 48, 5412, 8028, 7332, 6982, 83, 48, 301, 284, 2771, 537, 26, 7297, 44, 15068, 83, 428, 8776, 46, 3196, 48, 1130, 967, 6609, 301, 291, 6609, 301, 8528, 30, 5417, 44, 225, 34, 320, 284, 320, 203, 111, 203, 203, 3106, 6982, 83, 48, 14743, 436, 5412, 8028, 7332, 6982, 83, 48, 301, 284, 827, 6324, 280, 15068, 83, 428, 8776, 46, 3196, 48, 970, 446, 2771, 2354, 1652, 2278, 630, 27, 967, 3659, 46, 8171, 403, 1097, 48, 2], "prompt_token_count": 149, "reference_codepoints": 256, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [601, 630, 32, 5954, 81, 3423, 26, 1855, 30, 3443], "continuation_token_count": 10, "decoded": "return self.convert_uri(source, stream", "decoded_codepoints": 38, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/_markitdown.py", "example_id": "00019ac49a0d512885fd05258c8106e572ec35262bb923fe0845988ab9826967", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1468, 442, 630, 32, 5954, 81, 3423, 26, 1855, 30, 3443, 81, 1338, 47, 2238, 81, 1338, 30, 40265, 5321, 27, 324, 813, 44, 400, 442, 630, 32, 5954, 81, 1696, 26, 1855, 30, 3443, 81, 1338, 47, 2238, 81, 1338, 30, 1115, 5321, 27, 291, 588, 5380, 1300, 291, 4348, 6937, 26, 1855, 30, 5380, 711, 1802, 3, 30, 3443, 81, 1338, 47, 2238, 81, 1338, 30, 1115, 5321, 27, 291, 588, 4448, 1789, 291, 4348, 6937, 26, 1855, 30, 5167, 32, 1397, 711, 324, 442, 630, 32, 5954, 81, 1986, 26, 1855, 30, 3443, 81, 1338, 47, 2238, 81, 1338, 30, 1115, 5321, 27, 291, 588, 13312, 3443, 291, 4348, 308, 324, 1401, 269, 2], "prompt_token_count": 118, "reference_codepoints": 32, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [400, 436, 1938, 81, 1516, 30, 1938], "continuation_token_count": 7, "decoded": "\n for page_num, page", "decoded_codepoints": 35, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py", "example_id": "00019e2349eef4d6ec801403ef25b46e9b1357d34fcebede68e6a840877acfce", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1938, 81, 1516, 44, 6012, 1451, 308, 35, 31, 27845, 27, 584, 3759, 44, 324, 1682, 432, 1778, 3099, 5436, 101, 623, 330, 2238, 370, 330, 18209, 370, 330, 426, 370, 330, 107, 81, 966, 25, 291, 1524, 291, 5703, 280, 1605, 584, 1596, 44, 324, 17117, 81, 3651, 32, 14408, 26, 34, 27, 324, 623, 17117, 557, 859, 32, 1676, 26, 4682, 81, 3651, 27, 619, 17117, 44, 3, 1657, 26, 4682, 32, 5646, 711, 528, 1938, 280, 17117, 32, 5646, 77, 1637, 81, 1516, 429, 225, 35, 79, 225, 588, 225, 34, 31, 27845, 528, 5703, 280, 617, 8281, 81, 2242, 81, 1070, 81, 1637, 26, 1637, 27, 291, 2940, 3268, 44, 324, 3097, 584, 588, 11882, 810, 10693, 2747, 308, 1393, 372, 6822, 27, 291, 5703, 32, 3323, 2], "prompt_token_count": 133, "reference_codepoints": 32, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [202, 27, 478, 202, 862, 1056, 32, 601, 687, 610], "continuation_token_count": 10, "decoded": "\t)\n\n\tassert result.returncode ==", "decoded_codepoints": 32, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/test_browser_use_skill_install_docs.py", "example_id": "00019eab1322d7d6ca994bad03353a06b272d0ca7b2eec7923e9ae5bd1b25ac7", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 203, 202, 2121, 710, 22033, 4065, 785, 280, 2322, 32, 983, 12595, 32, 2524, 26, 2050, 436, 1742, 328, 308, 466, 26, 7789, 471, 4533, 32, 371, 463, 22033, 4065, 370, 330, 2847, 415, 1742, 27, 203, 202, 2121, 710, 12232, 81, 15976, 81, 14180, 81, 12896, 81, 3539, 785, 280, 596, 26, 7971, 81, 1132, 27, 478, 202, 1267, 280, 16539, 32, 1945, 26, 357, 202, 77, 3731, 32, 21823, 30, 6470, 95, 370, 330, 7128, 81, 539, 32, 4538, 370, 330, 10887, 370, 330, 3789, 2188, 357, 202, 15598, 47, 7789, 30, 203, 3, 30, 357, 202, 878, 47, 1815, 30, 357, 202, 5457, 47, 35, 34, 30, 203, 202, 27, 478, 202, 862, 1056, 32, 601, 687, 610, 225, 34, 30, 1056, 32, 8228, 203, 202, 862, 16726, 81, 1132, 32, 850, 81, 878, 26, 8644, 1057, 3310, 31, 42, 683, 610, 330, 3732, 2443, 769, 2958, 225, 37, 32, 35, 36, 769, 13874, 769, 5538, 5427, 31, 539, 25, 203, 202, 3140, 280, 308, 357, 202, 25, 1559, 78, 96, 25, 357, 202, 25, 426, 44, 5427, 31, 539, 78, 96, 25, 357, 202, 5438, 41963, 44, 313, 6997, 2], "prompt_token_count": 195, "reference_codepoints": 32, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [264, 1424, 26, 1294, 77, 36, 8492, 5492, 26, 34, 106, 34, 34, 293, 397, 1424, 26, 1294, 77, 37, 8492, 5492, 26, 34, 106, 34, 34, 293, 397], "continuation_token_count": 29, "decoded": " expect(raw[2]).toBe(0x00);\n expect(raw[3]).toBe(0x00);\n ", "decoded_codepoints": 69, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/completions/installers/powershell-installer.test.ts", "example_id": "0001a0c3df3128bcd1fd6231bd56ccba20580d693948557540ff72c09dff082c", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 97, 14753, 30, 5307, 4300, 6274, 78, 96, 895, 1687, 660, 1056, 280, 2014, 25079, 32, 7799, 4290, 26, 3613, 3206, 1215, 293, 397, 1424, 26, 1267, 547, 5492, 26, 1508, 293, 1687, 660, 5081, 280, 2014, 5980, 32, 32263, 26, 3959, 1215, 293, 397, 1424, 26, 1294, 77, 34, 8492, 5492, 26, 34, 13231, 293, 397, 1424, 26, 1294, 77, 35, 8492, 5492, 26, 34, 16353, 293, 275, 3, 26, 37, 547, 3108, 463, 3310, 31, 42, 895, 397, 1424, 26, 1286, 547, 38047, 3609, 4300, 6274, 895, 397, 1424, 26, 1286, 547, 38047, 3609, 18571, 15597, 44, 7383, 895, 284, 1122, 446, 561, 463, 3163, 7116, 9354, 31, 35, 40, 6744, 6274, 461, 11883, 561, 30355, 370, 2498, 1404, 532, 301, 397, 3066, 2164, 32, 2121, 32, 10933, 15597, 81, 2576, 81, 13236, 81, 1725, 2], "prompt_token_count": 139, "reference_codepoints": 64, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [203, 203, 589, 894, 81, 2548, 81, 5136, 81, 2946, 81, 2548, 81, 5136, 81, 2946, 81, 2548, 81, 5136, 81, 2946, 81, 2548, 81, 5136, 81, 2946, 81, 2548, 81, 5136, 81, 2946, 81, 2548, 81, 5136, 81, 2946, 81, 2548, 81, 5136, 81, 2946, 81, 2548, 81, 5136], "continuation_token_count": 50, "decoded": "\n\ndef test_fs_stats_system_fs_stats_system_fs_stats_system_fs_stats_system_fs_stats_system_fs_stats_system_fs_stats_system_fs_stats", "decoded_codepoints": 131, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/disk_test.go", "example_id": "0001a87218e35b65426753fb2b2ca2830c550ed06deaf5d12695f9c47f70072e", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 202, 10300, 12090, 26225, 44, 1992, 77, 800, 79, 10300, 32, 2338, 26225, 5944, 109, 577, 202, 20, 4223, 34, 563, 301, 558, 44, 313, 4223, 34, 392, 4841, 3644, 44, 225, 35, 34, 34, 34, 30, 5950, 3644, 44, 225, 35, 34, 34, 34, 835, 603, 202, 835, 355, 202, 835, 357, 202, 27, 1314, 202, 862, 32, 1815, 26, 102, 30, 3835, 27, 357, 202, 862, 32, 1324, 26, 102, 30, 313, 4223, 34, 392, 1202, 27, 357, 202, 862, 32, 1815, 26, 102, 30, 8616, 32, 4058, 27, 357, 202, 862, 32, 1324, 26, 102, 30, 31872, 8616, 32, 8849, 311, 38839, 27, 203, 202, 1748, 3, 6603, 2946, 32, 15516, 5773, 6807, 355, 202, 20, 12696, 392, 355, 202, 9663, 392, 355, 202, 1508, 30, 355, 202, 26162, 355, 202, 2548, 11512, 1222, 109, 603, 202, 18290, 44, 313, 9692, 289, 34, 96, 35, 98, 36, 392, 603, 202, 297, 2839, 44, 225, 901, 30, 603, 202, 10300, 12090, 26225, 44, 1992, 77, 800, 79, 10300, 32, 2338, 26225, 5944, 109, 577, 202, 20, 9692, 289, 34, 96, 35, 563, 301, 558, 44, 313, 9692, 289, 34, 96, 35, 392, 4841, 3644, 44, 225, 35, 34, 34, 34, 30, 5950, 3644, 44, 225, 35, 34, 34, 34, 111, 2], "prompt_token_count": 214, "reference_codepoints": 128, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [3677, 81, 1274, 81, 998, 81, 1719, 474, 225, 38, 45, 397, 632, 37, 36, 3677, 81, 1274, 81, 1449, 280, 3677, 81, 1274], "continuation_token_count": 24, "decoded": " hash_table_count_off + 4;\n U32 hash_table_max = hash_table", "decoded_codepoints": 64, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/pdb/pdb_parse.c", "example_id": "0001aeb9b55ef5f0b7c749096853185a783cb0edfa9582e5db10e073a4d63f76", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 4243, 81, 1657, 81, 1719, 474, 225, 38, 45, 397, 632, 37, 36, 4467, 81, 1439, 81, 520, 94, 280, 4467, 81, 1439, 81, 1719, 474, 4467, 81, 1657, 45, 8903, 434, 1858, 6371, 44, 3677, 1858, 397, 632, 37, 36, 3677, 81, 1274, 81, 998, 81, 1719, 280, 4467, 81, 1439, 81, 520, 94, 45, 397, 632, 37, 36, 3677, 81, 1274, 81, 1449, 81, 1719, 280, 3677, 81, 1274, 81, 998, 81, 1719, 474, 225, 38, 45, 8903, 632, 37, 36, 3677, 81, 1274, 81, 998, 280, 3, 225, 38, 2511, 706, 32, 891, 1511, 291, 3677, 81, 1274, 81, 998, 280, 10692, 71, 37, 36, 16886, 605, 32, 466, 474, 3677, 81, 1274, 81, 998, 81, 1719, 293, 291, 3677, 81, 1274, 81, 1449, 280, 10692, 71, 37, 36, 16886, 605, 32, 466, 474, 3677, 81, 1274, 81, 1449, 81, 1719, 293, 397, 320, 8903, 434, 1858, 6371, 44, 8153, 397, 632, 37, 36, 1929, 81, 2689, 81, 4068, 81, 1719, 280, 3677, 81, 1274, 81, 1449, 81, 1719, 474, 225, 38, 45, 664, 2], "prompt_token_count": 179, "reference_codepoints": 64, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [44, 715, 6761, 9011, 1114, 5954, 81, 452, 81, 916, 26, 1637, 32, 916, 81, 1286, 27, 528, 1135, 32161, 715, 4036, 400, 415, 646, 2530, 44, 528, 4036, 400, 415, 2530, 32, 1363, 26, 35, 27, 610, 313, 878, 563, 528], "continuation_token_count": 42, "decoded": ":\n yield cls._convert_to_html(page.html_content)\n case _:\n continue\n if not match:\n continue\n if match.group(1) == \"text\":\n ", "decoded_codepoints": 256, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/core/shell.py", "example_id": "0001b1298a3165d4fa6e19ce5eaa6e6fa12b102ec258772e47a4c2d119c92a61", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 45581, 9936, 26, 33574, 30, 1938, 32, 2079, 26, 2079, 81, 9003, 490, 324, 436, 1938, 328, 7853, 44, 400, 2530, 32808, 81, 681, 44, 528, 1135, 313, 8523, 563, 715, 6761, 9011, 1114, 5954, 81, 452, 81, 8523, 26, 1637, 32, 916, 81, 1286, 27, 528, 1135, 313, 916, 20, 3, 263, 829, 715, 436, 309, 328, 308, 1014, 2706, 96, 392, 1014, 2706, 100, 392, 1014, 2706, 102, 392, 1014, 313, 3003, 715, 8063, 1014, 588, 6478, 36059, 2], "prompt_token_count": 82, "reference_codepoints": 256, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [313, 2157, 81, 1508, 392, 291, 3049, 347, 16651, 706, 45834, 328, 322, 1688, 32, 4517, 1244], "continuation_token_count": 17, "decoded": " \"store_true\",\n help=\"Keep data URIs in the output. By default", "decoded_codepoints": 69, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/__main__.py", "example_id": "0001b154b03f755e757ff38d9424e634c36d75371b62d83c99ce2eb1ccffde4d", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 225, 4118, 32, 669, 81, 2669, 26, 291, 7915, 668, 31, 5558, 392, 291, 2125, 347, 2157, 81, 1508, 392, 291, 3049, 347, 720, 6713, 225, 37, 5334, 31, 9744, 10252, 32, 34430, 884, 3892, 1412, 1471, 322, 429, 98, 556, 769, 539, 31, 2796, 2470, 4414, 284, 829, 446, 4118, 32, 669, 81, 2669, 26, 291, 7915, 10504, 31, 605, 31, 26780, 392, 291, 3, 12596, 5703, 27, 328, 322, 1688, 32, 4517, 1244, 30, 706, 45834, 884, 33658, 4414, 284, 829, 446, 4118, 32, 669, 81, 2669, 440, 3607, 392, 34292, 347, 44917, 284, 2181, 280, 4118, 32, 2208, 81, 1132, 346, 446, 588, 8661, 322, 5016, 14230, 284, 5016, 81, 12118, 280, 2181, 32, 6728, 284, 415, 5016, 81, 12118, 438, 646, 1665, 2], "prompt_token_count": 128, "reference_codepoints": 64, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [769, 27, 397, 769, 27, 397, 769, 27, 397, 769, 27, 397, 769, 27, 397, 769, 27, 397, 769, 27, 397, 769, 27, 397, 769, 27, 397, 769, 27, 397, 769, 27, 397, 769, 27, 397, 769, 27, 397], "continuation_token_count": 39, "decoded": " --)\n --)\n --)\n --)\n --)\n --)\n --)\n --)\n --)\n --)\n --)\n --)\n --)\n ", "decoded_codepoints": 130, "document_id": "steipete/agent-scripts@bb3688355a4c1894dd53b4ed867d1600918fadf0:skills/npm/scripts/reserve-packages.sh", "example_id": "0001b189a89a84bd87332fdf2c440f8b60620926ba70253305beb4477f2f89ec", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 102, 3845, 397, 5733, 225, 36, 397, 10368, 284, 769, 1094, 27, 397, 37190, 9483, 36, 39516, 9785, 1623, 3845, 397, 37190, 81, 1460, 2743, 1102, 780, 47, 35, 397, 5733, 225, 36, 397, 10368, 284, 769, 3524, 27, 397, 13850, 7498, 9483, 36, 39516, 9785, 3497, 3845, 397, 5733, 225, 36, 397, 10368, 284, 429, 90, 523, 769, 4756, 27, 397, 6886, 397, 4323, 225, 34, 397, 10368, 284, 769, 27, 397, 3, 3348, 284, 2941, 397, 30103, 17475, 9372, 18663, 35, 657, 397, 5733, 397, 10368, 334, 2813, 329, 203, 5087, 203, 203, 21, 21778, 17163, 24256, 322, 20239, 1623, 636, 7351, 1591, 1597, 8189, 13413, 32, 203, 325, 428, 429, 96, 3941, 19846, 20, 1481, 962, 428, 3941, 10941, 81, 1460, 2743, 1102, 780, 20, 429, 3685, 225, 34, 4028, 1615, 334, 37190, 347, 16920, 20, 203, 5501, 203, 203, 325, 428, 6313, 21, 7604, 17475, 13283, 30631, 429, 3685, 225, 34, 4028, 361, 2], "prompt_token_count": 159, "reference_codepoints": 128, "repo": "steipete/agent-scripts", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [647, 5302, 44, 861, 30, 324, 827, 44, 330, 761, 370, 324, 3049], "continuation_token_count": 13, "decoded": " optional: true,\n type: 'file',\n help", "decoded_codepoints": 64, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/1688/download.js", "example_id": "0001b9d95a79302ab075a10a4a722719875867d7f61421302470ce0ee53dc441", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 636, 44, 330, 4984, 370, 284, 2857, 44, 330, 850, 370, 284, 3048, 44, 330, 47098, 20878, 225, 35, 40, 42, 42, 225, 20994, 9444, 3433, 7714, 4782, 1077, 14752, 4475, 27585, 11787, 47263, 370, 284, 5880, 44, 330, 1499, 32, 35, 40, 42, 42, 32, 508, 370, 284, 13689, 44, 39243, 32, 31784, 30, 284, 2181, 44, 428, 291, 301, 324, 636, 44, 330, 1131, 370, 324, 2129, 44, 861, 30, 324, 39161, 44, 861, 30, 1568, 3, 291, 301, 636, 44, 330, 2024, 370, 1244, 44, 3005, 35, 40, 42, 42, 31, 14552, 370, 3049, 44, 330, 16693, 15541, 25, 801, 284, 2505, 284, 6090, 44, 2107, 1055, 370, 330, 681, 370, 330, 1517, 370, 330, 891, 2188, 284, 3420, 44, 2498, 308, 1637, 30, 10306, 27, 532, 301, 291, 660, 13638, 280, 2014, 6571, 14015, 1562, 1612, 26, 1637, 30, 892, 26, 5321, 32, 1131, 7475, 330, 4646, 397, 2], "prompt_token_count": 154, "reference_codepoints": 64, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [647, 1422, 537, 3081, 26, 731, 293, 284, 320, 284, 442, 5760, 45, 203, 111, 203, 203, 4396, 667, 622, 74, 905, 15634, 33981, 26, 1637, 27, 301, 284, 1207, 5760, 45, 284, 1596, 301, 291, 2014], "continuation_token_count": 37, "decoded": " throw new Error(error);\n }\n return rows;\n}\n\nasync function getXiaoeCourses(page) {\n let rows;\n try {\n await", "decoded_codepoints": 132, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/xiaoe/courses.js", "example_id": "0001c201cc003ed80057ffef4ee68162229cfe989b17051832f21631f9df764f", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1421, 45, 203, 1748, 6620, 45, 203, 111, 203, 203, 4396, 667, 622, 74, 905, 15634, 33981, 26, 1637, 27, 301, 284, 1207, 5760, 45, 284, 1596, 301, 291, 2014, 1938, 32, 7761, 463, 641, 555, 19900, 32, 41497, 15634, 31, 6631, 32, 508, 13093, 301, 4465, 14877, 44, 330, 944, 370, 739, 5531, 11071, 44, 225, 42, 34, 34, 34, 1122, 291, 5760, 280, 2014, 1938, 32, 13697, 26, 1832, 33981, 3206, 1035, 284, 320, 2368, 308, 731, 27, 301, 664, 3, 261, 529, 5288, 372, 1149, 816, 905, 15634, 32751, 44, 2283, 1436, 13045, 324, 330, 1637, 1631, 646, 1159, 14380, 556, 3796, 1631, 526, 2129, 370, 291, 1093, 284, 320, 284, 415, 1429, 1261, 32, 15436, 26, 2138, 27, 1276, 5760, 32, 1322, 1720, 225, 34, 27, 301, 291, 1422, 537, 14893, 1394, 924, 26, 324, 330, 41497, 15634, 33, 19013, 370, 276, 2], "prompt_token_count": 148, "reference_codepoints": 128, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [261, 442, 45, 397, 320, 284, 320, 2368, 308, 731, 27, 301, 397, 660, 5797, 280, 372, 20253, 2301, 26, 6240, 40610, 2780, 1371, 804, 225, 36, 18284, 1687, 415, 308, 2184], "continuation_token_count": 32, "decoded": " return;\n }\n } catch (error) {\n const payload = toCleanupOutput(await unregisterStore({ id 2}));\n\n if (options", "decoded_codepoints": 130, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/commands/store.ts", "example_id": "0001c5c640409b6332fc0139f537ce593ce4294398e982400fac2668307c1ad3", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 351, 1048, 397, 1093, 284, 320, 334, 320, 719, 2498, 40610, 26, 314, 44, 802, 30, 2075, 44, 8809, 2526, 2031, 280, 2149, 711, 4664, 46, 1117, 48, 301, 284, 1596, 301, 397, 660, 5797, 280, 372, 20253, 2301, 26, 6240, 40610, 2780, 1371, 804, 10536, 1687, 415, 308, 2184, 32, 1260, 27, 301, 291, 1459, 2526, 26, 6263, 293, 291, 3, 225, 2075, 32, 1260, 30, 291, 301, 2968, 44, 744, 30, 10880, 44, 744, 30, 2276, 44, 744, 30, 2287, 44, 1605, 801, 291, 1048, 397, 1093, 284, 320, 334, 320, 719, 2498, 3345, 26, 314, 44, 802, 30, 2075, 44, 8809, 4913, 2031, 280, 2149, 711, 4664, 46, 1117, 48, 301, 284, 1596, 301, 397, 660, 1760, 280, 2014, 11656, 2780, 20253, 1371, 804, 225, 2], "prompt_token_count": 130, "reference_codepoints": 128, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [1468, 638, 2714, 346, 324, 638], "continuation_token_count": 6, "decoded": " .send()\n .", "decoded_codepoints": 33, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/languages/python/uv.rs", "example_id": "0001d8623d53091e1c2247271d12e146d458cff3a0d04ffd9be7a2f178966f1e", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 87, 4621, 16843, 1751, 372, 4281, 2330, 10078, 324, 617, 532, 442, 630, 32, 3789, 81, 1070, 81, 6656, 81, 1237, 26, 2157, 30, 1760, 30, 1914, 547, 6240, 30, 291, 1472, 584, 4588, 9170, 32902, 16726, 5035, 645, 44, 12263, 4125, 81, 965, 293, 291, 1207, 1789, 280, 10980, 37899, 81, 10923, 324, 638, 371, 1652, 1237, 81, 965, 27, 203, 3, 1109, 657, 324, 638, 2714, 346, 324, 638, 6240, 324, 638, 363, 81, 3356, 26, 2403, 12581, 403, 1397, 403, 731, 81, 979, 81, 1517, 27, 324, 638, 1793, 81, 1819, 40130, 2179, 9170, 5288, 372, 5630, 16726, 5035, 645, 4354, 1164, 821, 301, 1237, 81, 965, 111, 2131, 12370, 584, 1207, 5035, 44, 26024, 81, 1260, 403, 882, 280, 1789, 32, 1260, 922, 2], "prompt_token_count": 129, "reference_codepoints": 32, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [262, 436, 6024, 328, 24195, 44, 528, 415, 6024, 32, 3229, 32, 2040], "continuation_token_count": 13, "decoded": " for shape in shapes:\n if shape.shape.has", "decoded_codepoints": 64, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py", "example_id": "0001dfb8590035c6892b1a5f377ccd73b50b5a2cdd887b56d88802069767a037", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 3229, 32, 2040, 81, 878, 81, 1744, 44, 528, 415, 6024, 610, 1780, 44, 715, 8735, 81, 1286, 1454, 5100, 313, 474, 6024, 32, 878, 32, 94, 7201, 346, 474, 18474, 96, 20, 528, 813, 44, 715, 8735, 81, 1286, 1454, 6024, 32, 878, 474, 18474, 96, 20, 2110, 588, 7051, 41550, 291, 3, 9779, 44, 528, 8594, 81, 23312, 280, 8594, 26, 715, 6024, 32, 23312, 30, 715, 1202, 47, 5962, 816, 44, 308, 1014, 1897, 10359, 5267, 657, 415, 646, 816, 32, 1393, 813, 816, 32, 1393, 30, 1014, 1897, 10359, 5267, 657, 415, 646, 816, 32, 1873, 813, 2], "prompt_token_count": 103, "reference_codepoints": 64, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [81, 800, 81, 2668, 81, 102, 45, 334, 802, 81, 384, 280, 802], "continuation_token_count": 13, "decoded": "_string_buffer_t;\n string_ht = string", "decoded_codepoints": 38, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/pdb_ext/pdb_builder.c", "example_id": "0001e20c114eecd5a7fdba265b3e8b7a1c3296bb2b5d55f46c4164aed065f7fa", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1372, 81, 955, 81, 1347, 81, 6158, 26, 22731, 30, 632, 35, 40, 30, 2047, 81, 668, 32, 998, 293, 334, 2899, 32, 1855, 81, 761, 81, 426, 81, 2881, 81, 846, 280, 1914, 81, 761, 81, 426, 81, 21463, 81, 846, 45, 334, 12867, 81, 979, 81, 13449, 26, 491, 30, 225, 34, 30, 2047, 81, 846, 81, 998, 30, 3082, 91, 81, 1832, 81, 761, 81, 1338, 81, 5157, 81, 761, 81, 21463, 81, 2795, 30, 549, 2795, 293, 719, 434, 8921, 5852, 334, 892, 42, 802, 81, 2668, 280, 6677, 81, 3, 30, 802, 81, 384, 293, 719, 434, 6371, 803, 3099, 15521, 334, 892, 42, 720, 803, 81, 1338, 81, 45903, 280, 301, 34, 1255, 334, 596, 42, 81, 3542, 81, 2409, 26, 22731, 30, 549, 761, 81, 1338, 81, 45903, 293, 334, 596, 42, 81, 3542, 81, 2018, 81, 103, 35, 40, 26, 22731, 30, 549, 761, 81, 1338, 81, 45903, 30, 2047, 81, 998, 35, 40, 293, 334, 596, 42, 81, 3542, 81, 2018, 81, 103, 35, 40, 26, 22731, 30, 549, 761, 81, 1338, 81, 45903, 30, 3380, 81, 1855, 81, 761, 81, 998, 35, 40, 2], "prompt_token_count": 195, "reference_codepoints": 32, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [24, 301, 284, 660, 2488, 280, 3475, 32, 539, 2084, 46, 4424, 1714, 1308, 1563, 1693, 27, 284, 3475, 32, 48332, 4114, 225, 549, 301, 397, 660, 2488, 280, 3475, 32, 539, 2084, 46, 4424, 1714, 1308], "continuation_token_count": 37, "decoded": "& {\n const ref = React.useRef(null)\n React.useEffect(() & {\n const ref = React.useRef{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [2848, 280, 14161, 3135, 26, 7128, 81, 3959, 47, 7128, 81, 3959, 27, 357, 202, 1567, 81, 4891, 280, 3903, 5990, 346, 357, 202, 6589, 14612, 280, 7337, 9417, 14612, 26, 7128, 81, 2848], "continuation_token_count": 34, "decoded": "session = BrowserSession(browser_profile=browser_profile)\n\t\tevent_bus = EventBus()\n\t\twatchdog = SecurityWatchdog(browser_session", "decoded_codepoints": 128, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/security/test_domain_filtering.py", "example_id": "0001e2f86532be42486fe26c21412390077eaf1b07aa09282faf3a60a45d96fc", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 7622, 10375, 547, 2993, 478, 202, 589, 894, 81, 4884, 81, 668, 81, 10504, 101, 81, 5607, 81, 3592, 26, 784, 711, 357, 202, 2993, 1006, 688, 10375, 333, 225, 35, 34, 34, 3946, 4986, 5257, 9215, 2193, 7103, 357, 202, 1070, 323, 356, 352, 1188, 3903, 5990, 1314, 202, 1070, 5427, 81, 539, 32, 7128, 32, 6589, 14612, 101, 32, 4373, 81, 6589, 14612, 1188, 7337, 9417, 14612, 1314, 202, 7128, 81, 3, 357, 202, 7128, 81, 2848, 280, 14161, 3135, 26, 7128, 81, 3959, 47, 7128, 81, 3959, 27, 357, 202, 1567, 81, 4891, 280, 3903, 5990, 346, 357, 202, 6589, 14612, 280, 7337, 9417, 14612, 26, 7128, 81, 2848, 47, 7128, 81, 2848, 30, 1692, 81, 4891, 47, 1567, 81, 4891, 27, 1314, 202, 21, 9043, 4204, 526, 312, 1149, 357, 202, 862, 6937, 26, 7128, 81, 2848, 32, 7128, 81, 37835, 2], "prompt_token_count": 147, "reference_codepoints": 128, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [262, 638, 1832, 346, 324, 638, 15349, 473, 284, 773, 1133, 7897, 1554, 16016, 5507, 32, 5376, 26, 1126, 26, 1003, 7897, 1554, 16016, 5507, 27, 301, 291, 773, 1133, 7897, 1554, 16016, 5507, 32, 5376, 26, 1126, 26, 1003, 7897, 1554, 16016, 5507, 27, 301, 324, 773, 1133, 7897, 1554, 16016, 5507, 32, 5376, 26, 1126], "continuation_token_count": 57, "decoded": " .build()\n .toList();\n var timeTriggerWithWatermarks.forEach(function(timeTriggerWithWatermarks) {\n var timeTriggerWithWatermarks.forEach(function(timeTriggerWithWatermarks) {\n var timeTriggerWithWatermarks.forEach(function", "decoded_codepoints": 259, "document_id": "Netflix/maestro@abdbdadf8f075b8fa488c9efb386b468c709a63c:maestro-timetrigger/src/main/java/com/netflix/maestro/timetrigger/utils/TimeTriggerSubscriptionClient.java", "example_id": "0001e4066ad26b51c16aeeaa5fd668fdbe5047b8944520190d677407f3e74b4c", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2565, 26, 9141, 5229, 32, 6037, 81, 7100, 9629, 81, 36951, 30, 27084, 1035, 334, 320, 719, 1022, 8125, 10776, 372, 6063, 1474, 32, 569, 334, 945, 3717, 7897, 6136, 42542, 6136, 26, 11199, 10153, 30, 20462, 15298, 101, 1550, 27, 301, 284, 773, 1133, 7897, 1554, 16016, 5507, 280, 291, 3, 2407, 638, 1832, 1157, 324, 638, 15349, 473, 284, 442, 3717, 7897, 6136, 32, 4164, 346, 291, 638, 9874, 606, 26, 9874, 32, 7061, 1157, 291, 638, 9874, 2062, 26, 5229, 32, 4804, 81, 34850, 81, 8703, 18118, 81, 4530, 27, 291, 638, 9874, 7897, 15298, 26, 1700, 32, 11957, 7897, 15298, 1157, 397, 2], "prompt_token_count": 108, "reference_codepoints": 256, "repo": "Netflix/maestro", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [30, 27234, 1078, 3212, 280, 2149, 478, 202, 589, 1156, 1664, 3207, 784, 30, 1695, 81, 1515, 44, 225], "continuation_token_count": 19, "decoded": ", FileSystemState]] = {}\n\n\tdef __init__(self, base_dir: ", "decoded_codepoints": 56, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/filesystem/file_system.py", "example_id": "0001eca662f9b1f4c07e0ae94b1e6696aebf030c377f1bb9632a6a3b694058ee", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 285, 26, 784, 27, 967, 596, 44, 357, 202, 601, 330, 916, 25, 478, 203, 823, 12491, 974, 26, 1761, 974, 711, 203, 202, 2993, 5732, 803, 4736, 2993, 478, 202, 50, 2433, 203, 202, 589, 5016, 26, 784, 27, 967, 596, 44, 357, 202, 601, 330, 2593, 25, 478, 203, 823, 27234, 1078, 26, 44115, 711, 203, 202, 2993, 12642, 1603, 432, 322, 803, 2664, 2993, 478, 202, 2536, 44, 5436, 77, 466, 30, 5436, 77, 466, 3, 1215, 30, 1487, 81, 1536, 81, 2536, 44, 1560, 280, 2933, 711, 357, 202, 21, 7968, 322, 5380, 11741, 2670, 8276, 2599, 17094, 1664, 505, 357, 202, 784, 32, 1439, 81, 1515, 280, 5380, 26, 1439, 81, 1515, 27, 415, 6937, 26, 1439, 81, 1515, 30, 596, 27, 813, 1695, 81, 1515, 357, 202, 784, 32, 1439, 81, 1515, 32, 10174, 26, 19277, 47, 1815, 30, 2307, 81, 1253, 47, 1815, 27, 1314, 202, 21, 2648, 461, 793, 312, 409, 2], "prompt_token_count": 161, "reference_codepoints": 256, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [44, 400, 442, 31660, 11932, 1397, 26, 528, 6886, 47, 3220, 81, 8795, 32, 271, 81, 1824, 40130, 1158, 81, 21567, 32, 302, 81, 612, 922, 363, 81, 3356, 12143, 91, 110, 595, 32, 8795, 32, 6358, 35728, 528, 15994, 47, 3220, 81, 21567, 30, 528, 1542, 81, 1648, 47, 1160, 81, 1648], "continuation_token_count": 53, "decoded": ":\n return StreamingCompletionResponse(\n usage=final_usage.or_else(|| final_interaction.as_ref().and_then(|i| i.usage.clone())),\n interaction=final_interaction,\n model_version=model_version", "decoded_codepoints": 260, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:crates/rig-core/src/providers/gemini/interactions_api/streaming.rs", "example_id": "0001ed00f0b34bf668fb5d011ad7ce94f47bc4b5dcfb45696626739c09694034", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 9434, 13860, 403, 9782, 1397, 26, 18051, 11932, 1397, 301, 400, 6886, 44, 1158, 81, 8795, 32, 271, 81, 1824, 40130, 1158, 81, 21567, 32, 302, 81, 612, 922, 363, 81, 3356, 12143, 91, 110, 595, 32, 8795, 32, 6358, 35728, 400, 15994, 44, 1158, 81, 21567, 30, 400, 1542, 81, 1648, 30, 324, 16586, 3, 5970, 46, 103, 42, 16723, 203, 27, 967, 35446, 1151, 1862, 203, 2767, 284, 394, 44, 20214, 2725, 474, 14429, 474, 4101, 474, 1230, 403, 3972, 403, 3529, 474, 330, 1574, 30, 203, 109, 284, 1207, 4031, 1692, 81, 1855, 280, 12671, 41862, 403, 890, 26, 1580, 32, 6358, 1026, 1326, 293, 446, 1207, 3443, 280, 3443, 19, 301, 291, 2218, 1207, 4185, 26, 1567, 81, 1267, 27, 225, 2], "prompt_token_count": 127, "reference_codepoints": 256, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [390, 17734, 3842, 26, 1761, 44907, 711, 324, 636, 280, 313, 33982, 20, 324, 6660, 81, 20798, 280, 3037, 2763, 32, 508, 1446, 324, 1477, 81, 11400, 280, 3037, 641], "continuation_token_count": 30, "decoded": " CrawlRule(BaseSpider):\n name = \"crawl\"\n allowed_domains = [\"example.com\"]\n start_urls = [\"https", "decoded_codepoints": 129, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/spiders/test_sitemap.py", "example_id": "0001f3fa327011b1fa2329c9274f89a72ea8ca2e3186422798b79a744b81c4ff", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 965, 30, 26093, 347, 1536, 657, 284, 442, 5127, 478, 203, 4396, 665, 617, 6174, 26, 11661, 44, 10726, 4815, 27, 967, 1149, 44, 284, 442, 428, 1094, 2498, 436, 1623, 328, 1894, 272, 79, 478, 203, 823, 2108, 69, 23078, 44907, 4055, 44, 284, 477, 12408, 32, 1826, 32, 38326, 284, 2498, 665, 894, 81, 965, 470, 81, 1285, 30578, 81, 10997, 81, 7004, 26, 784, 711, 291, 443, 3, 784, 711, 400, 442, 428, 53, 17734, 3842, 26, 2359, 16653, 26, 4568, 47, 100, 9663, 8224, 33, 2113, 3309, 47, 784, 32, 2208, 81, 1526, 2177, 1064, 2498, 665, 3185, 81, 1526, 26, 784, 30, 1789, 711, 400, 6761, 3447, 1526, 563, 1789, 32, 965, 111, 584, 1869, 1391, 280, 358, 346, 291, 963, 280, 2014, 617, 6174, 26, 35585, 1114, 2], "prompt_token_count": 135, "reference_codepoints": 128, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [385, 31, 38, 32, 35, 1801, 529, 89, 385, 31, 38, 32, 35, 31, 16432, 1801, 529, 89, 385, 31, 38, 32, 35, 31, 16432, 31, 5323, 1801, 529, 89, 385, 31, 38, 32, 35, 31, 16432, 31, 16432], "continuation_token_count": 39, "decoded": "pt-4.1`, `gpt-4.1-lite`, `gpt-4.1-lite-latest`, `gpt-4.1-lite-lite", "decoded_codepoints": 66, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:skills/cloud/references/api-v2.md", "example_id": "0002007abf2e30bc4e300ee7da2b84dda781f37173eaf33c25b7a0ecee9b88b3", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 520, 81, 2795, 81, 363, 81, 2848, 82, 523, 203, 110, 6548, 1533, 523, 529, 2480, 1801, 529, 32100, 82, 523, 203, 110, 14161, 3135, 1533, 523, 529, 2480, 1801, 529, 32100, 82, 523, 203, 110, 15637, 47865, 523, 529, 352, 1801, 529, 3418, 1801, 529, 2173, 1801, 529, 283, 1801, 529, 11554, 1801, 529, 4452, 1801, 529, 286, 1801, 529, 5501, 1801, 529, 1173, 1801, 529, 266, 82, 20893, 35, 42, 39, 1829, 27, 523, 203, 110, 24557, 3199, 11071, 523, 529, 7128, 31, 539, 31, 611, 95, 1801, 529, 89, 385, 31, 38, 32, 35, 1801, 529, 89, 385, 3, 1801, 529, 300, 15920, 31, 9237, 31, 5323, 1801, 529, 300, 15920, 31, 9237, 31, 16432, 31, 5323, 1801, 529, 300, 15920, 31, 37, 31, 9237, 31, 8687, 1801, 529, 300, 15920, 31, 37, 32, 35, 31, 9237, 31, 16432, 1801, 529, 8475, 795, 31, 1155, 1299, 31, 38, 31, 36, 34, 36, 39, 34, 39, 35, 38, 1801, 529, 89, 385, 31, 38, 97, 1801, 529, 89, 385, 31, 38, 97, 31, 15920, 1801, 529, 611, 4478, 31, 38, 31, 934, 424, 1226, 31, 35, 41, 84, 31, 35, 36, 42, 87, 31, 266, 1167, 1801, 529, 8475, 795, 31, 37, 31, 41, 31, 1155, 1299, 31, 36, 34, 36, 39, 34, 36, 35, 43, 82, 523, 203, 110, 16206, 14264, 523, 529, 893, 33, 2], "prompt_token_count": 230, "reference_codepoints": 64, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [958, 442, 45, 616, 320, 813, 301, 324, 442, 45, 616, 320, 291, 320, 813, 301, 616, 660, 6765, 280, 2322, 32, 23407, 463, 8439, 895, 616], "continuation_token_count": 27, "decoded": " return;\n } else {\n return;\n }\n } else {\n const home = os.getenv('HOME');\n ", "decoded_codepoints": 134, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/hooks/caveman-config.js", "example_id": "0002074dce5d0a0d68d87e957ad34be8cce01756fcc3c827e29ed9804c4651f7", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1232, 2073, 2359, 1157, 301, 291, 4011, 2976, 280, 5980, 32, 35490, 4764, 26, 1515, 293, 291, 660, 4011, 5944, 280, 5980, 32, 4597, 4764, 26, 4543, 2976, 293, 291, 415, 1429, 4543, 5944, 32, 30841, 1157, 442, 45, 291, 415, 308, 5139, 2164, 32, 371, 1890, 1720, 330, 1126, 683, 301, 616, 415, 308, 4543, 5944, 32, 1890, 3326, 2164, 32, 371, 1890, 1157, 301, 397, 3, 647, 442, 45, 616, 320, 291, 320, 813, 301, 616, 660, 6765, 280, 2322, 32, 2833, 1515, 473, 616, 660, 17666, 280, 1519, 32, 5284, 26, 4543, 2976, 547, 10493, 473, 616, 660, 17666, 4625, 280, 1519, 32, 5284, 26, 2833, 547, 10493, 473, 616, 415, 1429, 20030, 32, 13912, 26, 4382, 2], "prompt_token_count": 122, "reference_codepoints": 128, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [1594, 323, 1178, 280, 301, 34, 106, 34, 34, 1255, 284, 343, 280, 617, 858, 81, 8018, 81, 11751, 6714, 26, 83, 30, 323, 30, 225, 34, 293, 284, 1201], "continuation_token_count": 30, "decoded": "char b[] = {0x00};\n d = _test_distance_hamming(a, b, 0);\n assert", "decoded_codepoints": 70, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:tests/test-unit.c", "example_id": "000207d571c2f990d0da7a7f6e68da1fcef998498ba6ee369ee08a51e0e1b91a", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 88, 26, 86, 429, 225, 36, 32, 34, 88, 27, 333, 225, 35, 87, 31, 40, 88, 293, 334, 320, 719, 5242, 440, 225, 3367, 7291, 81, 4952, 482, 81, 1808, 3312, 5403, 5327, 96, 724, 203, 111, 203, 203, 1117, 894, 81, 8018, 81, 11751, 6714, 346, 301, 334, 5242, 440, 15624, 904, 101, 25378, 96, 392, 1156, 1298, 15683, 334, 1897, 343, 45, 719, 434, 17492, 1578, 3493, 8212, 44, 7291, 280, 225, 34, 334, 301, 284, 3622, 1351, 312, 1178, 280, 301, 34, 4769, 1255, 284, 3622, 225, 3, 862, 26, 86, 610, 225, 34, 32, 34, 88, 293, 334, 320, 719, 434, 3367, 3449, 44, 7291, 280, 225, 42, 334, 301, 284, 3622, 1351, 312, 1178, 280, 301, 34, 4769, 1255, 284, 3622, 1351, 323, 1178, 280, 301, 34, 106, 34, 34, 1255, 284, 343, 280, 617, 858, 81, 8018, 81, 11751, 6714, 26, 83, 30, 323, 30, 225, 42, 293, 284, 1201, 26, 86, 610, 225, 42, 32, 34, 88, 293, 334, 320, 719, 434, 46079, 3449, 44, 225, 34, 4769, 8480, 225, 34, 106, 34, 56, 280, 225, 38, 7030, 3178, 334, 301, 284, 707, 3434, 2], "prompt_token_count": 194, "reference_codepoints": 64, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [47690, 6238, 2606, 203, 12281, 225, 7349, 44, 10086], "continuation_token_count": 9, "decoded": "─────────────────────────────────────\n│ Core: ", "decoded_codepoints": 71, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:engineering-book/src/ch09-no-std-and-feature-verification.md", "example_id": "0002098efcb58405c9a54fc6ff930a4676fe2877ccfc90df9c55cc0bb3e986b7", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 10016, 8684, 308, 5553, 322, 6642, 20748, 27, 203, 31, 551, 6600, 25473, 28814, 308, 3142, 31, 47839, 20913, 2770, 17528, 27, 203, 31, 21192, 31, 2649, 29171, 87, 28814, 308, 6474, 2297, 556, 484, 11603, 56, 24931, 27, 203, 203, 1482, 529, 1262, 82, 8480, 529, 3558, 82, 8480, 529, 1530, 82, 12011, 886, 27945, 7950, 483, 203, 203, 914, 878, 203, 1740, 239, 47690, 6238, 2606, 3, 6797, 5283, 203, 12281, 225, 35838, 328, 5296, 474, 6157, 30, 14875, 2045, 44, 10086, 5283, 203, 12281, 225, 14050, 2032, 439, 33, 65, 308, 1530, 403, 2548, 30, 1230, 403, 716, 27, 12992, 5283, 203, 12281, 225, 14050, 8159, 299, 308, 1530, 403, 1299, 27, 15921, 5283, 203, 12281, 225, 14050, 7800, 101, 308, 1530, 403, 3426, 27, 2407, 2], "prompt_token_count": 131, "reference_codepoints": 64, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [27, 203, 202, 3437, 351, 4991, 1468], "continuation_token_count": 7, "decoded": ")\n\tPort integer ", "decoded_codepoints": 33, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/server.go", "example_id": "0002162ccba7efcc4ca7fa65d334afef3dd4085292c1179d0e95bc5767f326f1", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 100, 424, 2031, 4304, 3488, 2075, 436, 8049, 322, 17727, 2145, 32, 203, 681, 4226, 2031, 1671, 301, 203, 202, 6762, 264, 802, 1468, 434, 8159, 2965, 372, 14884, 544, 308, 87, 32, 89, 4317, 10685, 38, 39, 42, 41, 40, 20, 556, 2430, 983, 33, 452, 33, 4817, 657, 203, 202, 4711, 802, 1468, 434, 8159, 827, 2884, 9374, 20, 556, 313, 16705, 20, 3, 19466, 562, 5036, 436, 9156, 203, 111, 203, 203, 306, 20089, 12778, 31764, 20089, 7041, 810, 3523, 2484, 372, 7358, 16834, 11708, 32, 203, 869, 20089, 12778, 1992, 77, 800, 79, 35647, 32, 2062, 203, 203, 306, 4793, 2059, 11187, 322, 17727, 2145, 623, 322, 3943, 2075, 32, 203, 306, 2030, 1359, 3009, 322, 2145, 623, 408, 2], "prompt_token_count": 125, "reference_codepoints": 32, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [835, 400, 301, 3835, 44, 861, 30, 5816, 44, 1605, 801, 400, 301, 3835], "continuation_token_count": 14, "decoded": "},\n { ok: true, missing: [] },\n { ok", "decoded_codepoints": 66, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/xianyu/publish.test.js", "example_id": "00021d81d29da9eb2205a7ac5992cedca8a80b6acd604c101072f11e53021d0d", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 96, 369, 1419, 26, 2019, 6136, 924, 293, 584, 2014, 1424, 26, 7211, 2019, 32, 1298, 26, 2682, 1969, 1371, 324, 13396, 5472, 44, 428, 400, 301, 1401, 9681, 1241, 44, 861, 801, 400, 301, 3835, 44, 861, 801, 400, 301, 3835, 44, 861, 30, 5816, 44, 1605, 801, 400, 301, 3835, 44, 861, 225, 3, 26, 2019, 6136, 924, 293, 284, 1122, 446, 561, 463, 7128, 6215, 3261, 438, 2498, 461, 3217, 20639, 7829, 17510, 370, 2498, 1404, 532, 301, 291, 660, 1056, 280, 2014, 1420, 9610, 3206, 10385, 1831, 772, 1640, 48, 15472, 377, 1640, 855, 1831, 10154, 1156, 858, 9818, 1832, 1908, 4220, 26968, 463, 38352, 11295, 5192, 4646, 3017, 2], "prompt_token_count": 115, "reference_codepoints": 64, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [43, 43, 392, 324, 588, 7688, 225, 40, 44, 24517, 2274, 16274, 324, 313, 55, 1252, 11158, 295, 24517, 2274, 16274, 392, 324, 313, 8242, 31, 43, 34, 35, 36, 392, 324, 3941, 39, 43, 32, 43, 43], "continuation_token_count": 38, "decoded": "99\",\n # Product 6: Wireless Mouse\n \"Ergonomic Wireless Mouse\",\n \"ACC-9012\",\n \"$59.99", "decoded_codepoints": 128, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_pdf_tables.py", "example_id": "00022453497390c8e3e46ea0a42333046be4ef203bbfc6f2772b86420ef959e0", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 392, 324, 313, 7979, 40570, 429, 41891, 19866, 392, 324, 313, 24191, 31, 39, 39, 36, 35, 392, 324, 3941, 37, 38, 43, 32, 43, 43, 392, 324, 3941, 36, 43, 43, 32, 43, 43, 392, 324, 588, 7688, 225, 36, 44, 12621, 31, 53, 17347, 324, 313, 13291, 31, 53, 17347, 225, 41, 31, 266, 31, 35, 23630, 392, 324, 313, 8242, 31, 42, 42, 37, 38, 392, 324, 3941, 41, 43, 32, 43, 43, 392, 324, 3941, 35, 39, 43, 32, 3, 958, 3941, 36, 40, 34, 32, 34, 34, 392, 324, 588, 7688, 225, 38, 44, 24517, 2274, 16274, 324, 313, 55, 1252, 11158, 295, 24517, 2274, 16274, 392, 324, 313, 8242, 31, 43, 34, 35, 36, 392, 324, 3941, 39, 43, 32, 43, 43, 392, 324, 588, 7688, 225, 39, 44, 14215, 14106, 299, 27989, 324, 313, 4615, 14106, 299, 27989, 392, 324, 313, 53, 3195, 31, 35, 35, 39, 40, 392, 291, 2], "prompt_token_count": 159, "reference_codepoints": 128, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [32, 6060, 1162, 2872, 27, 532, 2530, 32, 983, 1720, 13012], "continuation_token_count": 11, "decoded": ".some((match) => match.path === prompt", "decoded_codepoints": 38, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/update.ts", "example_id": "0002245f825b75caf879f93df29bdd26773ded31e4cf6bcf020f9f32e4950be0", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 19739, 1867, 606, 27, 532, 3304, 1227, 106, 11199, 101, 32, 2040, 26, 9874, 606, 4236, 446, 415, 308, 268, 3471, 444, 16197, 32, 1322, 848, 225, 34, 27, 301, 397, 2014, 458, 32, 14413, 23025, 20253, 26, 291, 2074, 1215, 30, 291, 8298, 4455, 23025, 18249, 3839, 26, 616, 13879, 30, 616, 10606, 444, 16197, 32, 1110, 1162, 13232, 27, 532, 3, 284, 320, 446, 660, 23616, 16197, 280, 622, 23025, 4455, 18249, 16197, 26, 18557, 27, 397, 638, 2029, 1162, 13232, 27, 532, 653, 268, 3471, 444, 16197, 32, 6060, 1162, 2872, 27, 532, 2530, 32, 983, 1720, 13012, 32, 983, 876, 446, 415, 308, 26946, 16197, 32, 1322, 848, 225, 34, 27, 301, 397, 2549, 32, 751, 26, 30239, 32, 14970, 463, 2626, 4106, 18329, 3962, 2], "prompt_token_count": 131, "reference_codepoints": 32, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [202, 862, 32, 1324, 26, 102, 30, 1692, 32, 2301, 32, 1175], "continuation_token_count": 12, "decoded": "\tassert.Equal(t, event.Output.Message", "decoded_codepoints": 37, "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/interrupt_test.go", "example_id": "000229d9136ff151dcfae1a368a9dfbc4811e4b4f58f20c4f655982bc5c680b0", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 303, 524, 32, 1175, 32, 1777, 30, 313, 1772, 7669, 9435, 623, 706, 20791, 4257, 657, 203, 202, 1567, 30, 3835, 280, 3850, 32, 3353, 346, 203, 202, 862, 32, 1815, 26, 102, 30, 3835, 27, 203, 202, 862, 32, 15109, 26, 102, 30, 1692, 32, 4309, 27, 203, 202, 862, 32, 1324, 26, 102, 30, 1692, 32, 2301, 32, 1175, 2301, 32, 1175, 32, 1777, 30, 313, 14704, 657, 203, 202, 3739, 3835, 280, 3850, 32, 3353, 346, 203, 202, 862, 32, 2700, 26, 102, 30, 3835, 27, 203, 3, 202, 601, 549, 1772, 2780, 109, 357, 202, 95, 44, 1992, 77, 800, 18311, 2263, 6807, 203, 202, 111, 203, 111, 203, 203, 681, 1672, 2780, 1671, 301, 203, 202, 95, 1992, 77, 800, 18311, 2263, 203, 111, 203, 203, 1298, 308, 95, 319, 1772, 2780, 27, 1756, 2176, 1619, 32, 1222, 30, 1202, 802, 30, 786, 1605, 2263, 27, 1048, 301, 203, 202, 95, 32, 95, 77, 678, 79, 280, 786, 203, 202, 601, 1302, 203, 111, 203, 203, 1298, 308, 95, 319, 1772, 2780, 27, 1390, 2176, 1619, 32, 1222, 30, 1202, 802, 27, 2], "prompt_token_count": 189, "reference_codepoints": 32, "repo": "cloudwego/eino", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [2796, 392, 291, 2125, 347, 2157, 81, 1508, 392, 291, 3049, 347, 4391, 322, 429, 98, 2470, 372, 5543, 372, 6256, 20107, 17443, 308, 87, 32, 89, 4317, 17117, 30, 10561, 30, 317, 38, 547, 34430, 884, 3892, 1412, 1471, 322, 429, 98, 2470, 4414, 284, 829, 446, 4118, 32, 669, 81, 2669, 26, 291, 4825, 86, 392, 291, 7915, 2811, 392, 291, 2125, 347, 2157], "continuation_token_count": 66, "decoded": "plugin\",\n action=\"store_true\",\n help=\"Use the -p option to route to Content Understanding (e.g., pdf,jpeg,mp4). Plugins are loaded when using the -p option.\",\n )\n\n parser.add_argument(\n \"-d\",\n \"--debug\",\n action=\"store", "decoded_codepoints": 259, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/__main__.py", "example_id": "00022aa34962fccab14944bb39d7d38a1850d200259d3a5b25d8455934533e1f", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 958, 7915, 9802, 31, 761, 31, 2516, 392, 291, 827, 47, 466, 30, 291, 3049, 347, 34010, 31, 26398, 1149, 432, 803, 3738, 372, 5543, 372, 6256, 20107, 17443, 308, 87, 32, 89, 4317, 17117, 30, 10561, 30, 317, 38, 547, 1670, 24143, 30, 1169, 5420, 3738, 884, 1118, 5643, 4414, 284, 829, 446, 4118, 32, 669, 81, 2669, 26, 291, 4825, 98, 392, 291, 7915, 539, 31, 3, 37, 5334, 31, 9744, 10252, 32, 34430, 884, 3892, 1412, 1471, 322, 429, 98, 556, 769, 539, 31, 2796, 2470, 4414, 284, 829, 446, 4118, 32, 669, 81, 2669, 26, 291, 7915, 10504, 31, 605, 31, 26780, 392, 291, 2125, 347, 2157, 81, 1508, 392, 291, 3049, 347, 16651, 706, 45834, 308, 6228, 1695, 40, 38, 31, 12596, 5703, 27, 328, 322, 1688, 32, 4517, 1244, 30, 225, 2], "prompt_token_count": 139, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [334, 442, 45, 203, 111, 203, 203, 730, 46586, 280, 2771, 4114], "continuation_token_count": 12, "decoded": "\n return;\n}\n\nlet debounce = fn(()", "decoded_codepoints": 34, "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:benchmarks/correctness.js", "example_id": "00022c4b8eaf1ee57d4c9dd6bc8bb6b2f651012fe95480b32675490950109e20", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 87, 32, 687, 111, 203, 203, 306, 7477, 322, 46586, 667, 203, 913, 2771, 280, 5940, 46586, 1720, 330, 1126, 25, 1018, 46586, 334, 499, 5940, 2297, 3326, 330, 6376, 25, 962, 5940, 2297, 32, 3783, 1720, 330, 1126, 25, 1018, 2297, 32, 3783, 334, 499, 744, 45, 203, 203, 325, 1429, 3359, 27, 301, 334, 2549, 32, 731, 440, 8534, 44, 1289, 46586, 667, 2431, 657, 3, 409, 27807, 318, 667, 1395, 646, 8379, 13282, 203, 730, 1476, 1534, 280, 225, 34, 45, 203, 913, 409, 27807, 318, 280, 2771, 4114, 532, 301, 1476, 1534, 3334, 801, 225, 39, 34, 293, 203, 286, 27807, 318, 473, 203, 286, 27807, 318, 473, 203, 286, 27807, 318, 473, 203, 203, 325, 308, 1851, 1534, 848, 225, 34, 27, 301, 334, 2549, 32, 731, 440, 8534, 44, 46586, 30303, 13282, 308, 3163, 4465, 13372, 334, 2164, 32, 87, 2], "prompt_token_count": 148, "reference_codepoints": 32, "repo": "DietrichGebert/ponytail", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [44, 357, 202, 1704, 3420, 346, 301, 355, 202, 3739, 1137, 1025, 9161, 32, 57, 4315, 6189, 26, 2095, 30, 549, 57, 4315, 1104, 109, 603, 202, 5516, 44, 313, 731, 392, 355, 202, 1748, 355, 202, 325, 1137, 6901, 310, 45, 355, 202, 5087, 1025, 1930, 26, 6622, 1560], "continuation_token_count": 50, "decoded": ":\n\t\tgo func() {\n\t\t\t_, err := backend.GrepRaw(ctx, &GrepRequest{\n\t\t\t\tPattern: \"error\",\n\t\t\t})\n\t\t\tif err!= n;\n\t\t\tdone := make(chan bool", "decoded_codepoints": 132, "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/filesystem/backend_inmemory_test.go", "example_id": "00023495fc16db28f029eed94ab19391bf2fccf7af0db6904068793251be6a06", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 4315, 6189, 3803, 44, 904, 104, 392, 1137, 27, 357, 202, 111, 357, 202, 325, 2069, 26, 8933, 27, 863, 225, 35, 301, 355, 202, 102, 32, 5497, 440, 7700, 225, 35, 2530, 30, 5424, 904, 86, 392, 2069, 26, 8933, 490, 357, 202, 111, 203, 202, 1748, 203, 111, 203, 203, 1298, 2108, 35500, 10564, 81, 57, 4315, 6189, 81, 18720, 26, 102, 319, 4266, 32, 70, 27, 301, 203, 202, 7878, 1025, 3136, 35500, 10564, 346, 203, 202, 2095, 1025, 1619, 32, 5770, 346, 478, 202, 979, 595, 1025, 225, 34, 45, 595, 3, 623, 1048, 1474, 392, 595, 471, 357, 202, 1748, 203, 202, 111, 478, 202, 102, 32, 2529, 440, 8347, 14173, 7373, 392, 3420, 26, 102, 319, 4266, 32, 70, 27, 301, 357, 202, 5087, 1025, 1930, 26, 6622, 1560, 27, 357, 202, 979, 595, 1025, 225, 34, 45, 595, 333, 225, 35, 34, 45, 595, 1046, 301, 355, 202, 1704, 3420, 346, 301, 603, 202, 3739, 1137, 1025, 9161, 32, 57, 4315, 6189, 26, 2095, 30, 549, 57, 4315, 1104, 109, 577, 202, 5516, 44, 313, 731, 392, 603, 202, 1748, 603, 202, 325, 1137, 863, 310, 2], "prompt_token_count": 195, "reference_codepoints": 128, "repo": "cloudwego/eino", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [313, 10586, 21404, 36, 54, 1044, 9929, 34, 8871, 96, 20, 284, 313, 10586, 21404, 36, 54, 1044, 9929, 35, 8871, 96, 20, 284], "continuation_token_count": 24, "decoded": " \"uniform sampler2D uTex0;\\n\"\n \"uniform sampler2D uTex1;\\n\"\n ", "decoded_codepoints": 66, "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:renderers/GLES3/clay_renderer_gles3.h", "example_id": "00023d247a24191a43935a6d59d02fdb50bb9da0afb04e5177602acec8f8aa6d", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1843, 81, 2731, 280, 4712, 38, 26, 1442, 85, 319, 4712, 36, 26, 35, 32, 34, 30, 429, 35, 32, 34, 471, 225, 34, 32, 34, 30, 225, 35, 32, 34, 21814, 96, 20, 284, 313, 264, 354, 12232, 280, 312, 12232, 8871, 96, 20, 284, 313, 264, 354, 1514, 280, 312, 1514, 8871, 96, 20, 284, 313, 264, 354, 9929, 9490, 280, 312, 9929, 9490, 8871, 96, 20, 284, 313, 4104, 96, 866, 203, 203, 913, 1351, 319, 38130, 37, 81, 6016, 81, 36113, 81, 21026, 280, 284, 3194, 3898, 81, 4530, 284, 2706, 96, 20, 284, 313, 15144, 10058, 2277, 1897, 8871, 96, 20, 284, 3, 8871, 96, 20, 284, 313, 10586, 21404, 36, 54, 1044, 9929, 34, 8871, 96, 20, 284, 313, 10586, 21404, 36, 54, 1044, 9929, 35, 8871, 96, 20, 284, 313, 10586, 21404, 36, 54, 1044, 9929, 36, 8871, 96, 20, 284, 313, 10586, 21404, 36, 54, 1044, 9929, 37, 8871, 96, 20, 284, 313, 541, 4712, 38, 17854, 1514, 8871, 96, 20, 284, 313, 1117, 2575, 346, 6913, 96, 20, 284, 313, 264, 629, 9848, 280, 629, 26, 104, 9929, 9490, 474, 225, 34, 32, 39, 21814, 96, 20, 284, 313, 264, 1897, 14755, 8871, 2], "prompt_token_count": 204, "reference_codepoints": 64, "repo": "nicbarker/clay", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [1559, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523, 5094, 523], "continuation_token_count": 86, "decoded": "--- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |", "decoded_codepoints": 257, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/_test_vectors.py", "example_id": "000241141d9ec2c073ee7c0c308334211340a241c8c73a1e9714c1e09eeffa20", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 696, 9726, 37, 53, 3672, 23, 36, 34, 1644, 23, 37, 54, 392, 291, 2505, 284, 2588, 284, 2032, 1006, 2863, 26, 291, 4870, 347, 858, 81, 874, 10640, 4441, 32, 4700, 392, 291, 18346, 681, 347, 878, 33, 4700, 392, 291, 8485, 347, 2219, 43, 37, 36, 392, 291, 1984, 47, 2521, 30, 291, 2298, 81, 1017, 6020, 324, 29425, 225, 40901, 523, 42761, 41036, 114, 523, 225, 32471, 5977, 523, 392, 324, 29425, 5094, 523, 5094, 523, 5094, 225, 3, 20, 14510, 392, 291, 1984, 47, 2521, 30, 291, 2298, 81, 1017, 6020, 324, 313, 39, 84, 40, 38, 85, 42, 42, 85, 31, 84, 37, 85, 37, 31, 38, 39, 35, 34, 31, 30582, 42, 31, 1804, 34, 84, 36, 34, 34, 40, 34, 36, 86, 42, 392, 324, 313, 43, 41, 34, 34, 3455, 43, 43, 31, 40, 40, 42, 39, 31, 38, 34, 84, 38, 31, 43, 83, 37, 83, 31, 39, 87, 38, 34, 40, 27414, 37, 41, 88, 37, 392, 291, 2505, 291, 2298, 81, 1206, 81, 1017, 33792, 284, 2588, 284, 2032, 1006, 2863, 26, 291, 4870, 347, 858, 81, 17260, 32, 2593, 392, 664, 2], "prompt_token_count": 195, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [284, 20344, 14704, 523, 827, 610, 313, 2171, 657, 461, 284, 20344, 14704, 81, 269, 523, 827, 610, 313, 2171, 657, 461, 284, 20344, 14704, 81, 1170, 523, 827, 610, 313, 2171, 657, 461, 284], "continuation_token_count": 35, "decoded": "\n (.completed | type == \"number\") and\n (.completed_at | type == \"number\") and\n (.completed_by | type == \"number\") and\n ", "decoded_codepoints": 130, "document_id": "steipete/agent-scripts@bb3688355a4c1894dd53b4ed867d1600918fadf0:skills/clawsweeper-status/scripts/clawsweeper-status.sh", "example_id": "00024a1c855fcf70c62510e5982a946ee60a5a3285357e7465828d4e28f4214e", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2785, 5979, 641, 555, 573, 812, 1586, 21603, 32, 1676, 573, 812, 32, 3044, 3188, 1237, 33, 16925, 31, 6212, 31, 3926, 20, 766, 284, 848, 25526, 16925, 81, 3926, 81, 1260, 20, 225, 36, 9159, 1902, 33, 1693, 962, 766, 334, 21023, 429, 87, 330, 284, 827, 610, 313, 1473, 20, 461, 284, 20344, 9671, 523, 827, 610, 313, 2171, 657, 461, 284, 20344, 7147, 299, 523, 827, 610, 313, 2171, 657, 461, 284, 20344, 1315, 86, 523, 827, 610, 313, 2171, 657, 461, 3, 7230, 47, 1870, 334, 5242, 17246, 78, 96, 25, 848, 25526, 16925, 81, 3926, 81, 1260, 20, 203, 5501, 203, 203, 2480, 81, 998, 19709, 13841, 13198, 32, 9874, 81, 19245, 1178, 334, 523, 2192, 13157, 1517, 610, 313, 266, 81, 6654, 20, 556, 638, 1517, 610, 313, 9671, 20, 556, 638, 1517, 610, 313, 28111, 20, 556, 638, 1517, 610, 313, 21110, 20, 556, 638, 1517, 610, 313, 22115, 657, 203, 79, 523, 3104, 25, 3941, 19245, 81, 1260, 47988, 203, 2], "prompt_token_count": 170, "reference_codepoints": 128, "repo": "steipete/agent-scripts", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [3361, 610, 33095, 1473, 4565, 4034, 668, 5984, 4034, 1160, 4565, 4034, 878, 31, 20711, 31, 37, 31, 4884, 5984, 4034, 605, 4565, 428, 34, 32, 35, 79], "continuation_token_count": 28, "decoded": " body == \"{\\\"object\\\": \\\"list\\\", \\\"model\\\": \\\"text-embedding-3-small\\\", \\\"data\\\": [0.1]", "decoded_codepoints": 87, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:crates/rig-core/src/providers/openai/embedding.rs", "example_id": "0002559e9788436ed8dfd2561114618e64ed35d88ea83dc24b69edea94efd35e", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 85, 81, 1676, 3044, 81, 20711, 81, 1986, 81, 13966, 81, 8795, 346, 301, 291, 1207, 3361, 280, 540, 21, 9588, 324, 313, 1473, 563, 313, 668, 392, 324, 313, 1160, 563, 313, 878, 31, 20711, 31, 37, 31, 4884, 392, 324, 313, 605, 563, 7316, 313, 1473, 563, 313, 20711, 392, 313, 1055, 563, 225, 34, 30, 313, 20711, 563, 428, 34, 32, 35, 79, 16752, 291, 36509, 21, 45, 584, 1201, 3, 3612, 40299, 45, 291, 1207, 1913, 81, 1580, 280, 324, 9803, 299, 15132, 403, 1793, 81, 731, 81, 1986, 26, 525, 403, 8693, 403, 28442, 1345, 30, 3361, 293, 291, 1207, 2043, 280, 2252, 31016, 1486, 403, 4164, 346, 324, 638, 1237, 81, 678, 440, 858, 31, 678, 657, 324, 638, 525, 81, 1580, 26, 525, 81, 1580, 27, 324, 638, 700, 2], "prompt_token_count": 138, "reference_codepoints": 256, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [44, 5997, 32, 314, 30, 528, 11875, 44, 892, 26, 5766, 32, 4338, 471, 528], "continuation_token_count": 15, "decoded": ": note.id,\n views: String(note.views),\n ", "decoded_codepoints": 77, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/xiaohongshu/creator-notes-summary.js", "example_id": "0002577f08991d2d1a4b3d4650df77e3401e893a4f331e2b48d802478eacdff6", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 432, 10173, 32, 9150, 1157, 301, 324, 415, 308, 1055, 848, 225, 34, 27, 301, 400, 2014, 1938, 32, 1684, 1371, 1133, 44, 225, 35, 474, 4175, 32, 3855, 346, 319, 225, 36, 1122, 324, 320, 324, 415, 1429, 5766, 32, 314, 27, 301, 400, 3276, 32, 2018, 1371, 528, 11263, 44, 1650, 474, 225, 35, 30, 528, 804, 44, 5997, 3, 14554, 81, 269, 44, 5997, 32, 770, 30, 528, 11875, 44, 892, 26, 5766, 32, 4338, 471, 528, 39869, 44, 892, 26, 5766, 32, 30242, 471, 528, 7901, 101, 44, 892, 26, 5766, 32, 6174, 101, 471, 528, 8446, 44, 892, 26, 5766, 32, 8680, 471, 528, 30132, 44, 2550, 2], "prompt_token_count": 114, "reference_codepoints": 64, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [26, 1260, 32, 1819, 3839, 32, 4699, 547, 7285, 2009, 3140, 9903, 1215, 1989, 397, 1424], "continuation_token_count": 16, "decoded": "(json.contextFiles.apply).toEqual([expectedApplyPath]);\n expect", "decoded_codepoints": 68, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/commands/artifact-workflow.test.ts", "example_id": "00025b780723224a11fb7f18b1cdb3b00153e0be83cdf5caecba786b4827adcb", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 83, 558, 547, 5492, 463, 2285, 31, 36418, 895, 397, 1424, 26, 1260, 32, 1293, 547, 5492, 463, 2584, 895, 397, 1424, 26, 1260, 32, 1819, 3839, 547, 38601, 473, 397, 1424, 26, 5139, 2361, 32, 1819, 3839, 547, 5492, 463, 1473, 895, 397, 1424, 26, 1260, 32, 1819, 3839, 32, 25520, 547, 7285, 2009, 3140, 23962, 1215, 1989, 397, 1424, 3, 264, 561, 463, 49115, 3982, 31, 6443, 12460, 21419, 45631, 3733, 2287, 461, 4871, 370, 2498, 1404, 532, 301, 397, 660, 5365, 2976, 280, 1519, 32, 2524, 26, 1433, 2976, 30, 330, 11593, 897, 370, 330, 14331, 370, 330, 13285, 31, 858, 895, 397, 660, 12877, 2976, 280, 1519, 32, 2524, 26, 3968, 2976, 30, 330, 8881, 895, 397, 2014, 5980, 32, 95, 2], "prompt_token_count": 127, "reference_codepoints": 64, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [32, 2524, 26, 2868, 30, 5608, 85, 453, 37076, 32, 1260, 4646, 334, 2164, 32, 31015, 26, 2868, 293, 334, 1201, 32, 20308, 26, 13737, 2101, 1026, 330, 16432, 895, 203, 1916, 203, 203, 858, 463, 19659, 638, 85, 453, 37076, 32, 1260], "continuation_token_count": 43, "decoded": ".join(tmp, '.caveman.json'));\n process.chdir(tmp);\n assert.strictEqual(getDefaultMode(), 'lite');\n});\n\ntest('reads .caveman.json", "decoded_codepoints": 130, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:tests/test_repo_local_config.js", "example_id": "000265c9533ba90be0390f91e2667dea1c5dcb61d656442a805ea02786f4f675", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1359, 12066, 3312, 78, 96, 895, 203, 203, 858, 463, 3255, 313, 2620, 20, 1412, 1289, 4533, 30, 1289, 5867, 1359, 30, 1289, 1256, 1359, 370, 308, 2868, 27, 532, 301, 334, 2164, 32, 31015, 26, 2868, 293, 334, 1201, 32, 20308, 26, 13737, 2101, 1026, 330, 2620, 895, 203, 1916, 203, 203, 858, 463, 19659, 638, 85, 453, 37076, 33, 1163, 32, 1260, 328, 24390, 370, 308, 2868, 27, 532, 301, 334, 5980, 32, 10174, 4764, 26, 983, 3, 18284, 334, 2164, 32, 31015, 26, 2868, 293, 334, 1201, 32, 20308, 26, 13737, 2101, 1026, 330, 16432, 895, 203, 1916, 203, 203, 858, 463, 19659, 638, 85, 453, 37076, 32, 1260, 328, 24390, 370, 308, 2868, 27, 532, 301, 334, 5980, 32, 42398, 26, 983, 32, 2524, 26, 2868, 30, 5608, 85, 453, 37076, 32, 1260, 1425, 284, 3398, 32, 8136, 1371, 1244, 2101, 44, 330, 338, 2692, 25, 10536, 334, 2164, 32, 31015, 26, 2868, 293, 334, 1201, 32, 2], "prompt_token_count": 163, "reference_codepoints": 128, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [784, 1114, 7128, 81, 2184, 32, 1877, 26, 528, 301, 715, 313, 21823, 563, 1359, 32, 21823, 81, 983, 30, 715], "continuation_token_count": 21, "decoded": "self._browser_options.update(\n {\n \"executable\": config.executable_path,\n ", "decoded_codepoints": 137, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/_browsers/_base.py", "example_id": "00026bb30e9138495c507af885bb0d5187f4ea4e2c4618985e3659e41221dbd9", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 264, 301, 528, 313, 1132, 563, 5736, 30, 528, 313, 48097, 563, 1359, 32, 48097, 30, 528, 313, 3237, 563, 313, 11226, 20, 415, 1359, 32, 4543, 81, 11226, 813, 313, 27275, 392, 400, 320, 324, 829, 324, 415, 1359, 32, 21823, 81, 983, 44, 353, 3, 225, 813, 44, 324, 630, 1114, 7128, 81, 2184, 280, 2149, 584, 415, 1359, 32, 12187, 81, 1132, 44, 324, 630, 1114, 1819, 81, 2184, 32, 1877, 26, 1163, 32, 12187, 81, 1132, 27, 446, 665, 617, 1832, 81, 1819, 81, 1793, 81, 5866, 26, 784, 30, 7664, 44, 5648, 77, 5392, 620, 79, 280, 1665, 27, 967, 14580, 77, 466, 30, 6204, 2786, 291, 1524, 334, 2], "prompt_token_count": 116, "reference_codepoints": 128, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [1206, 920, 334, 415, 308, 2157, 32, 2912, 32, 297, 81, 6319, 27, 442, 330, 1206, 920, 334, 415, 308, 2157, 32, 2912], "continuation_token_count": 23, "decoded": "not';\n if (store.git.is_repository) return 'not';\n if (store.git", "decoded_codepoints": 66, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/commands/store.ts", "example_id": "000279d5423b5ce42cf086804cbda2830af7c6abe93c500c3b4d2782ad479a64", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 87, 32, 4519, 32, 2689, 1720, 744, 27, 442, 330, 6876, 920, 334, 442, 330, 5790, 920, 203, 111, 203, 203, 1126, 2179, 34158, 7546, 21390, 26, 2157, 44, 8809, 34158, 2301, 710, 26231, 8150, 2171, 10794, 802, 301, 334, 415, 308, 2157, 32, 2912, 32, 297, 81, 6319, 1720, 744, 27, 442, 330, 6876, 920, 334, 415, 1429, 2157, 32, 2912, 32, 297, 81, 6319, 27, 442, 330, 1206, 225, 3, 1347, 44, 802, 711, 802, 532, 284, 786, 1720, 744, 1018, 330, 6876, 25, 499, 786, 1018, 9155, 499, 1289, 45, 719, 442, 529, 6319, 14098, 308, 18908, 44, 2283, 11711, 26, 2157, 32, 2912, 32, 2040, 81, 18908, 30, 330, 7134, 370, 330, 4108, 683, 835, 707, 42182, 3404, 44, 2283, 11711, 26, 2157, 32, 2912, 32, 2040, 81, 311, 42182, 81, 12764, 30, 330, 7134, 370, 330, 1347, 683, 835, 6562, 44, 2283, 11711, 26, 101, 2], "prompt_token_count": 152, "reference_codepoints": 64, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [284, 17735, 37, 81, 28598, 26, 6404, 293, 284, 17735, 37, 81, 28598, 26, 6404, 293, 284, 17735, 37, 81, 28598, 26, 6404, 293, 284, 17735, 37, 81, 28598, 26, 6404, 293, 284, 17735, 37, 81, 28598], "continuation_token_count": 37, "decoded": "\n sqlite3_finalize(stmt);\n sqlite3_finalize(stmt);\n sqlite3_finalize(stmt);\n sqlite3_finalize(stmt);\n sqlite3_finalize", "decoded_codepoints": 133, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:sqlite-vec-rescore.c", "example_id": "00027f91b8983c7f5ddc8b9d0e23d0e62d8cd23c3bd02b9c9606b03fbdf5edfd", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2950, 27, 301, 397, 17735, 37, 81, 28598, 26, 6404, 293, 397, 442, 7631, 45, 284, 320, 284, 17735, 37, 81, 2539, 81, 410, 40, 38, 26, 6404, 30, 225, 35, 30, 7311, 81, 643, 314, 293, 284, 17735, 37, 81, 2539, 81, 410, 40, 38, 26, 6404, 30, 225, 36, 30, 7311, 81, 643, 314, 293, 284, 17735, 37, 81, 2539, 81, 4501, 906, 1145, 40, 38, 26, 6404, 30, 225, 37, 30, 11589, 81, 891, 293, 284, 7631, 280, 17735, 37, 81, 2997, 26, 6404, 293, 284, 17735, 37, 81, 28598, 26, 6404, 293, 3, 1281, 16623, 203, 306, 24300, 1649, 203, 306, 43278, 203, 203, 1574, 763, 736, 1262, 81, 9768, 518, 81, 1808, 81, 452, 81, 2400, 26, 913, 1897, 319, 1617, 30, 1727, 42, 81, 102, 319, 6298, 30, 10631, 1334, 81, 102, 13135, 27, 225, 2], "prompt_token_count": 143, "reference_codepoints": 128, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [398, 1204, 2526, 334, 398, 1204, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526, 334, 398, 1204, 2526], "continuation_token_count": 86, "decoded": " $linkJson\n $link\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson\n $linkJson", "decoded_codepoints": 258, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/mido.sh", "example_id": "00028400d9b6e80ade81a5528bcea5905209bc1f5a1a69f7f860f07a232d0c60", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 899, 863, 225, 34, 11975, 1615, 284, 1048, 313, 4499, 2145, 25863, 1770, 1289, 5822, 2552, 372, 2992, 1326, 436, 600, 24305, 5822, 11555, 284, 3099, 313, 1397, 44, 398, 1204, 2526, 20, 284, 442, 225, 35, 334, 8058, 719, 488, 779, 65, 81, 2413, 12672, 1204, 20, 334, 442, 225, 34, 203, 111, 203, 203, 4984, 2839, 14066, 346, 301, 719, 2196, 804, 12672, 35, 20, 334, 2196, 7275, 12672, 36, 20, 334, 3, 827, 347, 12487, 20, 397, 8888, 4303, 347, 5910, 31, 35, 35, 31, 12487, 31, 19276, 31, 2159, 545, 31, 6569, 20, 10368, 284, 313, 4463, 35, 35, 1667, 20753, 4781, 11915, 19276, 31, 2159, 545, 31, 6569, 20, 829, 397, 827, 347, 2159, 545, 20, 397, 8888, 4303, 347, 5910, 31, 35, 35, 31, 19276, 20, 10368, 284, 313, 4463, 36, 34, 36, 39, 31, 6569, 20, 829, 397, 827, 347, 1786, 20, 397, 8888, 4303, 347, 5910, 31, 1786, 31, 36, 34, 36, 39, 20, 10368, 284, 313, 2], "prompt_token_count": 167, "reference_codepoints": 256, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [3997, 31, 22189, 523, 313, 3997, 31, 22189, 523, 313, 3997, 31, 22189, 523, 313, 3997, 31, 22189, 523, 313, 3997, 31, 22189, 523, 313, 3997, 31, 22189, 523, 313, 3997, 31, 22189, 523, 313, 3997], "continuation_token_count": 36, "decoded": "nn-*\" | \"nn-*\" | \"nn-*\" | \"nn-*\" | \"nn-*\" | \"nn-*\" | \"nn-*\" | \"nn", "decoded_codepoints": 65, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/define.sh", "example_id": "000285ff92eb64fc2da9c0c2ee898be339357a76b1de3a8fe73bb3dece0e3e62", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 89, 347, 62, 450, 10461, 2531, 20, 397, 27668, 347, 2159, 31, 11704, 20, 10368, 284, 313, 6973, 20, 523, 313, 6973, 22258, 28, 523, 313, 4474, 104, 2531, 20, 523, 313, 4474, 4788, 18534, 20, 829, 397, 3813, 3941, 1131, 20, 610, 313, 4474, 104, 2531, 20, 1276, 3941, 1131, 20, 610, 313, 4474, 4788, 18534, 20, 20503, 962, 804, 347, 6973, 20, 397, 4504, 347, 6973, 20, 397, 7275, 347, 9062, 104, 2531, 20, 397, 27668, 347, 6973, 31, 20698, 20, 10368, 284, 313, 1490, 20, 523, 313, 1490, 22258, 28, 523, 313, 3997, 20, 523, 313, 3997, 22258, 28, 523, 313, 3, 1276, 3941, 1131, 20, 610, 313, 1347, 20, 1276, 3941, 1131, 20, 610, 313, 19573, 1376, 89, 2531, 20, 1276, 3941, 1131, 20, 610, 313, 96, 1734, 93, 20, 20503, 962, 804, 347, 3997, 20, 397, 4504, 347, 1347, 20, 397, 7275, 347, 31486, 1376, 89, 2531, 20, 397, 27668, 347, 1490, 31, 2576, 20, 10368, 284, 313, 8378, 20, 523, 313, 8378, 22258, 28, 523, 313, 25256, 380, 20, 523, 313, 9828, 265, 25746, 20, 829, 397, 3813, 3941, 1131, 20, 610, 313, 25256, 380, 20, 1276, 3941, 1131, 20, 610, 313, 9828, 265, 25746, 20, 20503, 549, 2], "prompt_token_count": 206, "reference_codepoints": 64, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [563, 2933, 835, 324, 2505, 284, 829, 284, 665, 894, 81, 371, 81, 21326, 81, 1793, 81, 2988, 81, 5078, 26, 784, 30, 10306, 711, 291, 1524, 291, 2108, 688, 21032, 884, 4717, 623, 3115, 4826, 291, 1524, 291, 1789, 280, 630, 32, 1580, 32, 371, 26, 324, 10156, 440, 1237, 44, 21326, 2113, 324], "continuation_token_count": 55, "decoded": "\": True},\n ],\n )\n def test_get_cookies_with_custom_headers(self, kwargs):\n \"\"\"\n Test that cookies are returned with custom headers\n \"\"\"\n response = self.client.get(\n reverse(\"api:cookies\"),\n ", "decoded_codepoints": 257, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/fetchers/async/test_stealth.py", "example_id": "00029a401b2efaa1aeea87c17d021e4edeae5a46e34f771d12cd3be684fdd9dc", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 96, 518, 47, 1815, 27, 291, 6804, 1517, 610, 225, 36, 34, 34, 446, 477, 12408, 32, 1826, 32, 28913, 26, 291, 313, 5321, 392, 291, 428, 324, 3447, 1521, 81, 43425, 563, 2933, 30, 313, 4568, 81, 40050, 563, 2933, 835, 324, 3447, 1521, 81, 43425, 563, 3177, 30, 313, 4568, 81, 40050, 563, 2933, 835, 324, 3447, 1521, 81, 43425, 563, 2933, 30, 313, 4568, 81, 40050, 3, 225, 35, 34, 30, 400, 313, 21326, 563, 28254, 426, 563, 313, 858, 392, 313, 853, 563, 313, 35, 36, 37, 392, 313, 4116, 563, 313, 2763, 32, 508, 392, 313, 983, 563, 2430, 10828, 400, 313, 2175, 81, 1903, 563, 2933, 30, 400, 313, 7615, 81, 5078, 563, 3447, 395, 97, 563, 49051, 400, 313, 9003, 81, 1163, 563, 3447, 10504, 81, 8680, 563, 3177, 30, 313, 10504, 2], "prompt_token_count": 141, "reference_codepoints": 256, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [313, 878, 20, 577, 202, 835, 577, 202, 109, 1379, 202, 20, 4846, 20816, 332, 5516, 563, 4320, 1379, 202, 20, 3864, 563, 296, 3528, 30, 1379, 202, 20, 314, 563, 313, 878, 37, 36, 34, 42, 36, 35, 34, 36, 39, 40, 392, 1379, 202, 20, 1449, 563, 225, 35, 36, 30, 1379], "continuation_token_count": 54, "decoded": " \"text\"\n\t\t\t\t\t},\n\t\t\t\t\t{\n\t\t\t\t\t\t\"autogeneratePattern\": \"\",\n\t\t\t\t\t\t\"hidden\": fals,\n\t\t\t\t\t\t\"id\": \"text3208210256\",\n\t\t\t\t\t\t\"max\": 12,\n\t\t\t\t\t", "decoded_codepoints": 130, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/migrations/0_collections_snapshot_0_19_0_dev_1.go", "example_id": "00029b4edc6d2f7c9559dfe1a27124471b85c1f256d33d7ba30fcdf3eb112d5e", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 40, 6553, 1379, 202, 20, 3864, 563, 901, 30, 1379, 202, 20, 314, 563, 313, 878, 37, 36, 34, 42, 36, 35, 34, 36, 39, 40, 392, 1379, 202, 20, 1449, 563, 225, 35, 36, 30, 1379, 202, 20, 887, 563, 225, 40, 30, 1379, 202, 20, 426, 563, 313, 314, 392, 1379, 202, 20, 5607, 563, 9044, 77, 83, 31, 88, 34, 31, 43, 6155, 30145, 1379, 202, 20, 2689, 444, 563, 901, 30, 1379, 202, 20, 36712, 563, 861, 30, 1379, 202, 20, 3648, 563, 861, 30, 1379, 202, 20, 2946, 563, 861, 30, 1379, 202, 20, 681, 563, 3, 12610, 37, 37, 41, 41, 36, 41, 35, 35, 41, 43, 392, 1379, 202, 20, 1449, 1908, 563, 225, 35, 30, 1379, 202, 20, 887, 1908, 563, 225, 34, 30, 1379, 202, 20, 426, 563, 313, 2946, 392, 1379, 202, 20, 2689, 444, 563, 901, 30, 1379, 202, 20, 3648, 563, 901, 30, 1379, 202, 20, 2946, 563, 901, 30, 1379, 202, 20, 681, 563, 313, 12610, 20, 603, 202, 835, 603, 202, 109, 1379, 202, 20, 4846, 20816, 332, 5516, 563, 4320, 1379, 202, 20, 3864, 563, 296, 3528, 2], "prompt_token_count": 194, "reference_codepoints": 128, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [101, 312, 529, 1347, 81, 1530, 82, 4253, 32, 203, 203, 46, 3958, 48], "continuation_token_count": 14, "decoded": "s a `no_std` library.\n\n
", "decoded_codepoints": 32, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:engineering-book/src/ch09-no-std-and-feature-verification.md", "example_id": "00029ec8b3ba13e3bddfd7eeadb976c4ccc3dab38b031c1bc737e002fffbbe63", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 5905, 474, 2504, 44265, 44, 203, 19464, 16445, 1505, 769, 5520, 31, 3274, 769, 10899, 203, 19464, 1505, 769, 10899, 769, 464, 31, 5905, 203, 19464, 1505, 769, 10899, 769, 1347, 31, 1536, 31, 5905, 203, 914, 203, 377, 3958, 48, 203, 203, 765, 43006, 131, 35507, 225, 36, 44, 5238, 312, 529, 1347, 81, 1530, 82, 13392, 203, 203, 1922, 312, 4253, 8628, 688, 47820, 3, 6656, 4138, 31, 21511, 16911, 3112, 32, 12072, 561, 47820, 436, 529, 7381, 104, 41, 405, 31, 4108, 31, 39903, 10006, 88, 82, 308, 14024, 390, 27764, 31, 63, 547, 203, 203, 46, 3958, 48, 203, 46, 1367, 48, 13628, 377, 1367, 48, 203, 203, 914, 7421, 203, 306, 5034, 32, 3666, 203, 44291, 1347, 81, 1530, 79, 203, 203, 2862, 1671, 32894, 2013, 46, 913, 489, 44, 12622, 48, 301, 284, 706, 44, 428, 103, 42, 45, 489, 614, 284, 5759, 44, 12622, 30, 284, 2069, 44, 1770, 2], "prompt_token_count": 158, "reference_codepoints": 32, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [308, 11810, 4117, 27, 308, 53, 27, 563, 313, 40, 36, 32, 34, 392, 577], "continuation_token_count": 15, "decoded": " (Sensor memory) (C)\": \"62.0\",\n\t\t\t\t", "decoded_codepoints": 35, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/gpu_test.go", "example_id": "0002a041d079f54f9784dd585e4a62de6960a36adbaa6c6647d32784a5bd8328", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 10027, 27, 563, 313, 34, 392, 577, 202, 20, 9268, 2210, 9325, 11348, 308, 52, 27, 563, 313, 39, 37, 40, 42, 41, 34, 43, 35, 36, 392, 577, 202, 20, 9268, 2210, 9325, 12781, 11348, 308, 52, 27, 563, 313, 38, 42, 36, 36, 40, 37, 34, 38, 34, 392, 577, 202, 20, 3588, 20886, 563, 313, 2781, 10506, 102, 428, 68, 1525, 267, 225, 40, 42, 34, 63, 12032, 603, 202, 835, 603, 202, 20, 2294, 35, 563, 301, 577, 202, 20, 11989, 563, 313, 37, 42, 36, 43, 38, 392, 577, 202, 20, 19412, 308, 11810, 6731, 27, 308, 53, 27, 563, 313, 38, 43, 32, 34, 392, 577, 202, 20, 19412, 3, 577, 202, 20, 19412, 308, 11810, 4117, 27, 308, 53, 27, 563, 313, 40, 36, 32, 34, 392, 577, 202, 20, 15685, 16065, 9707, 8554, 308, 73, 27, 563, 313, 35, 43, 32, 34, 392, 577, 202, 20, 14871, 793, 10027, 27, 563, 313, 36, 34, 32, 37, 392, 577, 202, 20, 9268, 2210, 9325, 11348, 308, 52, 27, 563, 313, 36, 39, 41, 39, 37, 34, 36, 40, 39, 40, 34, 392, 577, 202, 20, 9268, 2210, 9325, 12781, 11348, 308, 52, 27, 563, 313, 41, 43, 38, 37, 38, 35, 37, 41, 40, 392, 577, 202, 20, 3588, 20886, 563, 313, 6646, 91, 225, 37, 35, 428, 68, 1525, 97, 2], "prompt_token_count": 230, "reference_codepoints": 32, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [313, 495, 5488, 20, 20503, 962, 804, 347, 290, 20, 397, 4504, 347, 290, 20, 397, 7275, 347, 68, 14235, 2531, 20, 397, 27668, 347, 290, 31, 1013, 20, 10368, 284, 313, 2947, 20, 523, 313, 2947, 22258, 28, 523, 313, 100, 12574, 20, 523, 313, 100, 12574, 20, 829, 397, 3813, 3941, 1131, 20, 610, 313, 100, 12574, 20, 1276, 3941, 1131, 20, 610, 313, 100, 12574, 20, 20503, 962, 804, 347, 2947, 20, 397, 4504, 347, 2947, 20, 397, 7275, 347, 68, 12574, 20, 397, 27668, 347, 2947], "continuation_token_count": 90, "decoded": " \"romana\" ]] && id=\"ro\"\n short=\"ro\"\n lang=\"Romanian\"\n culture=\"ro-RO\" ;;\n \"ru\" | \"ru-\"* | \"russian\" | \"russian\" )\n [[ \"$input\" == \"russian\" || \"$input\" == \"russian\" ]] && id=\"ru\"\n short=\"ru\"\n lang=\"Russian\"\n culture=\"ru", "decoded_codepoints": 257, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/define.sh", "example_id": "0002a9a9cc67791a71e29114fde80d3d10bffb1842783627c24209fa7b503ef3", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 87, 20, 397, 5585, 347, 3437, 888, 340, 277, 20, 397, 27668, 347, 385, 31, 4758, 20, 10368, 284, 313, 385, 22258, 28, 829, 397, 4504, 347, 593, 20, 397, 7275, 347, 3437, 888, 340, 277, 20, 397, 27668, 347, 385, 31, 4758, 20, 10368, 284, 313, 290, 20, 523, 313, 290, 22258, 28, 523, 313, 48090, 2531, 20, 523, 313, 495, 36631, 17468, 20, 523, 313, 495, 5488, 20, 829, 397, 3813, 3941, 1131, 20, 610, 313, 48090, 2531, 20, 1276, 3941, 1131, 20, 610, 313, 495, 36631, 17468, 20, 1276, 3941, 1131, 20, 610, 3, 20, 10368, 284, 313, 1990, 20, 523, 313, 1990, 22258, 28, 523, 313, 101, 23717, 774, 20, 523, 313, 101, 23717, 1229, 93, 8047, 20, 523, 313, 101, 23717, 1229, 7643, 20, 829, 397, 3813, 3941, 1131, 20, 610, 313, 101, 23717, 774, 20, 1276, 3941, 1131, 20, 610, 313, 101, 23717, 1229, 93, 8047, 20, 1276, 3941, 1131, 20, 610, 313, 101, 23717, 1229, 7643, 20, 20503, 962, 804, 347, 1990, 20, 397, 4504, 347, 1990, 20, 397, 7275, 347, 69, 23717, 774, 20, 397, 27668, 347, 1990, 31, 9718, 20, 10368, 284, 313, 2003, 20, 523, 313, 2003, 22258, 28, 523, 313, 3434, 20, 523, 313, 3434, 22258, 2], "prompt_token_count": 209, "reference_codepoints": 256, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [330, 2342, 2976, 920, 397, 660, 1374, 1215, 280, 1519, 32, 2524, 26, 16452, 2976, 30, 330, 2285, 32, 954, 895, 397, 2014, 5980, 32, 39052, 26, 2285, 1215, 30, 7715, 2710, 293, 1687, 660, 909, 280, 225, 35, 45, 397, 2014, 5980, 32, 39052, 26, 2285, 1215, 30, 909, 293, 1687, 660, 909, 280, 225, 36, 45, 397, 2014, 5980, 32, 39052, 26, 2285, 1215, 30, 909, 293, 1687, 660, 909], "continuation_token_count": 72, "decoded": " 'changeDir';\n const specPath = path.join(specsDir, 'spec.md');\n await fs.writeFile(specPath, deltaSpec);\n\n const val = 1;\n await fs.writeFile(specPath, val);\n\n const val = 2;\n await fs.writeFile(specPath, val);\n\n const val", "decoded_codepoints": 258, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/validation.test.ts", "example_id": "0002ab0a674ed62f6ca4f88d144c1144ee19be2a3797dc623cecf041f0f8c6ed", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 994, 32, 4275, 547, 5492, 26, 34, 293, 397, 1424, 26, 3734, 32, 4476, 32, 6060, 26, 91, 532, 595, 32, 1436, 32, 6411, 463, 5297, 1755, 2847, 547, 5492, 26, 1870, 293, 284, 1122, 446, 561, 463, 13822, 646, 2385, 13174, 4826, 6517, 296, 8984, 1340, 9058, 37706, 322, 2129, 13174, 2385, 370, 2498, 1404, 532, 301, 397, 660, 1539, 2976, 280, 3, 16944, 15386, 203, 1318, 2664, 10184, 2908, 312, 7715, 2280, 328, 2819, 1688, 32, 203, 203, 78, 28150, 28150, 82, 8523, 203, 765, 34394, 44, 5938, 13174, 203, 78, 28150, 28150, 82, 203, 7839, 1687, 660, 1374, 1215, 280, 1519, 32, 2524, 26, 16452, 2976, 30, 330, 2285, 32, 954, 895, 397, 2014, 5980, 32, 39052, 26, 2285, 1215, 30, 7715, 2710, 293, 1687, 660, 909, 2], "prompt_token_count": 132, "reference_codepoints": 256, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [30, 2287, 81, 10354, 30, 2287, 81, 687, 30, 2287, 81, 1436, 30, 2287, 81, 965, 30, 2287], "continuation_token_count": 18, "decoded": ", status_reason, status_code, status_message, status_url, status", "decoded_codepoints": 64, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/hub/heartbeat/heartbeat_test.go", "example_id": "0002ab773b7b8a02ee1fed4622fbb29fed0da6b042227ef2721379a53e317266", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 17423, 4882, 32, 1006, 4599, 27, 319, 1262, 32, 3157, 301, 203, 202, 102, 32, 2762, 346, 203, 202, 496, 30, 1137, 1025, 16456, 17423, 4882, 32, 1922, 1240, 26, 725, 32, 1290, 30, 313, 2300, 50, 2763, 32, 508, 392, 313, 2895, 35, 36, 37, 657, 203, 202, 1981, 32, 15109, 26, 102, 30, 1137, 27, 203, 202, 601, 1256, 203, 111, 203, 203, 1298, 1487, 1006, 1598, 26, 102, 319, 4266, 32, 70, 30, 1123, 319, 11397, 17423, 4882, 32, 1006, 4599, 30, 35336, 30, 636, 30, 3408, 30, 2287, 3, 1922, 3157, 26, 725, 32, 1290, 30, 313, 17579, 392, 1992, 77, 800, 79, 1813, 109, 357, 202, 20, 426, 563, 261, 636, 30, 357, 202, 20, 2035, 563, 261, 3408, 30, 357, 202, 20, 625, 563, 261, 313, 38, 39, 42, 41, 40, 392, 357, 202, 20, 3707, 563, 225, 1605, 800, 109, 28385, 835, 357, 202, 20, 1517, 563, 2287, 30, 203, 202, 1748, 203, 202, 1981, 32, 15109, 26, 102, 30, 1137, 27, 203, 202, 601, 2664, 203, 111, 203, 203, 1298, 1487, 38568, 8098, 26, 102, 319, 4266, 32, 70, 30, 1123, 319, 11397, 17423, 519, 2], "prompt_token_count": 195, "reference_codepoints": 64, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [27, 446, 477, 12408, 32, 1826, 32, 28913, 26], "continuation_token_count": 9, "decoded": ")\n\n @pytest.mark.parametrize(", "decoded_codepoints": 32, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_cu_converter.py", "example_id": "0002ae5a83aac0520fef26ed8a793ecfb7fd1f9725e75bebef7de71c30219fb0", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 261, 4939, 1260, 392, 324, 4939, 3969, 392, 324, 4939, 929, 356, 392, 324, 4939, 978, 392, 324, 4939, 3666, 392, 291, 2505, 284, 829, 284, 665, 894, 81, 11592, 101, 81, 34019, 81, 9081, 26, 784, 30, 1447, 711, 291, 11492, 280, 617, 2682, 81, 13956, 346, 291, 1201, 646, 11492, 32, 7494, 101, 26, 716, 32, 3644, 2338, 26, 84, 1010, 471, 7537, 1120, 3, 2657, 203, 21, 19201, 346, 3312, 12011, 28124, 31, 7873, 203, 21, 40595, 478, 203, 823, 2108, 7071, 101, 21304, 44, 284, 1524, 1006, 19201, 346, 436, 28124, 827, 9215, 7103, 446, 477, 978, 2], "prompt_token_count": 103, "reference_codepoints": 32, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [202, 835, 355, 202, 109, 603, 202, 20, 26640, 3410, 563, 861], "continuation_token_count": 12, "decoded": "\t},\n\t\t\t{\n\t\t\t\t\"cascadeDelete\": true", "decoded_codepoints": 34, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/migrations/0_collections_snapshot_0_19_0_dev_1.go", "example_id": "0002aed310a0bd79bc59d0dccd1e97bcd3fafe7ee71f6474ced3b7a2165124d6", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 77, 83, 31, 108, 34, 31, 43, 6155, 30145, 603, 202, 20, 2689, 444, 563, 901, 30, 603, 202, 20, 36712, 563, 861, 30, 603, 202, 20, 3648, 563, 861, 30, 603, 202, 20, 2946, 563, 861, 30, 603, 202, 20, 681, 563, 313, 878, 20, 355, 202, 835, 355, 202, 109, 603, 202, 20, 26640, 3410, 563, 861, 30, 603, 202, 20, 4170, 606, 563, 7286, 4365, 81, 3707, 81, 2393, 31084, 603, 202, 20, 3864, 563, 901, 30, 603, 202, 20, 314, 563, 313, 12610, 36, 37, 41, 39, 36, 41, 40, 35, 34, 39, 392, 355, 3, 563, 225, 34, 30, 603, 202, 20, 426, 563, 313, 496, 392, 603, 202, 20, 2689, 444, 563, 901, 30, 603, 202, 20, 3648, 563, 901, 30, 603, 202, 20, 2946, 563, 901, 30, 603, 202, 20, 681, 563, 313, 12610, 20, 355, 202, 835, 355, 202, 109, 603, 202, 20, 26640, 3410, 563, 861, 30, 603, 202, 20, 4170, 606, 563, 313, 36, 19080, 39, 96, 573, 42, 102, 425, 93, 39, 8462, 392, 603, 202, 20, 3864, 563, 901, 30, 603, 202, 20, 314, 563, 313, 12610, 37, 37, 41, 41, 36, 41, 35, 35, 41, 43, 392, 603, 202, 20, 934, 2], "prompt_token_count": 206, "reference_codepoints": 32, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [280, 17675, 291, 630, 32, 14806, 81, 1338, 280, 13489, 81, 1338, 446, 665, 1156, 466, 3207, 784, 711, 291, 442, 296, 20, 5288, 11741, 11549, 436, 301, 784, 32, 13956, 111, 3491, 96, 109, 784, 32, 14806, 81, 1338, 3845, 478, 203, 823, 35102, 5288, 26, 984, 711, 284, 1524, 284, 23148, 312, 11741, 3803, 32, 284, 1524, 446, 665, 1156, 1664], "continuation_token_count": 63, "decoded": " = converter\n self.exc_info = exc_info\n\n def __str__(self):\n return f\"Failed conversion attempt for {self.converter}:\\n{self.exc_info}\"\n\n\nclass ConversionFailed(Exception):\n \"\"\"\n Represents a conversion failed.\n \"\"\"\n\n def __init", "decoded_codepoints": 257, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/_exceptions.py", "example_id": "0002d098598f02343a237ffc493c47d122e75ef19e532cd947c8b76cab53fd28", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 265, 1597, 2431, 436, 322, 2702, 803, 32, 284, 1524, 446, 3097, 478, 203, 823, 12228, 14350, 23922, 26, 1473, 711, 284, 1524, 284, 23148, 312, 3982, 11549, 372, 4483, 312, 803, 32, 284, 1524, 446, 665, 1156, 1664, 3207, 784, 30, 17675, 44, 6204, 30, 13489, 81, 1338, 44, 5648, 77, 7288, 79, 280, 1665, 711, 291, 630, 32, 13956, 3, 225, 1474, 44, 5648, 77, 466, 79, 280, 1665, 30, 291, 20130, 44, 5648, 77, 720, 77, 5288, 14350, 23922, 3212, 280, 1665, 30, 284, 8063, 291, 630, 32, 36456, 280, 20130, 584, 415, 1474, 438, 1665, 44, 324, 415, 20130, 438, 1665, 44, 400, 1474, 280, 313, 974, 11741, 3803, 3107, 284, 2], "prompt_token_count": 117, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [280, 636, 32, 800, 45, 2855, 415, 308, 5665, 81, 426, 81, 1753, 610, 225, 34, 27, 301, 715, 5799, 81, 426, 280, 636, 32, 800, 45, 2855], "continuation_token_count": 28, "decoded": " = name.string;\n if (unique_name_ptr == 0) {\n unique_name = name.string;\n ", "decoded_codepoints": 138, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/pdb/pdb_parse.c", "example_id": "0002d536a826a8e1f3ffc3424bb8ade09842d9886aa2b877cbd0754971712e11", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 647, 434, 5799, 636, 528, 415, 308, 6055, 81, 5665, 81, 426, 1511, 2855, 415, 308, 487, 81, 1167, 396, 2962, 549, 18066, 81, 620, 6567, 81, 3993, 10189, 558, 27, 301, 715, 632, 42, 319, 5665, 81, 426, 81, 1753, 280, 636, 81, 1753, 474, 636, 32, 891, 474, 225, 35, 45, 715, 892, 42, 5799, 81, 426, 3, 6019, 320, 528, 320, 528, 813, 109, 2855, 20037, 81, 426, 280, 636, 45, 528, 320, 1750, 320, 400, 320, 1090, 320, 2969, 45, 47225, 1135, 18066, 81, 17203, 4663, 81, 7420, 36, 44, 1568, 2], "prompt_token_count": 97, "reference_codepoints": 128, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [262, 313, 2912, 1359, 769, 16811, 31, 464, 769, 2946, 5296, 32, 12329, 1215, 2296, 31182, 1026, 324, 313, 2912, 1359, 769, 16811, 31, 464, 769, 2946, 5296, 32, 12329, 1215, 2296, 31182, 1026, 324, 313, 2912, 1359, 769, 16811, 31, 464, 769, 2946, 5296, 32, 12329, 1215, 2296, 31182, 1026, 324, 313, 2912, 1359, 769, 16811, 31, 464, 769, 2946, 5296, 32, 12329, 1215], "continuation_token_count": 65, "decoded": " \"git config --unset-all --system core.hooksPath\".cyan(),\n \"git config --unset-all --system core.hooksPath\".cyan(),\n \"git config --unset-all --system core.hooksPath\".cyan(),\n \"git config --unset-all --system core.hooksPath", "decoded_codepoints": 259, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/install.rs", "example_id": "0002d5d6d3a6c7eb6159cb3e5a0d80fdbd41e2029cfcc9f6fe9a8b0a834eb0ef", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1468, 313, 225, 43240, 96, 392, 324, 2588, 324, 313, 5766, 1924, 32, 14970, 922, 8570, 1026, 324, 313, 12118, 1924, 32, 14970, 922, 8570, 1026, 324, 313, 2912, 1359, 769, 16811, 31, 464, 769, 3264, 5296, 32, 12329, 1215, 2296, 31182, 1026, 324, 313, 2912, 1359, 769, 16811, 31, 464, 769, 2946, 5296, 32, 12329, 1215, 2296, 31182, 1026, 291, 3, 81, 1515, 922, 6240, 49, 284, 1472, 446, 1207, 3738, 44, 7479, 46, 9824, 620, 48, 280, 415, 1169, 301, 291, 36337, 620, 403, 853, 81, 25582, 922, 452, 81, 3137, 346, 284, 320, 813, 301, 291, 622, 81, 7133, 81, 2516, 26, 7133, 81, 2516, 30, 2074, 32, 302, 81, 612, 1026, 1359, 32, 302, 81, 26601, 1157, 284, 1472, 446, 436, 11962, 81, 681, 328, 3738, 301, 291, 1207, 11962, 81, 983, 280, 11962, 2], "prompt_token_count": 140, "reference_codepoints": 256, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [660, 1351, 319, 1131, 280, 313, 15003, 1897, 77], "continuation_token_count": 9, "decoded": " const char *input = \"emb float[", "decoded_codepoints": 32, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:tests/test-unit.c", "example_id": "0002d7a65932c0fdc18ede08e8051ca69a5a60990ce4434e062e1dceda15b523", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 719, 434, 3081, 44, 5816, 6936, 334, 301, 284, 660, 1351, 319, 1131, 280, 313, 15003, 1897, 77, 35, 36, 42, 79, 18178, 1345, 9519, 1020, 26, 22412, 81, 9768, 2265, 47, 7003, 15542, 284, 7631, 280, 4712, 34, 81, 2208, 81, 2402, 81, 2592, 26, 1131, 30, 308, 410, 27, 15460, 26, 1131, 471, 549, 748, 293, 284, 1201, 26, 899, 610, 4428, 2345, 81, 2930, 293, 334, 320, 719, 434, 3081, 44, 8665, 8218, 334, 301, 284, 3, 35, 36, 42, 79, 18178, 1345, 6936, 420, 96, 1586, 26, 22412, 81, 9768, 2265, 47, 7003, 15542, 284, 7631, 280, 4712, 34, 81, 2208, 81, 2402, 81, 2592, 26, 1131, 30, 308, 410, 27, 15460, 26, 1131, 471, 549, 748, 293, 284, 1201, 26, 899, 610, 4428, 2345, 81, 2930, 293, 334, 320, 719, 434, 3081, 44, 8665, 2470, 1202, 334, 301, 284, 660, 1351, 319, 1131, 280, 313, 15003, 1897, 77, 35, 36, 42, 79, 18178, 1345, 6936, 9519, 1020, 26, 941, 1799, 713, 2], "prompt_token_count": 168, "reference_codepoints": 32, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [111, 203, 202, 102, 32, 2529, 440, 30788, 3872, 2838], "continuation_token_count": 10, "decoded": "}\n\tt.Run(\"registers direct child", "decoded_codepoints": 32, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/disk_test.go", "example_id": "0002d9ede84150bc978d27d1b9ab24a5dcb6aeaca5ed6ef5108512711e4a1fd4", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2312, 1215, 44, 264, 2430, 7615, 31, 18290, 101, 392, 603, 202, 10300, 12090, 26225, 44, 1992, 77, 800, 79, 10300, 32, 2338, 26225, 5944, 109, 577, 202, 20, 9692, 289, 34, 96, 35, 98, 35, 563, 301, 558, 44, 313, 9692, 289, 34, 96, 35, 98, 35, 3918, 577, 202, 20, 9692, 289, 35, 96, 35, 563, 261, 301, 558, 44, 313, 9692, 289, 35, 96, 35, 3918, 603, 202, 835, 355, 202, 835, 357, 202, 111, 203, 202, 111, 478, 202, 102, 32, 2529, 440, 30788, 3872, 2838, 432, 6717, 31, 18290, 101, 392, 3420, 26, 102, 319, 4266, 32, 70, 27, 301, 3, 26, 1110, 77, 800, 6603, 2946, 32, 15516, 5773, 4370, 357, 202, 86, 1025, 1930, 17323, 26, 4867, 27, 1314, 202, 86, 32, 669, 10728, 9113, 15516, 26, 10300, 32, 10728, 5944, 109, 355, 202, 3033, 44, 262, 2430, 1902, 33, 9692, 289, 34, 96, 35, 98, 35, 392, 355, 202, 8849, 311, 38839, 44, 2430, 7615, 31, 18290, 101, 33, 9692, 289, 34, 96, 35, 98, 35, 505, 85, 28491, 35, 31, 2388, 392, 357, 202, 1748, 1314, 202, 5136, 30, 5375, 1025, 7669, 32, 2548, 5773, 1365, 9692, 289, 34, 96, 35, 98, 35, 1446, 357, 202, 862, 2], "prompt_token_count": 208, "reference_codepoints": 32, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [261, 638, 1274, 606, 26, 10586, 1599, 606, 27, 324], "continuation_token_count": 10, "decoded": " .tableId(uniformTableId)\n ", "decoded_codepoints": 39, "document_id": "unitycatalog/unitycatalog@ed504deea31b30c3e7d27e360372077cce04a509:server/src/test/java/io/unitycatalog/server/utils/PopulateTestDatabase.java", "example_id": "0002df7ea6cf5b6da82660a53ff9025fdca2de197f5d451840dc4deb64bda0cc", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 86, 473, 284, 1015, 620, 1031, 2185, 2526, 1031, 26, 5507, 2137, 11938, 293, 446, 5548, 1120, 12913, 16483, 1599, 1120, 12913, 280, 291, 5548, 1120, 12913, 32, 4164, 346, 324, 638, 314, 26, 10586, 1599, 606, 27, 324, 638, 426, 26, 16820, 474, 7286, 10586, 657, 324, 638, 3968, 606, 26, 7595, 32, 33004, 26, 3968, 606, 490, 616, 3, 263, 638, 6057, 26, 720, 32, 1028, 26, 314, 2137, 11938, 30, 636, 2137, 11938, 30, 26729, 2137, 11938, 490, 324, 638, 19135, 2207, 26, 8615, 2207, 32, 36020, 32, 6682, 1157, 324, 638, 681, 26, 1599, 620, 32, 14417, 32, 6682, 1157, 324, 638, 26296, 26, 890, 2821, 1157, 324, 638, 40086, 26, 96, 2], "prompt_token_count": 118, "reference_codepoints": 32, "repo": "unitycatalog/unitycatalog", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [322, 2432, 2532, 619, 322, 3833, 2078, 203, 913, 390, 2253, 4546, 81, 6323, 81, 32474, 280, 313, 59, 4621, 1420, 322, 2016, 372, 2596, 328, 866, 203, 913, 390, 2253, 4546, 81, 635, 2730, 81, 927, 567, 280, 313, 17743], "continuation_token_count": 41, "decoded": " the same order as the enum values\nconst CHOICE_RUN_SETUP = \"I'll run the command to sign in\";\nconst CHOICE_STAY_ANON = \"Continue", "decoded_codepoints": 129, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/mcp/src/lib/auth/auth-prompt.ts", "example_id": "0002e8d3f888793e0cda4b0fc62842fbc3ff97cc2b602dac1e56eb49ecc73699", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 86, 19408, 10677, 1991, 1370, 488, 2955, 2043, 1359, 4414, 284, 313, 5125, 561, 44117, 30, 7378, 1615, 316, 31, 4898, 322, 7049, 41, 488, 2955, 2145, 328, 1370, 7012, 1259, 322, 537, 10677, 4818, 5744, 4414, 334, 13819, 2524, 5528, 96, 724, 203, 111, 203, 203, 306, 2680, 31, 30364, 5852, 2064, 619, 3833, 660, 2078, 44, 24256, 322, 3, 203, 913, 390, 2253, 4546, 81, 6323, 81, 32474, 280, 313, 59, 4621, 1420, 322, 2016, 372, 2596, 328, 866, 203, 913, 390, 2253, 4546, 81, 635, 2730, 81, 927, 567, 280, 313, 17743, 23231, 631, 623, 14763, 17740, 866, 203, 203, 1332, 203, 319, 506, 8017, 312, 2234, 31, 2816, 709, 295, 9982, 688, 43632, 312, 2596, 31, 266, 310, 14336, 328, 322, 2043, 5316, 203, 319, 1412, 322, 9161, 1401, 2596, 8940, 308, 15796, 529, 74, 31, 2], "prompt_token_count": 142, "reference_codepoints": 128, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [32, 2714, 26, 105, 30, 3692, 27, 357, 202, 1981, 32, 15109, 26], "continuation_token_count": 13, "decoded": ".send(w, ctx)\n\t\trequire.NoError(", "decoded_codepoints": 32, "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/failover_chatmodel_test.go", "example_id": "0002e9de0001d219b2f1e4825609cdaa9f626d7798dbb6baa6468a9c6fc680da", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 23922, 27, 603, 202, 601, 345, 36, 30, 1302, 30, 1302, 355, 202, 835, 357, 202, 111, 1314, 202, 105, 1025, 537, 56, 44148, 1243, 4672, 24370, 3968, 32, 1175, 729, 24, 1919, 30971, 5392, 1243, 6807, 8444, 27, 357, 202, 2095, 1025, 623, 11851, 7570, 1243, 6143, 2650, 9970, 26, 1819, 32, 5770, 1026, 549, 6172, 1243, 6143, 2650, 9970, 109, 355, 202, 1919, 30971, 3267, 4411, 1243, 44, 345, 35, 30, 357, 202, 1748, 357, 202, 6858, 30, 1137, 1025, 3, 109, 3968, 32, 1240, 1175, 440, 4980, 657, 1748, 357, 202, 1981, 32, 15109, 26, 102, 30, 1137, 27, 357, 202, 12617, 30, 1137, 1025, 44262, 1175, 1862, 26, 6858, 27, 357, 202, 1981, 32, 15109, 26, 102, 30, 1137, 27, 357, 202, 1981, 32, 5745, 26, 102, 30, 34373, 30, 225, 35, 27, 357, 202, 1981, 32, 1324, 26, 102, 30, 313, 3220, 392, 34373, 77, 34, 997, 1777, 27, 357, 202, 1981, 32, 1324, 26, 102, 30, 313, 98, 35, 98, 36, 392, 10925, 2301, 32, 3013, 1157, 357, 202, 1981, 32, 1324, 26, 102, 30, 328, 2], "prompt_token_count": 184, "reference_codepoints": 32, "repo": "cloudwego/eino", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [2811, 2926, 438, 5887, 436, 47826, 3452, 2993, 203, 202, 601, 617, 297, 81, 2811, 81, 2816, 346, 556, 617, 297, 81, 2811, 81, 2816, 81], "continuation_token_count": 26, "decoded": "debug mode is enabled for observability\"\"\"\n\treturn _is_debug_mode() or _is_debug_mode_", "decoded_codepoints": 86, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/observability.py", "example_id": "0002edc0b76665fff1c3a2165b42611a949ea14ce552adca1314046a1d4f22a7", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 625, 6204, 30, 24849, 30, 2768, 1881, 30, 9936, 203, 203, 4073, 280, 5741, 32, 10579, 4064, 426, 8223, 203, 1070, 8057, 2121, 1188, 2454, 81, 32006, 203, 203, 944, 81, 32006, 346, 203, 203, 21, 2768, 13183, 203, 56, 280, 2768, 1881, 463, 56, 370, 5085, 47, 14489, 40557, 6204, 1130, 478, 203, 21, 3456, 415, 996, 4484, 328, 4588, 2926, 203, 589, 617, 297, 81, 2811, 81, 2816, 346, 967, 1560, 44, 203, 202, 2993, 2140, 415, 225, 3, 5729, 346, 203, 202, 325, 456, 8152, 100, 81, 2811, 81, 2816, 610, 330, 2811, 950, 357, 202, 21, 4082, 32, 1338, 463, 3529, 2926, 438, 5887, 436, 47826, 3452, 683, 357, 202, 601, 2933, 203, 202, 21, 4082, 32, 1338, 463, 3529, 2926, 438, 6869, 436, 47826, 3452, 683, 203, 202, 601, 3177, 478, 203, 21, 8959, 372, 1188, 456, 8152, 100, 23980, 203, 81, 21062, 15422, 81, 25431, 280, 3177, 203, 81, 94, 8152, 100, 81, 24283, 280, 2], "prompt_token_count": 163, "reference_codepoints": 128, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [15276, 45, 284, 320, 284, 434, 12888, 11589, 12998, 2530, 7311, 81, 891, 40836, 284, 415, 308, 43456, 3644, 333, 308, 98, 396, 7190, 81, 891, 474, 225, 41, 27, 517, 225, 42, 1276, 291, 2698, 3631, 3644, 333, 298, 396, 7190, 81, 891, 319, 308, 410, 27, 7545, 26, 91, 40, 38, 490, 301, 397, 7631, 280, 4428, 2345, 81, 2930, 45, 397, 7195, 225, 15276, 45, 284, 320, 284, 434, 12888, 11589, 12998], "continuation_token_count": 75, "decoded": "cleanup;\n }\n // Validate blob sizes match chunk_size expectations\n if (validityBytes < (p->chunk_size + 7) / 8 ||\n rowidsBytes < p->chunk_size * (int)sizeof(i64)) {\n rc = SQLITE_ERROR;\n goto cleanup;\n }\n // Validate blob sizes", "decoded_codepoints": 258, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:sqlite-vec-rescore.c", "example_id": "000303fa034fb62d0fbb436f22503192f8a779af6251491cbe9e72e5069c5c31", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 301, 397, 7631, 280, 4428, 2345, 81, 2930, 45, 397, 7195, 13144, 45, 284, 320, 284, 434, 12888, 11589, 12998, 2530, 7311, 81, 891, 40836, 284, 415, 308, 43456, 3644, 333, 308, 98, 396, 7190, 81, 891, 474, 225, 41, 27, 517, 225, 42, 1276, 291, 2698, 3631, 3644, 333, 298, 396, 7190, 81, 891, 319, 308, 410, 27, 7545, 26, 91, 40, 38, 490, 301, 397, 7631, 280, 4428, 2345, 81, 2930, 45, 397, 7195, 225, 3, 45, 397, 436, 308, 410, 594, 280, 225, 34, 45, 594, 333, 298, 396, 7190, 81, 891, 45, 594, 1987, 301, 291, 415, 1429, 16121, 81, 371, 26, 7190, 34586, 30, 594, 490, 616, 4036, 45, 291, 595, 40, 38, 19220, 280, 7311, 2352, 3631, 77, 92, 970, 291, 763, 319, 6264, 280, 323, 1903, 1652, 1923, 30, 1417, 2352, 3631, 383, 396, 108, 30, 1417, 2352, 3631, 383, 396, 1322, 30, 7686, 309, 2], "prompt_token_count": 154, "reference_codepoints": 256, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [22, 2868, 45, 1615, 284, 22264, 225, 40, 38, 38, 3941, 2868, 20, 334, 8058, 719, 415, 653, 22264, 225, 40, 38, 38, 225, 35, 36, 41, 398, 2868, 45, 1615, 284, 22264, 225, 40, 38, 38, 225, 35, 36, 41, 3941, 2868, 20, 334, 8058, 719, 415, 653, 22264, 225, 40, 38, 38, 225, 35, 36, 41, 398, 2868, 45, 1615], "continuation_token_count": 62, "decoded": "$tmp; then\n chmod 644 \"$tmp\"\n fi\n\n if ! chmod 644 127 $tmp; then\n chmod 644 127 \"$tmp\"\n fi\n\n if ! chmod 644 127 $tmp; then", "decoded_codepoints": 132, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/answer.sh", "example_id": "00030626ff96f77db41c9fb21538a51c8b5e4434e94532d38d4947a8e395fa2c", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 313, 5288, 372, 2192, 398, 681, 1778, 1650, 398, 1055, 11555, 397, 442, 225, 35, 284, 8058, 334, 8058, 719, 415, 653, 3634, 6533, 5732, 3941, 2868, 20, 1276, 284, 653, 816, 95, 611, 410, 769, 3780, 364, 769, 1347, 541, 3941, 2868, 866, 1615, 284, 10194, 429, 88, 3941, 2868, 20, 284, 1048, 313, 6533, 398, 681, 7592, 803, 438, 5535, 11555, 284, 442, 225, 35, 334, 8058, 719, 415, 653, 22264, 225, 40, 38, 38, 225, 3, 8058, 719, 442, 225, 34, 203, 111, 203, 203, 5536, 14066, 5732, 346, 301, 719, 588, 32428, 12877, 884, 4723, 645, 3623, 4302, 7022, 2050, 1259, 334, 588, 4335, 23760, 7205, 21036, 2940, 436, 11903, 31, 10265, 30945, 32, 719, 2196, 804, 12672, 35, 20, 334, 2196, 14098, 81, 1055, 9483, 36, 5979, 3845, 334, 2196, 4302, 9483, 2], "prompt_token_count": 139, "reference_codepoints": 128, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [301, 357, 202, 25, 2997, 81, 2171, 950, 225, 34, 30, 357, 202, 25, 2997, 81, 1366], "continuation_token_count": 17, "decoded": " {\n\t\t'step_number': 0,\n\t\t'step_start", "decoded_codepoints": 36, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/test_history_wait_time.py", "example_id": "000317d756ad550db6336dba541664135c4ba5c3b68e30dc5a8b167d63c9248c", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 332, 3610, 2179, 645, 3398, 203, 202, 1455, 81, 4519, 81, 2665, 280, 301, 357, 202, 1182, 519, 98, 81, 2171, 950, 225, 34, 30, 357, 202, 1182, 519, 98, 81, 1366, 81, 1003, 950, 225, 35, 34, 34, 34, 32, 34, 30, 357, 202, 1182, 519, 98, 81, 416, 81, 1003, 950, 225, 35, 34, 34, 36, 32, 39, 30, 357, 202, 21, 3111, 81, 7568, 1600, 4163, 1330, 2307, 308, 1455, 2179, 27, 203, 202, 111, 478, 202, 21, 9043, 2454, 7504, 623, 3111, 81, 7568, 1244, 299, 372, 1665, 203, 202, 4519, 280, 3, 81, 4519, 81, 2665, 27, 478, 202, 862, 5035, 32, 2997, 81, 2171, 610, 225, 34, 203, 202, 862, 5035, 32, 2997, 81, 1366, 81, 1003, 610, 225, 35, 34, 34, 34, 32, 34, 203, 202, 862, 5035, 32, 2997, 81, 416, 81, 1003, 610, 225, 35, 34, 34, 36, 32, 39, 203, 202, 862, 5035, 32, 2997, 81, 7568, 438, 1665, 225, 588, 4101, 786, 478, 203, 589, 894, 81, 6932, 81, 6360, 81, 2433, 81, 38252, 81, 14110, 2262, 203, 202, 2993, 1006, 688, 2], "prompt_token_count": 185, "reference_codepoints": 32, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [2358, 26, 9671, 547, 5492, 1883, 473, 397, 1424, 26, 95, 542, 32, 371, 440, 9671, 11596, 5492, 1883, 473, 397, 1424, 26, 95, 542, 32, 371, 440, 9671, 11596, 5492, 1883, 473, 397, 1424], "continuation_token_count": 35, "decoded": "expect(pending).toBeNull();\n expect(moc.get(\"pending\")).toBeNull();\n expect(moc.get(\"pending\")).toBeNull();\n expect", "decoded_codepoints": 130, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/auth-commands.test.ts", "example_id": "0003212c2234a0442e4f64a1a30202864c7d9d386a7067a5e9608f1ee7f3685c", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 44, 313, 39624, 20, 801, 397, 1122, 1687, 660, 11350, 280, 4436, 5324, 26, 1870, 293, 397, 434, 8819, 17850, 49034, 2685, 322, 2815, 225, 34, 874, 7898, 45, 12899, 81, 1746, 1615, 397, 434, 17413, 101, 322, 7898, 810, 225, 39, 34, 34, 34, 874, 2670, 322, 3100, 17850, 32, 397, 2014, 8943, 32, 22545, 41490, 1083, 1043, 2981, 26, 39, 39, 34, 34, 293, 1568, 3, 22192, 301, 397, 8943, 32, 539, 6877, 41490, 473, 284, 320, 334, 1122, 719, 894, 440, 3255, 744, 1412, 1477, 1326, 2571, 392, 2498, 1404, 532, 301, 284, 4395, 2130, 3033, 8466, 32, 3613, 32582, 882, 26, 890, 3081, 440, 4573, 2835, 2974, 446, 1424, 26, 6240, 4436, 5324, 26, 1870, 3427, 5492, 1883, 473, 284, 1424, 26, 95, 542, 2], "prompt_token_count": 130, "reference_codepoints": 128, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [21, 1683, 3985, 544, 2979, 31, 19541, 17503, 291, 434, 428, 4687, 26, 1206, 26, 16705, 12634, 291], "continuation_token_count": 18, "decoded": "# Unused on non-Unix platforms\n // [cfg(not(unix))]\n ", "decoded_codepoints": 66, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/install.rs", "example_id": "0003216bc1ca8a073368c81393f364edc11feed0e3ecc62ea6dbd497acf3e554", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 490, 291, 638, 3227, 9670, 2883, 61, 81, 12896, 9166, 549, 1132, 32, 2524, 440, 41320, 446, 5980, 81, 530, 403, 2961, 2031, 403, 890, 346, 291, 638, 1821, 26, 1508, 27, 291, 638, 1297, 26, 1508, 27, 291, 638, 25432, 26, 1508, 27, 291, 638, 1676, 1652, 7133, 81, 983, 6505, 291, 638, 1821, 81, 464, 26, 7133, 81, 1423, 32, 302, 81, 3651, 1157, 12370, 446, 5496, 4687, 26, 16705, 2177, 284, 301, 276, 3, 7133, 81, 983, 32, 4519, 48705, 11893, 473, 291, 38875, 32, 470, 81, 2816, 26, 7133, 81, 2816, 293, 291, 5980, 81, 530, 403, 470, 81, 11893, 1652, 7133, 81, 983, 30, 38875, 12942, 284, 320, 446, 434, 1683, 3985, 544, 2979, 31, 19541, 17503, 284, 5496, 4687, 26, 1206, 26, 16705, 12634, 284, 1207, 617, 280, 11962, 81, 2816, 45, 446, 2870, 43166, 4482, 21201, 32, 9362, 1026, 10698, 12118, 8474, 12370, 2], "prompt_token_count": 152, "reference_codepoints": 64, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [96, 657, 203, 202, 102, 32, 2529, 440, 4543, 96, 657, 203, 202, 102, 32, 2529, 440, 4543, 96, 657, 203, 202, 102, 32, 2529, 440, 4543, 96, 657, 203, 202, 102, 32, 2529, 440, 4543, 96, 657, 203, 202, 102, 32, 2529, 440, 4543, 96, 657, 203, 202, 102, 32, 2529, 440, 4543, 96, 657, 203, 202, 102, 32, 2529, 440, 4543, 96, 657, 203, 202, 102, 32, 2529, 440, 4543], "continuation_token_count": 72, "decoded": "n\")\n\tt.Run(\"realn\")\n\tt.Run(\"realn\")\n\tt.Run(\"realn\")\n\tt.Run(\"realn\")\n\tt.Run(\"realn\")\n\tt.Run(\"realn\")\n\tt.Run(\"realn\")\n\tt.Run(\"real", "decoded_codepoints": 128, "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:compose/chain_branch_test.go", "example_id": "00032e58cde93583b30d0977a5e8ed5305ca1fd0dc676abb6951d6123c48b84e", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 303, 524, 30, 1302, 355, 202, 111, 2610, 1314, 202, 862, 32, 9289, 26, 102, 30, 281, 32, 530, 27, 357, 202, 19243, 7418, 30, 1137, 1025, 281, 32, 13788, 26, 1819, 32, 5770, 1157, 357, 202, 862, 32, 9289, 26, 102, 30, 1137, 27, 1314, 202, 541, 30, 1137, 1025, 13831, 7418, 32, 8731, 26, 1819, 32, 5770, 1026, 313, 658, 657, 357, 202, 862, 32, 9289, 26, 102, 30, 1137, 27, 357, 202, 862, 32, 1324, 26, 102, 30, 313, 658, 658, 392, 963, 27, 203, 202, 1748, 478, 202, 102, 32, 2529, 440, 4543, 3, 301, 355, 202, 2076, 30, 1137, 1025, 17295, 32, 25622, 346, 355, 202, 325, 1137, 863, 1302, 301, 603, 202, 601, 4320, 1137, 355, 202, 111, 355, 202, 7353, 17295, 32, 4173, 346, 2540, 202, 4640, 3124, 301, 355, 202, 1732, 313, 658, 563, 603, 202, 601, 313, 658, 81, 678, 392, 1302, 355, 202, 1732, 313, 8268, 563, 603, 202, 601, 313, 8268, 81, 678, 392, 1302, 355, 202, 1732, 313, 12192, 563, 603, 202, 601, 313, 12192, 81, 678, 392, 1302, 355, 202, 1536, 44, 603, 202, 2094, 305, 2], "prompt_token_count": 191, "reference_codepoints": 128, "repo": "cloudwego/eino", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [32, 4526, 440, 4620, 319, 3753, 25937, 105, 1492, 48659], "continuation_token_count": 10, "decoded": ".execute(\"SELECT * FROM \\\"%w\\\".\\\"", "decoded_codepoints": 33, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:sqlite-vec-rescore.c", "example_id": "00033273f4f5185e93a8171e5f0ab036d781962e9ad133e9f7b4054af18afebb", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 434, 24300, 1191, 7311, 1858, 308, 8786, 6371, 619, 617, 2402, 81, 21803, 27, 284, 1351, 319, 108, 5344, 280, 17735, 37, 81, 317, 10744, 88, 26, 291, 313, 6037, 4925, 25937, 105, 1492, 48659, 23, 105, 81, 575, 1262, 81, 21803, 23, 34, 36, 86, 21328, 291, 11608, 643, 314, 11190, 5578, 30, 16540, 41070, 2370, 1181, 5715, 291, 298, 396, 3968, 558, 30, 298, 396, 16820, 30, 595, 293, 284, 415, 1429, 108, 5344, 3, 17735, 37, 81, 6404, 319, 6404, 45, 284, 629, 7631, 280, 17735, 37, 81, 9266, 81, 104, 36, 26, 1199, 30, 1288, 5344, 30, 429, 35, 30, 549, 6404, 30, 225, 34, 293, 284, 17735, 37, 81, 3994, 26, 108, 5344, 293, 284, 415, 1833, 899, 863, 4428, 2345, 81, 2950, 27, 1276, 308, 14107, 37, 81, 2997, 26, 6404, 27, 863, 4428, 2345, 81, 25001, 490, 301, 397, 319, 30417, 4309, 280, 17735, 37, 81, 317, 10744, 88, 26, 616, 313, 9752, 646, 1487, 7610, 575, 1262, 81, 21803, 23, 34, 36, 86, 25, 787, 339, 2], "prompt_token_count": 176, "reference_codepoints": 32, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [261, 320, 291, 320, 284, 320, 446, 434, 1670, 322], "continuation_token_count": 10, "decoded": " }\n }\n }\n\n // If the", "decoded_codepoints": 35, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/archive.rs", "example_id": "000336198cfac164ebafc3bf71372c619475d39b1b0ecc6d596e915c01bec2b8", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 9553, 372, 21846, 299, 30, 619, 1292, 44, 324, 434, 1678, 555, 2180, 32, 3666, 33, 4396, 81, 3969, 33, 34, 32, 34, 32, 35, 40, 33, 4396, 81, 3969, 33, 1439, 33, 850, 33, 2238, 33, 324, 40541, 30, 8529, 27, 280, 3414, 32, 5961, 922, 6240, 12370, 1064, 434, 8809, 322, 1550, 3401, 32, 324, 3401, 280, 8529, 32, 2881, 473, 1064, 4036, 45, 397, 3, 32, 2524, 26, 983, 293, 291, 1207, 438, 81, 1515, 280, 3414, 32, 6308, 922, 3038, 922, 1515, 34192, 584, 434, 21428, 1487, 322, 3362, 556, 2866, 322, 803, 372, 9519, 32, 291, 415, 438, 81, 1515, 301, 324, 415, 14904, 32, 3215, 26, 983, 32, 6358, 1157, 301, 400, 5980, 81, 530, 403, 13586, 716, 403, 1297, 81, 1515, 81, 464, 26, 983, 547, 812, 2], "prompt_token_count": 136, "reference_codepoints": 32, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [2416, 32, 2121, 32, 46651, 7204, 81, 21980, 81, 7789, 474, 3056, 5558, 33, 85, 453, 37076, 33, 85, 453, 37076, 32, 978, 895, 203, 111, 203, 203, 730, 20838, 1777, 280, 5980, 32, 27192, 26, 10887, 30, 330, 3310, 42, 895, 203, 730, 1688, 280, 5980, 32, 27192, 26, 2024, 30, 330, 3310, 42, 895, 203, 203, 730, 15133, 280, 5980, 32, 27192, 26, 16142, 30, 330, 3310, 42], "continuation_token_count": 70, "decoded": "process.env.CLAUDE_PLUGIN_ROOT + '/plugins/caveman/caveman.py');\n}\n\nlet skillContent = fs.readFileSync(skill, 'utf8');\nlet output = fs.readFileSync(output, 'utf8');\n\nlet candidate = fs.readFileSync(candidate, 'utf8", "decoded_codepoints": 214, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/hooks/caveman-activate.js", "example_id": "00033d9ab62e5672a7a8c2eb2ee44ab96559533530e77753c3f5fa1aa57ad69d", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 349, 21042, 821, 203, 306, 647, 398, 46651, 7204, 81, 6191, 81, 3197, 33, 12329, 33, 461, 322, 20838, 821, 398, 46651, 7204, 81, 6191, 81, 3197, 33, 25071, 33, 85, 453, 37076, 4724, 203, 306, 3367, 3980, 1464, 16843, 3919, 372, 322, 43362, 17163, 5750, 470, 4794, 32, 203, 913, 20838, 40965, 280, 4312, 203, 325, 308, 2416, 32, 2121, 32, 46651, 7204, 81, 21980, 81, 7789, 27, 301, 334, 20838, 40965, 32, 2018, 26, 3, 920, 203, 979, 308, 913, 15133, 432, 20838, 40965, 27, 301, 334, 1596, 301, 284, 20838, 1777, 280, 5980, 32, 27192, 26, 16142, 30, 330, 3310, 42, 895, 284, 1626, 45, 334, 320, 2368, 308, 87, 27, 301, 1257, 1596, 2354, 15133, 569, 320, 203, 111, 203, 203, 730, 1688, 45, 203, 203, 325, 308, 10887, 1777, 27, 301, 334, 434, 41928, 21792, 8432, 23229, 334, 660, 3361, 280, 20838, 1777, 32, 100, 2], "prompt_token_count": 152, "reference_codepoints": 256, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [101, 6620, 523, 529, 730, 4845, 44, 7479, 46, 103, 42, 5856, 436, 5253], "continuation_token_count": 14, "decoded": "s()` | `let buf: Vec` for fixed", "decoded_codepoints": 35, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:type-driven-correctness-book/src/ch13-reference-card.md", "example_id": "00033de5e0a3aa7fdee17ed0f83206cbe3f59edd81d1ce71b500dba53f2d5600", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 87, 523, 12029, 1330, 30310, 14429, 523, 203, 110, 529, 730, 16403, 81, 314, 44, 1044, 35, 40, 280, 225, 34, 24988, 82, 523, 44345, 40435, 22678, 523, 529, 730, 16403, 81, 314, 44, 3659, 46, 103, 35, 40, 48, 280, 1665, 82, 523, 203, 110, 529, 3359, 5543, 26, 2649, 44, 549, 466, 7601, 623, 17163, 523, 20775, 966, 45889, 1244, 523, 529, 730, 3193, 44, 46013, 2656, 280, 309, 32, 2208, 346, 39853, 523, 203, 110, 529, 1796, 403, 890, 922, 11333, 3, 1473, 23011, 523, 2768, 1293, 4906, 44, 529, 11333, 6620, 485, 733, 544, 529, 885, 82, 523, 203, 110, 529, 730, 4845, 44, 7479, 46, 103, 42, 5856, 436, 5253, 31, 891, 29099, 3112, 523, 8660, 1755, 8137, 821, 6091, 523, 529, 4329, 12176, 46, 38, 34, 43, 40, 5856, 308, 913, 10140, 27, 523, 203, 110, 16289, 529, 16263, 301, 8414, 403, 850, 22688, 37626, 26703, 318, 523, 632, 52, 19902, 30, 7542, 6774, 444, 523, 529, 2], "prompt_token_count": 165, "reference_codepoints": 32, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [100, 32, 30976, 30, 313, 6772, 44, 904, 101, 428, 2184, 79, 429, 1131, 333, 31380, 32, 2760, 5213, 96, 78, 96, 392, 2322, 32, 3080], "continuation_token_count": 26, "decoded": "r.Stderr, \"Usage: %s [options] -input \\n\\n\", os.Args", "decoded_codepoints": 64, "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:cmd/robots2policy/main.go", "example_id": "000344d27c4d98c2d71d6b719fb9f0079435e62c3ec383c16695e5a0b7c550c6", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 365, 32, 7583, 2264, 529, 6045, 1924, 3292, 30, 6039, 20, 2361, 1924, 3292, 30, 6039, 3171, 203, 202, 558, 958, 802, 6019, 529, 6045, 1924, 426, 20, 2361, 1924, 426, 3171, 203, 202, 1711, 262, 802, 6019, 529, 6045, 1924, 1141, 20, 2361, 1924, 1141, 3171, 203, 111, 203, 203, 1298, 3219, 346, 301, 203, 202, 4555, 32, 6772, 280, 3420, 346, 301, 357, 202, 3972, 32, 35808, 26, 500, 3, 15860, 101, 428, 2184, 79, 429, 1131, 333, 31380, 32, 2760, 5213, 96, 78, 96, 392, 2322, 32, 3080, 77, 34, 1130, 357, 202, 4555, 32, 4014, 14490, 346, 357, 202, 3972, 32, 56, 3948, 26, 500, 32, 30976, 30, 2706, 96, 17533, 23498, 357, 202, 3972, 32, 56, 3948, 26, 500, 32, 30976, 30, 313, 225, 588, 8125, 2196, 13047, 101, 32, 2760, 803, 657, 357, 202, 3972, 32, 56, 3948, 26, 500, 32, 30976, 30, 313, 225, 13047, 101, 36, 6038, 429, 1131, 13047, 101, 32, 2760, 429, 2024, 7231, 32, 107, 2], "prompt_token_count": 168, "reference_codepoints": 64, "repo": "TecharoHQ/anubis", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [6977, 396, 426, 30, 549, 4923, 293, 397, 415, 308], "continuation_token_count": 10, "decoded": " symbol->name, &cmp);\n if (", "decoded_codepoints": 32, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/lnk_symbol_table.c", "example_id": "000352c2a7f43acd1d1587cd2ae88d621b2e36ea28c5f37fe093a99f0c7cfef7", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 106, 35, 34, 34, 34, 293, 397, 537, 81, 42139, 396, 426, 3389, 280, 549, 7010, 396, 426, 45, 397, 537, 81, 42139, 396, 7010, 2407, 280, 6977, 45, 397, 11348, 8039, 1261, 26, 890, 81, 42139, 396, 2661, 293, 1687, 434, 1596, 372, 5551, 537, 1541, 397, 28933, 61, 81, 6084, 2885, 70, 4063, 319, 4923, 280, 7889, 81, 6231, 81, 1753, 81, 6569, 81, 1328, 81, 5157, 26, 8945, 81, 42139, 81, 1753, 30, 3, 1597, 6977, 17816, 49, 397, 415, 308, 4923, 610, 9985, 81, 42139, 27, 301, 291, 1626, 45, 397, 320, 1687, 434, 34524, 7311, 1149, 5840, 397, 769, 21803, 396, 2135, 396, 998, 45, 1687, 434, 11322, 5551, 623, 44845, 1541, 645, 4674, 3664, 397, 9985, 81, 42139, 280, 13593, 45, 284, 320, 446, 434, 2454, 1550, 6977, 664, 2], "prompt_token_count": 137, "reference_codepoints": 32, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [18964, 293, 291, 2014, 1424, 26, 3515, 32, 1298, 1371, 24605, 44, 330, 10104, 713, 25, 42709, 11592, 101, 32, 35798, 26, 47717, 293, 291, 2014, 1424], "continuation_token_count": 27, "decoded": " ArgumentNullException);\n await expect(cmd.func({ perf: 'turbo' })).rejects.toByteArray(ArgumentError);\n await expect", "decoded_codepoints": 131, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/lichess/lichess.test.js", "example_id": "00035e73549bd9e6738e0bb311d8593ad9b3080ef91f8b3bc1c6e24ab8e749f2", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 380, 299, 370, 2498, 1404, 532, 301, 291, 660, 5630, 3660, 280, 8943, 32, 3359, 473, 291, 8943, 32, 10520, 4455, 463, 5140, 370, 5630, 3660, 293, 291, 2014, 1424, 26, 3515, 32, 1298, 1371, 24605, 44, 4247, 42709, 11592, 101, 32, 32000, 26, 47717, 293, 291, 2014, 1424, 26, 3515, 32, 1298, 1371, 24605, 44, 330, 10104, 713, 25, 42709, 11592, 101, 32, 32000, 26, 47717, 3, 17350, 473, 284, 1122, 446, 561, 463, 5117, 14893, 1394, 924, 544, 3502, 22021, 2190, 370, 2498, 1404, 532, 301, 291, 8943, 32, 10520, 4455, 463, 5140, 370, 8943, 32, 3359, 922, 3613, 17923, 882, 26, 890, 5170, 26, 3265, 32, 8136, 1371, 4250, 44, 1605, 7305, 301, 2287, 44, 225, 36, 34, 34, 320, 4236, 291, 2014, 1424, 26, 3515, 32, 1298, 1371, 24605, 44, 2], "prompt_token_count": 136, "reference_codepoints": 128, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [3523, 438, 646, 203, 202, 306, 42050, 32, 203, 202, 862, 32, 2700, 26, 102, 30, 18578, 4309, 30, 313, 3163, 7768, 312, 18578, 1048, 657, 478, 202, 306, 886, 4835, 44, 18578, 4131, 8158, 3301, 322, 3523, 438, 42050, 32, 203, 202, 862, 32, 2700, 26, 102, 30, 18578, 4309, 30, 313, 3163, 7768, 312, 18578, 1048, 657, 478, 202, 306, 886, 4835, 44], "continuation_token_count": 65, "decoded": " session is not\n\t// interrupted.\n\tassert.False(t, checkpointErr, \"should receive a checkpoint error\")\n\n\t// The bug: checkpoint save fails because the session is interrupted.\n\tassert.False(t, checkpointErr, \"should receive a checkpoint error\")\n\n\t// The bug:", "decoded_codepoints": 256, "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/interrupt_test.go", "example_id": "00036ddcecad4a66bd25f5ff05517cb2a9b456233b74470d21653153e4246200", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 87, 454, 1493, 4309, 1048, 203, 202, 979, 301, 357, 202, 1567, 30, 3835, 1025, 3850, 32, 3353, 346, 357, 202, 325, 653, 1253, 301, 355, 202, 2969, 357, 202, 111, 357, 202, 5057, 280, 5489, 26, 5057, 30, 1692, 27, 357, 202, 325, 1692, 32, 4309, 863, 1302, 301, 355, 202, 17141, 4309, 280, 1692, 32, 4309, 355, 202, 102, 32, 43026, 440, 1567, 1048, 44, 904, 104, 392, 1692, 32, 4309, 27, 357, 202, 111, 203, 202, 111, 478, 202, 306, 886, 4835, 44, 18578, 4131, 8158, 3301, 322, 3, 7815, 3443, 1182, 1048, 328, 3523, 657, 478, 202, 869, 1401, 19497, 1560, 203, 202, 979, 4950, 1692, 1025, 2155, 5216, 301, 357, 202, 325, 1692, 32, 1711, 863, 1302, 962, 1692, 32, 1711, 32, 1646, 12828, 863, 1302, 301, 355, 202, 2040, 19497, 280, 861, 357, 202, 111, 203, 202, 111, 203, 202, 862, 32, 1815, 26, 102, 30, 1401, 19497, 30, 313, 3163, 7768, 600, 11264, 1692, 645, 322, 2], "prompt_token_count": 165, "reference_codepoints": 256, "repo": "cloudwego/eino", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [264, 660, 13420, 280, 2014, 13420], "continuation_token_count": 6, "decoded": " const validator = await validator", "decoded_codepoints": 37, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/validation.test.ts", "example_id": "00037b69df6a742b12c729fa88f43cc113c75a21f5ceb27d2ee46cb47af03afa", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 203, 765, 34394, 44, 8073, 10677, 203, 16627, 312, 1256, 623, 5535, 10677, 203, 5786, 2953, 6465, 322, 6207, 2234, 203, 10684, 2953, 2318, 600, 1048, 1474, 7839, 1687, 660, 1374, 1215, 280, 1519, 32, 2524, 26, 858, 2976, 30, 330, 2285, 32, 954, 895, 397, 2014, 5980, 32, 39052, 26, 2285, 1215, 30, 1374, 1777, 293, 1568, 1568, 3, 293, 397, 660, 3639, 280, 2014, 13420, 32, 4635, 2710, 26, 2285, 1215, 293, 8903, 1424, 26, 3734, 32, 1327, 547, 5492, 26, 1508, 293, 397, 1424, 26, 3734, 32, 1367, 32, 4275, 547, 5492, 26, 34, 293, 284, 1122, 446, 561, 463, 3163, 11140, 5816, 20783, 4169, 370, 2498, 1404, 532, 301, 397, 660, 1374, 1777, 280, 24930, 225, 2], "prompt_token_count": 122, "reference_codepoints": 32, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [45, 284, 660, 2968, 4058, 280, 2014, 3909, 2780, 463, 5883, 31, 1819, 25, 474, 2968, 558, 30, 10880, 2976, 293, 284, 660, 3414, 280, 2014, 2968, 2711, 26, 2157, 4058, 30, 330, 5883, 31, 1819, 370, 330, 5883, 31, 1819, 370, 330, 5883, 31, 1819, 370, 330, 5883, 31, 1819, 370, 330, 5883, 31, 1819, 370, 330, 5883, 31, 1819, 370, 330, 5883, 31, 1819, 370, 330, 5883, 31, 1819], "continuation_token_count": 71, "decoded": ";\n const storeRoot = await registerStore('team-context' + storeName, registryDir);\n const entry = await storeEntry(storeRoot, 'team-context', 'team-context', 'team-context', 'team-context', 'team-context', 'team-context', 'team-context', 'team-context", "decoded_codepoints": 257, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/references.test.ts", "example_id": "000381cd3201cf314a8f24bdbb2b0cdde433334ca16bb7dec0a39f500f1a7f72", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 369, 81, 2388, 81, 311, 36436, 370, 616, 2421, 44, 1424, 32, 800, 32135, 463, 11593, 897, 2968, 35726, 1425, 291, 1790, 397, 1093, 284, 320, 334, 1122, 719, 561, 463, 286, 4944, 101, 3638, 4121, 1412, 322, 10880, 438, 707, 18210, 370, 2498, 1404, 532, 301, 284, 660, 10880, 2976, 280, 1519, 32, 2524, 26, 3264, 750, 2976, 30, 330, 26231, 895, 3, 3038, 432, 8036, 27, 301, 397, 1424, 26, 3038, 32, 1517, 77, 34, 997, 687, 547, 5492, 463, 3576, 81, 8200, 81, 311, 18210, 895, 284, 320, 334, 1122, 719, 561, 463, 5961, 101, 1374, 1795, 30, 5630, 35722, 30, 461, 322, 23912, 328, 11806, 2926, 308, 37, 32, 40, 7243, 2498, 1404, 532, 301, 284, 660, 2968, 4058, 280, 2014, 3909, 2780, 463, 5883, 31, 1819, 25, 2], "prompt_token_count": 134, "reference_codepoints": 256, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [426, 334, 2196, 31605, 81, 314, 2443, 81], "continuation_token_count": 8, "decoded": "name\n local edition_id install_", "decoded_codepoints": 32, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/image.sh", "example_id": "0003859ef3a8760e7dd1e8007b867a4d840d70fe32523507f6124672a01f71e3", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 81, 426, 12672, 39, 20, 334, 2196, 429, 96, 7041, 81, 612, 12672, 9561, 81, 426, 20, 334, 2196, 429, 96, 26394, 81, 612, 12672, 29915, 81, 426, 20, 334, 2196, 429, 96, 8351, 81, 612, 12672, 6332, 81, 426, 20, 334, 2196, 429, 96, 17215, 81, 612, 12672, 18713, 81, 426, 20, 719, 2196, 2385, 1778, 1778, 81, 1055, 334, 2196, 2503, 4054, 5624, 334, 2196, 31605, 81, 314, 2443, 81, 3, 225, 7041, 81, 612, 41819, 334, 26394, 81, 612, 41819, 334, 8351, 81, 612, 41819, 334, 17215, 81, 612, 41819, 719, 5624, 9456, 371, 6841, 3941, 2593, 657, 334, 2385, 9456, 18974, 611, 410, 769, 3780, 364, 769, 16689, 330, 998, 7009, 73, 2331, 33, 10393, 9905, 429, 225, 36, 9159, 1902, 33, 1693, 33838, 3941, 2593, 657, 1276, 442, 225, 34, 719, 436, 1833, 91, 47, 35, 45, 595, 10040, 998, 45, 595, 1046, 876, 745, 446, 1778, 81, 1055, 9456, 18974, 611, 410, 769, 96, 2], "prompt_token_count": 162, "reference_codepoints": 32, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [396, 203, 202, 7878, 32, 2538, 26, 2095, 30, 549, 2538, 1104], "continuation_token_count": 12, "decoded": "->\n\tbackend.Write(ctx, &WriteRequest", "decoded_codepoints": 36, "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/filesystem/backend_inmemory_test.go", "example_id": "000385bf0813d628b475dad13d0c705e7aa26575ed21198c05ea9cd6564a2afa", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 79, 280, 861, 355, 202, 111, 813, 301, 603, 202, 102, 32, 5497, 440, 10203, 1519, 44, 904, 101, 392, 3099, 32, 1215, 27, 355, 202, 111, 357, 202, 111, 1314, 202, 979, 1519, 30, 2431, 1025, 2155, 2799, 301, 355, 202, 325, 653, 6264, 301, 603, 202, 102, 32, 5497, 440, 7700, 7976, 1519, 646, 2431, 44, 904, 101, 392, 1519, 27, 355, 202, 111, 357, 202, 111, 203, 202, 1748, 203, 111, 203, 203, 1298, 2108, 35500, 10564, 81, 18720, 26, 102, 319, 4266, 32, 70, 27, 225, 3, 346, 203, 202, 2095, 1025, 1619, 32, 5770, 346, 478, 202, 306, 2108, 22493, 19408, 461, 14822, 203, 202, 5087, 1025, 1930, 26, 6622, 1560, 27, 203, 202, 979, 595, 1025, 225, 34, 45, 595, 333, 225, 35, 34, 45, 595, 1046, 301, 357, 202, 1704, 3420, 26, 96, 629, 27, 301, 355, 202, 7878, 32, 2538, 26, 2095, 30, 549, 2538, 1104, 109, 603, 202, 9140, 44, 2430, 8347, 32, 2760, 392, 603, 202, 1777, 44, 225, 313, 1286, 392, 355, 202, 1748, 355, 202, 7878, 32, 435, 83, 2], "prompt_token_count": 183, "reference_codepoints": 32, "repo": "cloudwego/eino", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [271, 225, 34, 357, 202, 2613, 81, 16777, 280, 18623, 26, 8795, 30, 330, 2613, 81, 16777, 370, 225, 34, 27, 556, 225, 34, 357, 202, 13232, 81, 10569, 280, 18623, 26, 8795, 30, 330, 13232, 81, 10569, 370, 225, 34, 27, 556, 225, 34, 357, 202, 13232, 81, 2613, 81, 16777, 81, 8395, 280, 18623, 26, 8795, 30, 330, 13232, 81, 2613, 81, 16777, 81, 8395, 370, 225, 34, 27, 556, 225, 34, 1314, 202, 325, 13012, 81, 8395, 848, 13364, 81, 8395, 44, 355, 202, 601], "continuation_token_count": 88, "decoded": "or 0\n\t\tcache_creation = getattr(usage, 'cache_creation', 0) or 0\n\t\tprompt_cached = getattr(usage, 'prompt_cached', 0) or 0\n\t\tprompt_cache_creation_tokens = getattr(usage, 'prompt_cache_creation_tokens', 0) or 0\n\n\t\tif prompt_tokens > completion_tokens:\n\t\t\treturn", "decoded_codepoints": 261, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/llm/litellm/chat.py", "example_id": "0003865e59e050d90a40cec47b6954f03f72f6f62fd2570fba9077c30c1de992", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 658, 44, 357, 202, 2993, 10067, 2404, 6886, 645, 312, 21470, 1030, 95, 1789, 7103, 357, 202, 8795, 280, 18623, 26, 1986, 30, 330, 8795, 370, 1665, 27, 357, 202, 325, 6886, 438, 1665, 44, 355, 202, 601, 1665, 1314, 202, 13232, 81, 8395, 280, 18623, 26, 8795, 30, 330, 13232, 81, 8395, 370, 225, 34, 27, 556, 225, 34, 357, 202, 15825, 81, 8395, 280, 18623, 26, 8795, 30, 330, 15825, 81, 8395, 370, 225, 34, 27, 225, 3, 81, 10569, 280, 18623, 26, 3958, 30, 330, 10569, 81, 8395, 370, 1665, 27, 1314, 202, 601, 16090, 8731, 6772, 26, 355, 202, 13232, 81, 8395, 47, 13232, 81, 8395, 30, 355, 202, 13232, 81, 10569, 81, 8395, 47, 410, 26, 13232, 81, 10569, 27, 415, 13012, 81, 10569, 438, 646, 1665, 813, 1665, 30, 355, 202, 13232, 81, 2613, 81, 16777, 81, 8395, 47, 410, 26, 2613, 81, 16777, 27, 415, 3320, 81, 1220, 2], "prompt_token_count": 157, "reference_codepoints": 256, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [800, 81, 85, 4965, 1162, 1594, 3730, 426, 81, 1753, 30, 308, 1594, 18862, 2232, 474, 5205, 876, 528, 20037, 81, 426, 280, 636, 45, 528, 434, 5799, 81, 426, 528, 632, 42, 319, 5665, 81, 426, 81, 1753, 280, 636, 81, 1753, 474, 636, 32, 891, 474, 225, 35, 45, 528, 892, 42, 5799, 81, 426, 280, 596, 42, 81, 39802, 81], "continuation_token_count": 63, "decoded": "string_capped((char*)name_ptr, (char *)(first + cap));\n extracted_name = name;\n // unique_name\n U8 *unique_name_ptr = name_ptr + name.size + 1;\n String8 unique_name = str8_cstring_", "decoded_codepoints": 256, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/pdb/pdb_parse.c", "example_id": "0003887410964c8256357ef47d3797fe42fbe72bdb07c44919f6061320965254", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 29, 225, 35, 293, 528, 18066, 81, 12930, 24217, 1334, 280, 6677, 81, 10125, 81, 1070, 81, 605, 81, 3585, 26, 10125, 81, 1753, 30, 1932, 474, 5205, 293, 20192, 434, 636, 528, 632, 42, 319, 426, 81, 1753, 280, 12738, 81, 1753, 474, 1334, 32, 12596, 81, 891, 45, 528, 892, 42, 636, 280, 225, 3, 262, 632, 42, 319, 5665, 81, 426, 81, 1753, 280, 636, 81, 1753, 474, 636, 32, 891, 474, 225, 35, 45, 715, 892, 42, 5799, 81, 426, 280, 596, 42, 81, 39802, 81, 85, 4965, 1162, 1594, 3730, 5665, 81, 426, 81, 1753, 30, 308, 1594, 18862, 2232, 474, 5205, 876, 715, 20037, 81, 426, 280, 5799, 81, 426, 45, 2855, 320, 324, 2], "prompt_token_count": 122, "reference_codepoints": 256, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [958, 320, 324, 1122, 291, 320, 291, 442, 301, 324, 330, 731, 950, 301, 400, 330, 687, 950, 225, 38, 34, 34, 30, 3083, 330, 1436, 950, 330, 1045, 4096, 2965, 438, 2129, 6418, 324, 801, 324, 330, 605, 950, 301, 400, 330, 1935, 950, 4096, 30, 400, 330, 4682, 974], "continuation_token_count": 51, "decoded": " }\n });\n }\n return {\n 'error': {\n 'code': 400,\n 'message': 'An email address is required.',\n },\n 'data': {\n 'email': email,\n 'pdfFile", "decoded_codepoints": 256, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/paperreview/submit.js", "example_id": "00038ffac561a70700a979f78d20760d4e1ac26acd79818b2551b91eef0243ab", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1468, 1422, 537, 27070, 924, 463, 29940, 370, 330, 1045, 4096, 2965, 438, 2129, 6418, 330, 6129, 769, 1935, 333, 2468, 16026, 291, 320, 291, 415, 308, 24223, 2529, 27, 301, 324, 442, 46053, 23357, 1371, 400, 17117, 974, 30, 400, 4096, 30, 400, 19932, 340, 30, 616, 3, 225, 1411, 44, 330, 3705, 370, 324, 4826, 44, 301, 330, 1777, 31, 620, 950, 330, 3164, 33, 1260, 25, 801, 324, 3361, 44, 3398, 32, 8136, 1371, 400, 4870, 44, 17117, 974, 32, 10447, 30, 400, 19932, 340, 30, 324, 7305, 291, 1122, 291, 7279, 4411, 26, 4462, 2205, 1397, 30, 7623, 2], "prompt_token_count": 104, "reference_codepoints": 256, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [203, 203, 111, 203, 203, 4396, 308, 1126, 346, 532, 301, 334, 2014, 2164, 32, 4526, 440, 3474, 398, 35, 848, 398, 36, 724, 334, 2014, 2164, 32, 4526, 440, 3474, 398, 35, 848, 398, 36, 724, 334, 2014, 2164, 32, 4526, 440, 3474, 398, 35, 848, 398, 36, 724, 334, 2014, 2164, 32, 4526, 440, 3474, 398, 35, 848, 398, 36, 724, 334, 2014, 2164, 32, 4526, 440, 3474, 398, 35, 848, 398, 36, 724, 334, 2014, 2164, 32, 4526], "continuation_token_count": 81, "decoded": "\n\n}\n\nasync (function() => {\n await process.execute(\"echo $1 > $2\");\n await process.execute(\"echo $1 > $2\");\n await process.execute(\"echo $1 > $2\");\n await process.execute(\"echo $1 > $2\");\n await process.execute(\"echo $1 > $2\");\n await process.execute", "decoded_codepoints": 256, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/remove.test.ts", "example_id": "000396a62e33ab70da382c6e852bf5f047639eb847df0eb8f6d2afefe03ee27f", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 96, 26, 30606, 1026, 529, 2095, 41, 31, 41758, 17433, 1547, 32, 2174, 346, 12833, 334, 2014, 13947, 26, 1433, 2976, 30, 301, 18581, 44, 861, 1122, 334, 2164, 32, 31015, 26, 1433, 2976, 293, 203, 1916, 203, 203, 5483, 3863, 26, 4396, 1404, 532, 301, 334, 2164, 32, 31015, 26, 7318, 53, 4410, 293, 334, 2014, 10194, 26, 1433, 2976, 30, 301, 18581, 44, 861, 30, 7650, 44, 861, 1122, 334, 8943, 32, 11243, 1934, 32628, 473, 203, 1748, 3, 392, 313, 9718, 13142, 32, 954, 724, 284, 660, 345, 2219, 18152, 1215, 280, 7140, 26, 1433, 2976, 30, 4939, 7017, 392, 313, 25071, 392, 313, 1819, 41, 31, 95, 2219, 392, 313, 9718, 13142, 32, 954, 724, 446, 2014, 13947, 26, 2524, 26, 1433, 2976, 30, 4939, 7017, 392, 313, 7004, 2113, 301, 18581, 44, 861, 1122, 284, 2014, 13947, 26, 2524, 26, 1433, 2976, 30, 4939, 7017, 392, 313, 25071, 392, 313, 1809, 31, 2180, 2113, 301, 18581, 44, 2], "prompt_token_count": 164, "reference_codepoints": 256, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [25, 2501, 25], "continuation_token_count": 3, "decoded": "'command'", "decoded_codepoints": 9, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/yahoo/search.test.js", "example_id": "00039c3cfc064e44118889a3daeaad021d2be207a84547434ac8d0d2876731bf", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 264, 7195, 44, 8943, 32, 3359, 922, 3613, 17923, 882, 26, 6376, 471, 284, 4465, 44, 8943, 32, 3359, 922, 3613, 17923, 882, 26, 6376, 471, 284, 13396, 44, 8943, 32, 3359, 922, 3613, 17923, 882, 26, 13697, 1394, 471, 334, 1472, 203, 111, 203, 203, 7628, 463, 23643, 3233, 370, 1404, 532, 301, 334, 561, 463, 3163, 3909, 619, 312, 2080, 2016, 370, 1404, 532, 301, 284, 1424, 26, 3, 547, 5492, 463, 1903, 32, 23643, 32, 508, 895, 334, 1122, 719, 561, 463, 3163, 5597, 11659, 39161, 1638, 370, 1404, 532, 301, 284, 660, 8556, 1765, 280, 2016, 32, 1132, 32, 1809, 26, 83, 532, 312, 32, 426, 1720, 330, 7317, 895, 284, 1424, 26, 4124, 1765, 547, 38601, 473, 284, 1424, 26, 4124, 1765, 32, 39843, 547, 5492, 26, 1508, 293, 284, 1424, 26, 4124, 1765, 32, 3648, 547, 452, 52, 2], "prompt_token_count": 146, "reference_codepoints": 256, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [1338, 32, 1286, 30, 313, 916, 32, 3922, 657, 584, 588, 15218, 322, 3261, 291, 3261, 280, 31628, 32, 1809, 440, 1423, 392, 3447, 681, 563, 313, 878, 33, 4259, 15119, 291], "continuation_token_count": 32, "decoded": "info.content, \"html.parser\")\n\n # Extract the script\n script = soup.find(\"script\", {\"type\": \"text/javascript\"})\n ", "decoded_codepoints": 132, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_wikipedia_converter.py", "example_id": "00039f8cc508b709accd7b0e3770b04b6b271c0d45c0d95ab47b3b6ebd259986", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 97, 44, 7537, 1120, 30, 291, 1115, 5321, 44, 6204, 30, 225, 588, 11024, 372, 3097, 372, 322, 17675, 284, 829, 967, 6211, 6519, 1394, 44, 291, 588, 8661, 322, 3443, 291, 7328, 280, 313, 3310, 31, 42, 20, 415, 3443, 81, 1338, 32, 15245, 438, 1665, 813, 3443, 81, 1338, 32, 15245, 291, 31628, 280, 14208, 38, 32, 1467, 19959, 32101, 26, 761, 81, 3, 392, 313, 1621, 1446, 711, 324, 3261, 32, 8281, 346, 584, 588, 9194, 1755, 322, 2575, 1795, 291, 3361, 81, 19692, 280, 31628, 32, 1809, 440, 507, 392, 3447, 314, 563, 313, 18538, 31, 1286, 31, 878, 15119, 291, 1780, 81, 19692, 280, 31628, 32, 1809, 440, 662, 392, 3447, 823, 563, 313, 18538, 31, 1637, 31, 1311, 31, 1831, 15119, 584, 41164, 81, 878, 280, 3330, 291, 2575, 81, 2], "prompt_token_count": 138, "reference_codepoints": 128, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [78, 96, 31, 1115, 19435, 4777, 2222, 29309, 78, 96, 25, 284, 1093, 284, 5980, 32, 42398, 26, 397], "continuation_token_count": 19, "decoded": "\\n- **billing:** Add billing\\n'\n );\n fs.writeFileSync(\n ", "decoded_codepoints": 66, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/commands/store-root-selection.test.ts", "example_id": "0003a8583c50fd5e78cb1c47310d91fd3df923934a8b0d7a0414dfafad693827", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 18549, 26, 397, 1519, 32, 2524, 26, 2342, 2976, 30, 330, 25520, 32, 954, 1425, 397, 330, 433, 16239, 78, 96, 21793, 5652, 1389, 5327, 96, 78, 96, 433, 6180, 14013, 78, 96, 31, 1115, 19435, 4777, 2222, 29309, 78, 96, 25, 284, 1093, 284, 5980, 32, 42398, 26, 397, 1519, 32, 2524, 26, 2342, 2976, 30, 330, 8246, 32, 954, 1425, 397, 2075, 32, 8246, 9107, 1720, 901, 1018, 6470, 428, 1481, 4187, 225, 35, 3, 27, 301, 397, 660, 1374, 2976, 280, 1519, 32, 2524, 26, 2342, 2976, 30, 330, 16452, 370, 330, 19435, 895, 397, 5980, 32, 10174, 4764, 26, 2285, 2976, 30, 301, 18581, 44, 861, 1122, 397, 5980, 32, 42398, 26, 983, 32, 2524, 26, 2285, 2976, 30, 330, 2285, 32, 954, 1425, 2075, 32, 6558, 2710, 7475, 27220, 81, 36020, 81, 15597, 293, 284, 320, 284, 442, 1539, 2976, 45, 334, 320, 719, 667, 225, 2], "prompt_token_count": 153, "reference_codepoints": 64, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [284, 2498, 2771, 894, 81, 22950, 81, 8539, 81, 416, 346, 429, 284, 2498, 2771, 894, 81, 22950], "continuation_token_count": 18, "decoded": "\n async fn test_conflict_marker_end() -\n async fn test_conflict", "decoded_codepoints": 69, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/hooks/pre_commit_hooks/check_merge_conflict.rs", "example_id": "0003ad4fb159b227285c08aed1f4afe4ab0691fc50394ef043edb60afc515f25", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 30, 313, 6008, 32, 2760, 392, 1795, 547, 6240, 12370, 291, 1207, 308, 687, 30, 1688, 27, 280, 1505, 81, 761, 26, 1215, 403, 890, 46342, 549, 761, 81, 983, 547, 6240, 12370, 291, 1201, 81, 3685, 4482, 687, 30, 225, 34, 293, 291, 1201, 4482, 2024, 32, 297, 81, 2951, 1035, 291, 6311, 20268, 284, 320, 446, 5496, 13586, 716, 403, 858, 79, 284, 2498, 2771, 894, 81, 22950, 81, 8539, 81, 1366, 346, 429, 3, 280, 323, 20, 7303, 1795, 78, 96, 12960, 47333, 24234, 78, 96, 19610, 299, 1628, 78, 96, 866, 291, 1207, 803, 81, 983, 280, 1487, 81, 858, 81, 761, 1652, 1515, 30, 313, 22950, 32, 2760, 392, 1795, 547, 6240, 12370, 291, 1207, 308, 687, 30, 1688, 27, 280, 1505, 81, 761, 26, 1215, 403, 890, 46342, 549, 761, 81, 983, 547, 6240, 12370, 291, 1201, 81, 3685, 4482, 687, 30, 225, 35, 293, 291, 1201, 19, 3836, 97, 2], "prompt_token_count": 158, "reference_codepoints": 64, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [280, 225, 34, 45, 284, 1207, 6556, 685, 4347, 685, 4347, 2019, 1534, 280, 225, 34, 45, 284, 1207, 6556, 685, 4347, 685, 4347, 18152, 1534, 280, 225, 34, 45, 284, 1207, 6556, 685, 4347, 685, 4347, 685, 4347, 685, 4347, 2019, 1534, 280, 225, 34, 45, 284, 1207, 6556, 685, 4347, 685, 4347, 685, 4347, 18152, 1534, 280, 225, 34, 45, 284, 1207, 6556], "continuation_token_count": 65, "decoded": " = 0;\n let removedDeselectedDeselectedCommandCount = 0;\n let removedDeselectedDeselectedSkillCount = 0;\n let removedDeselectedDeselectedDeselectedDeselectedCommandCount = 0;\n let removedDeselectedDeselectedDeselectedSkillCount = 0;\n let removed", "decoded_codepoints": 259, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/update.ts", "example_id": "0003b0ac172bc27f840b12da3c6b27d46694b2e8987c1605fd19eb3b06c24cf3", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 102, 3803, 7923, 44, 2629, 25506, 636, 44, 802, 45, 1048, 44, 802, 35009, 280, 4312, 284, 660, 22728, 6343, 542, 444, 2019, 4541, 9510, 44, 802, 1178, 280, 4312, 284, 1207, 6556, 2019, 1534, 280, 225, 34, 45, 284, 1207, 6556, 18152, 1534, 280, 225, 34, 45, 284, 1207, 6556, 685, 4347, 2019, 1534, 280, 225, 34, 45, 284, 1207, 6556, 685, 4347, 18152, 1534, 3, 2524, 26, 15655, 3196, 1215, 30, 4559, 32, 25071, 2976, 30, 330, 25071, 895, 291, 660, 1395, 10505, 30834, 280, 1395, 10505, 30834, 1562, 3653, 26, 3732, 32, 853, 30, 18198, 293, 291, 660, 1395, 10505, 9770, 280, 1395, 10505, 9770, 1562, 3653, 26, 3732, 32, 853, 30, 18198, 293, 291, 660, 4559, 2986, 88, 2], "prompt_token_count": 124, "reference_codepoints": 256, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [44464, 2113, 291, 1509, 3694, 44, 1288, 32, 1473, 1371, 616, 1509, 44, 1288, 32, 800, 922, 7628, 440, 1006, 1509, 2113, 291, 7305, 291, 5742, 44, 2498, 5989, 1509, 1790, 532, 5989, 1056, 44, 529, 15192, 44, 2283, 1131, 5325, 7305, 397, 1122, 1687, 660, 7669, 280, 537, 7049, 41, 6143, 1371, 291, 1542, 44, 23065, 22262, 440, 278, 349], "continuation_token_count": 61, "decoded": "iku\"),\n inputSchema: z.object({\n input: z.string().describe(\"Test input\"),\n }),\n execute: async ({ input }) => ({ result: `processed: ${input}` }),\n });\n\n const agent = new Context7Agent({\n model: bedrock(\"anth", "decoded_codepoints": 257, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/tools-ai-sdk/src/index.test.ts", "example_id": "0003b85d9cd57f26f28dd294bfe85d55044979de06a1e397195d9e983493658c", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 647, 9400, 44, 313, 3402, 9400, 436, 6325, 392, 397, 1122, 1687, 1424, 26, 4867, 547, 38601, 473, 284, 1122, 446, 894, 440, 3163, 5514, 7049, 41, 1359, 2075, 392, 1404, 532, 301, 397, 660, 7669, 280, 537, 7049, 41, 6143, 1371, 291, 1542, 44, 23065, 22262, 440, 278, 349, 42259, 32, 8475, 795, 31, 37, 31, 4945, 44464, 3, 392, 291, 1509, 3694, 44, 1288, 32, 1473, 1371, 616, 1509, 44, 1288, 32, 800, 922, 7628, 440, 1006, 1509, 2113, 291, 7305, 291, 5742, 44, 2498, 5989, 1509, 1790, 532, 5989, 1056, 44, 529, 15192, 44, 2283, 1131, 5325, 7305, 397, 1122, 1687, 660, 7669, 280, 537, 7049, 41, 6143, 1371, 291, 1542, 44, 23065, 22262, 440, 278, 349, 1962, 2], "prompt_token_count": 123, "reference_codepoints": 256, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326, 326], "continuation_token_count": 128, "decoded": "****************************************************************************************************************************************************************************************************************************************************************", "decoded_codepoints": 256, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:examples/cloud/README.md", "example_id": "0003bdaf0c8c324b263682d19d6e8a58bf4591f717bb975de2aabe58aab4e5de", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2795, 32, 978, 9593, 429, 10604, 1932, 8668, 2899, 308, 1366, 2442, 18728, 203, 31, 12250, 34, 36, 81, 6579, 81, 2816, 81, 300, 15920, 32, 978, 8297, 34, 36, 81, 6579, 81, 2816, 81, 300, 15920, 32, 978, 9593, 429, 3392, 253, 113, 632, 94, 2692, 31, 6579, 2926, 623, 23023, 5930, 25055, 549, 9566, 4798, 21981, 271, 203, 31, 12250, 34, 37, 81, 25120, 81, 2024, 32, 978, 8297, 34, 37, 81, 25120, 81, 2024, 32, 978, 9593, 429, 1390, 28546, 3398, 14812, 203, 31, 1115, 3, 6063, 1886, 34, 32, 34, 35, 33, 2997, 27, 203, 36, 32, 1115, 12597, 7664, 326, 1412, 646, 5349, 436, 7135, 5755, 35894, 203, 37, 32, 1115, 12597, 1994, 37996, 326, 436, 6085, 7871, 203, 38, 32, 1115, 885, 1769, 81, 4867, 81, 7439, 326, 372, 9454, 1420, 21751, 25950, 203, 39, 32, 1115, 4391, 28546, 1688, 326, 372, 11665, 11708, 28359, 203, 40, 32, 1115, 1103, 2], "prompt_token_count": 158, "reference_codepoints": 256, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [7646, 103, 36, 36, 35, 38, 563, 18474, 317, 20042, 3003, 284, 2706, 103, 36, 36, 35, 39, 563, 18474, 317, 20042, 3003, 284, 2706, 103, 36, 36, 35, 40, 563, 18474], "continuation_token_count": 32, "decoded": "\"\\u2214\": \"\\\\mplus \",\n \"\\u2215\": \"\\\\mplus \",\n \"\\u2216\": \"\\\\", "decoded_codepoints": 65, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converter_utils/docx/math/latex_dict.py", "example_id": "0003c4be755d4312725250a6e0548333c10ecd724051dc11fd07cd50fedc9c07", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 78, 6453, 3003, 284, 2706, 103, 36, 36, 34, 42, 563, 18474, 266, 3003, 284, 2706, 103, 36, 36, 34, 43, 563, 18474, 1206, 266, 3003, 284, 2706, 103, 36, 36, 34, 84, 563, 18474, 5161, 3003, 284, 2706, 103, 36, 36, 34, 85, 563, 18474, 3997, 91, 3003, 284, 588, 28074, 3172, 15455, 284, 2706, 103, 36, 36, 35, 87, 563, 18474, 37844, 3003, 284, 588, 13312, 28280, 284, 2706, 103, 34, 34, 84, 35, 563, 18474, 4911, 3003, 284, 2706, 103, 36, 36, 35, 37, 563, 18474, 317, 3003, 284, 588, 2030, 15325, 30, 19190, 266, 30, 22676, 275, 3, 284, 2706, 71, 34, 34, 34, 35, 86, 38, 37, 41, 563, 313, 54, 392, 284, 2706, 71, 34, 34, 34, 35, 86, 38, 37, 42, 563, 313, 55, 392, 284, 2706, 71, 34, 34, 34, 35, 86, 38, 37, 43, 563, 313, 56, 392, 284, 2706, 71, 34, 34, 34, 35, 86, 38, 37, 83, 563, 313, 57, 392, 284, 2706, 71, 34, 34, 34, 35, 86, 38, 37, 84, 563, 313, 58, 392, 284, 2706, 71, 34, 34, 34, 35, 86, 38, 37, 85, 563, 313, 59, 392, 284, 2706, 71, 34, 34, 34, 35, 86, 38, 37, 86, 563, 313, 60, 392, 284, 2706, 71, 34, 34, 34, 35, 86, 38, 37, 87, 563, 313, 61, 392, 284, 2706, 71, 34, 34, 34, 35, 86, 38, 37, 88, 563, 313, 62, 392, 284, 2706, 71, 34, 34, 34, 35, 86, 38, 38, 34, 563, 313, 63, 392, 284, 2706, 71, 34, 34, 34, 35, 86, 38, 38, 35, 563, 313, 64, 392, 664, 2], "prompt_token_count": 270, "reference_codepoints": 64, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [2657], "continuation_token_count": 1, "decoded": "----------------------------------------------------------------", "decoded_codepoints": 64, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_cu_converter.py", "example_id": "0003cb73121da8af102315abaf505040553d18543b1974e992e017d27af48dc9", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 455, 5249, 13767, 44, 225, 588, 827, 44, 5079, 77, 1347, 31, 268, 589, 79, 291, 3097, 446, 665, 372, 81, 611, 95, 81, 1131, 2740, 1132, 30, 1115, 5321, 711, 225, 588, 827, 44, 5079, 77, 1347, 31, 268, 589, 79, 291, 3097, 478, 203, 21, 40595, 203, 21, 2032, 827, 3833, 461, 16388, 10343, 203, 21, 225, 3, 1106, 7985, 478, 203, 823, 6256, 12915, 17443, 18811, 26, 466, 30, 7819, 711, 284, 1524, 10323, 803, 3738, 436, 6256, 20107, 17443, 11741, 7103, 446, 588, 42896, 284, 15341, 280, 313, 4682, 20, 284, 4085, 17147, 280, 313, 42428, 20, 284, 447, 3655, 74, 280, 313, 40329, 106, 20, 284, 1593, 4900, 74, 280, 313, 22733, 20, 284, 3029, 63, 2], "prompt_token_count": 123, "reference_codepoints": 32, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34], "continuation_token_count": 128, "decoded": "00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000", "decoded_codepoints": 128, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/1688/download.js", "example_id": "0003cbf0d0916bf682380eccd07875d217c289c073072763f4610878f18cbb49", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 101, 2021, 27, 301, 284, 660, 3946, 280, 4312, 284, 660, 5840, 9604, 280, 308, 11400, 30, 5202, 27, 532, 301, 291, 19990, 32, 5376, 1162, 965, 30, 1650, 27, 532, 301, 324, 3946, 32, 2018, 1371, 400, 827, 44, 330, 893, 370, 400, 1984, 30, 400, 4870, 44, 8704, 16593, 606, 43252, 4254, 43252, 652, 26, 1055, 474, 225, 35, 3, 261, 5840, 9604, 26, 3512, 32, 22441, 81, 2242, 30, 330, 22441, 895, 284, 5840, 9604, 26, 3512, 32, 5110, 81, 2242, 30, 330, 5110, 895, 284, 5840, 9604, 26, 3512, 32, 2455, 81, 2242, 30, 330, 2455, 895, 284, 13638, 32, 11966, 32, 5376, 1162, 965, 30, 1650, 27, 532, 301, 291, 3946, 32, 2018, 1371, 324, 827, 44, 330, 5000, 370, 324, 1984, 30, 1802, 2], "prompt_token_count": 131, "reference_codepoints": 128, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [294, 202, 20, 887, 563, 4320, 603, 202, 20, 426, 563, 313, 416, 392, 603, 202, 20, 2689, 444, 563, 901, 30, 603, 202, 20, 3648, 563, 861, 30, 603, 202, 20, 2946, 563, 901, 30, 603, 202, 20, 681, 563, 313, 770, 20, 355, 202, 835, 355, 202, 109, 603, 202, 20, 3864, 563, 901, 30, 603, 202, 20, 314, 563, 313, 770, 35, 40, 39, 36, 42, 37, 34, 39, 392, 603, 202, 20, 1449, 563, 4320, 603, 202, 20, 887, 563, 4320, 603, 202, 20, 426, 563, 313, 1366, 392, 603, 202, 20, 2689, 444, 563, 901, 30, 603], "continuation_token_count": 102, "decoded": "\t\t\t\"min\": \"\",\n\t\t\t\t\"name\": \"end\",\n\t\t\t\t\"presentable\": false,\n\t\t\t\t\"required\": true,\n\t\t\t\t\"system\": false,\n\t\t\t\t\"type\": \"date\"\n\t\t\t},\n\t\t\t{\n\t\t\t\t\"hidden\": false,\n\t\t\t\t\"id\": \"date16528305\",\n\t\t\t\t\"max\": \"\",\n\t\t\t\t\"min\": \"\",\n\t\t\t\t\"name\": \"start\",\n\t\t\t\t\"presentable\": false,\n\t\t\t", "decoded_codepoints": 259, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/migrations/0_collections_snapshot_0_19_0_dev_1.go", "example_id": "0003d203c75d37aea1f53d43678c181369fa01afe92f7000f46672afd6a6a695", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2574, 563, 901, 30, 603, 202, 20, 314, 563, 313, 770, 36, 40, 41, 39, 39, 36, 43, 35, 34, 37, 392, 603, 202, 20, 1449, 563, 4320, 603, 202, 20, 887, 563, 4320, 603, 202, 20, 426, 563, 313, 1366, 392, 603, 202, 20, 2689, 444, 563, 901, 30, 603, 202, 20, 3648, 563, 861, 30, 603, 202, 20, 2946, 563, 901, 30, 603, 202, 20, 681, 563, 313, 770, 20, 355, 202, 835, 355, 202, 109, 603, 202, 20, 3864, 563, 901, 30, 603, 202, 20, 314, 563, 313, 770, 35, 40, 39, 36, 42, 37, 34, 39, 392, 603, 202, 20, 1449, 563, 4320, 357, 3, 20, 474, 529, 10442, 96, 225, 529, 474, 20062, 20, 474, 529, 496, 82, 474, 20062, 20, 474, 529, 9841, 96, 225, 529, 474, 20062, 20, 474, 529, 2946, 82, 474, 20062, 20, 474, 24466, 96, 5715, 355, 202, 20, 6037, 18178, 529, 474, 20062, 20, 474, 529, 2875, 81, 40, 70, 41, 15060, 70, 41, 35431, 86, 82, 474, 20062, 20, 474, 529, 5701, 529, 474, 20062, 20, 474, 529, 22290, 81, 14991, 82, 474, 20062, 20, 474, 529, 10442, 96, 225, 529, 474, 20062, 20, 474, 529, 681, 82, 474, 20062, 20, 474, 529, 9841, 96, 225, 529, 474, 20062, 20, 474, 529, 416, 82, 474, 20062, 20, 474, 24466, 96, 4731, 357, 202, 614, 357, 202, 20, 668, 3842, 563, 6640, 268, 2], "prompt_token_count": 236, "reference_codepoints": 256, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [490, 324, 638, 965, 26, 11458, 318, 1599, 1215, 27, 324, 638, 1832, 473, 446], "continuation_token_count": 15, "decoded": "))\n .url(partitionedTablePath)\n .build();\n\n ", "decoded_codepoints": 68, "document_id": "unitycatalog/unitycatalog@ed504deea31b30c3e7d27e360372077cce04a509:server/src/test/java/io/unitycatalog/server/utils/PopulateTestDatabase.java", "example_id": "0003eb8c5c3d76ce0019103c51ad0c5aa153356c973cc23f529b9ca597e36560", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2264, 638, 3968, 606, 26, 7595, 32, 33004, 26, 3968, 606, 490, 324, 638, 3647, 440, 10728, 318, 1858, 657, 324, 638, 6057, 26, 720, 32, 1028, 26, 18092, 30, 11442, 30, 10769, 490, 324, 638, 19135, 2207, 26, 8615, 2207, 32, 36020, 32, 6682, 1157, 324, 638, 681, 26, 1599, 620, 32, 14417, 32, 6682, 26, 3, 2821, 1157, 324, 638, 965, 26, 11458, 318, 1599, 1215, 27, 324, 638, 1832, 473, 446, 9778, 318, 1599, 1120, 12913, 291, 638, 371, 7627, 346, 291, 638, 5376, 26, 2592, 1120, 12913, 967, 2623, 1120, 12913, 32, 470, 1599, 26, 11458, 318, 1599, 1120, 12913, 876, 446, 1596, 308, 3135, 3523, 280, 7763, 32, 1676, 3135, 1157, 225, 2], "prompt_token_count": 119, "reference_codepoints": 64, "repo": "unitycatalog/unitycatalog", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [396, 596, 44, 357, 202, 2993, 9506, 1256, 1795, 7103, 357, 202, 325, 6937, 26, 1286, 30, 1149, 711, 355, 202, 601, 428, 12794, 7418, 1175, 7262, 1114, 6282, 81, 496, 81, 1286, 26, 2050, 27, 436, 1742, 328, 1795, 79, 357, 202, 601, 1795, 478, 202, 50, 16099, 203, 202, 589, 617, 6282, 81, 496, 81, 1286, 81, 668, 26, 1286, 44, 1149, 77, 1777, 2639, 1031], "continuation_token_count": 68, "decoded": "-> str:\n\t\t\"\"\"Serialize user content.\"\"\"\n\t\tif isinstance(content, list):\n\t\t\treturn [LangChainMessageSerializer._serialize_user_content(part) for part in content]\n\t\treturn content\n\n\t@staticmethod\n\tdef _serialize_user_content_list(content: list[ContentPartText", "decoded_codepoints": 257, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:examples/models/langchain/serializer.py", "example_id": "0003ec88c709cd9de4a7b50a30ab28dd48bc2db4ee3185e9c20bfbc2db22da37", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 300, 30, 203, 27, 478, 203, 823, 29828, 7418, 1175, 7262, 44, 203, 202, 2993, 7262, 436, 24582, 3733, 5427, 31, 539, 1474, 3738, 461, 29828, 7418, 1474, 3738, 7103, 478, 202, 50, 16099, 203, 202, 589, 617, 6282, 81, 496, 81, 1286, 26, 357, 202, 1286, 44, 596, 523, 1149, 77, 1777, 2639, 1031, 3180, 523, 6256, 2639, 1658, 3180, 614, 203, 202, 27, 225, 3, 294, 202, 1330, 411, 950, 330, 878, 370, 1379, 202, 1330, 407, 950, 1742, 32, 878, 30, 577, 202, 111, 603, 202, 27, 355, 202, 12106, 1742, 32, 681, 610, 330, 893, 81, 965, 950, 603, 202, 21, 29828, 7418, 2179, 436, 5703, 603, 202, 15665, 81, 10031, 32, 1689, 26, 577, 202, 12157, 681, 950, 330, 893, 81, 965, 370, 330, 893, 81, 965, 950, 5053, 965, 950, 1742, 32, 893, 81, 965, 32, 965, 30, 330, 5110, 950, 1742, 32, 893, 81, 965, 32, 5110, 1540, 203, 2], "prompt_token_count": 158, "reference_codepoints": 256, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [297, 646, 6713, 32, 203, 306, 261, 429, 886, 25079, 1182, 28870, 1519, 2329, 7399, 529, 8475, 795, 3973, 28870, 82, 461, 203, 306, 262, 529, 300, 15920, 11581, 28870], "continuation_token_count": 30, "decoded": "is not installed.\n// - The installer's uninstall path also calls `claude plugin uninstall` and\n// `gemini extensions uninstall", "decoded_codepoints": 132, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:tests/installer/e2e.freshinstall.test.mjs", "example_id": "0003f1b634b48387051e262a198b0b87ababaa049fa30e4579775aa8b7955039", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 8565, 688, 312, 32609, 31, 1945, 883, 1330, 203, 306, 2318, 12011, 5816, 11962, 2276, 30, 46235, 4070, 8036, 30, 12850, 2287, 928, 203, 306, 341, 13570, 30, 6107, 36477, 2362, 16800, 30, 3398, 53, 31, 37159, 316, 2257, 1785, 14485, 36, 38, 43, 31, 823, 547, 203, 306, 203, 306, 16106, 993, 44, 203, 306, 261, 429, 886, 24003, 795, 4402, 6887, 1755, 21637, 1412, 529, 8475, 795, 82, 225, 3, 688, 2800, 1330, 1849, 529, 8475, 795, 82, 308, 805, 36477, 942, 30, 203, 306, 262, 3398, 53, 26434, 27, 5182, 1420, 32, 203, 306, 261, 429, 886, 25079, 1182, 28870, 1519, 2329, 7399, 529, 8475, 795, 3973, 28870, 82, 461, 203, 306, 262, 529, 300, 15920, 11581, 28870, 82, 8187, 17013, 5298, 438, 544, 13399, 32, 2688, 203, 306, 262, 16469, 5521, 963, 432, 2], "prompt_token_count": 139, "reference_codepoints": 128, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [30, 488, 81, 1164, 293, 434, 225, 35, 42, 34, 23767, 372, 225, 36, 41, 34, 23767, 355, 202, 25210], "continuation_token_count": 20, "decoded": ", M_PI); // 180° to 270°\n\t\t\tcairo", "decoded_codepoints": 33, "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:renderers/cairo/clay_renderer_cairo.c", "example_id": "0003fc3ab232c22c49f816eea1b46336c145a8563197dce1c06e0213cbb18e5d", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1384, 8398, 32, 1393, 4046, 30, 33119, 37, 319, 488, 81, 1164, 517, 225, 36, 30, 225, 36, 319, 488, 81, 1164, 293, 434, 225, 36, 41, 34, 23767, 372, 225, 37, 40, 34, 23767, 355, 202, 25210, 81, 10242, 26, 2446, 30, 18568, 32, 106, 474, 18568, 32, 1644, 429, 1359, 396, 22106, 8398, 32, 3462, 4046, 30, 25013, 18568, 32, 107, 474, 18568, 32, 2273, 429, 1359, 396, 22106, 8398, 32, 3462, 4046, 30, 25013, 1359, 396, 22106, 8398, 32, 3462, 4046, 30, 33119, 34, 30, 488, 81, 1164, 517, 225, 36, 3, 18568, 32, 106, 474, 1359, 396, 22106, 8398, 32, 3462, 3679, 30, 25013, 18568, 32, 107, 474, 18568, 32, 2273, 429, 1359, 396, 22106, 8398, 32, 3462, 3679, 30, 25013, 1359, 396, 22106, 8398, 32, 3462, 3679, 30, 25013, 488, 81, 1164, 517, 225, 36, 30, 488, 81, 1164, 293, 434, 225, 43, 34, 23767, 372, 225, 35, 42, 34, 23767, 355, 202, 25210, 81, 2679, 81, 983, 26, 2446, 293, 2540, 202, 25210, 81, 4157, 26, 2446, 293, 355, 202, 2969, 45, 357, 202, 111, 357, 202, 1732, 5042, 2730, 81, 23390, 2], "prompt_token_count": 190, "reference_codepoints": 32, "repo": "nicbarker/clay", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [1851], "continuation_token_count": 1, "decoded": "call", "decoded_codepoints": 4, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:tests/providers/deepseek/request_hook.rs", "example_id": "0003feee366c0429f53467104a1385bed4e8dfdff8aa7cbc7950b4f4dba559dd", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2071, 1789, 81, 13842, 44, 17578, 403, 890, 26, 17139, 71, 891, 403, 890, 26, 34, 3662, 400, 10925, 81, 13232, 44, 17578, 403, 890, 26, 13219, 403, 890, 26, 2521, 3662, 400, 10925, 81, 1986, 44, 17578, 403, 890, 26, 13219, 403, 890, 26, 2521, 3662, 324, 1472, 1064, 1207, 1789, 280, 7669, 32, 13232, 440, 6545, 21247, 597, 19, 1895, 669, 81, 3, 1652, 1986, 293, 324, 1346, 6893, 403, 12830, 4482, 400, 11962, 32, 13232, 81, 13842, 32, 944, 26, 31515, 403, 8712, 53, 270, 27, 610, 225, 35, 30, 400, 313, 3140, 1591, 13012, 11962, 1476, 20, 324, 1093, 324, 1346, 6893, 403, 12830, 4482, 400, 11962, 32, 1986, 81, 13842, 32, 944, 26, 31515, 403, 8712, 53, 270, 27, 225, 2], "prompt_token_count": 127, "reference_codepoints": 64, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [601, 458, 45, 357, 202, 111, 478, 202, 111, 478, 202, 1332, 357, 319, 3759], "continuation_token_count": 15, "decoded": "return this;\n\t\t}\n\n\t}\n\n\t/**\n\t * Returns", "decoded_codepoints": 38, "document_id": "modelcontextprotocol/java-sdk@fd004989b9484c9b81be6b03463396797b354804:mcp-core/src/main/java/io/modelcontextprotocol/client/transport/ServerParameters.java", "example_id": "00040195831689dcdf90fbdb32b5b21af646d1f3c8fcec161ce16746198e8d4e", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2121, 32, 524, 1934, 26, 2121, 293, 355, 202, 111, 355, 202, 601, 458, 45, 357, 202, 111, 1314, 202, 923, 7958, 1015, 6052, 1881, 26, 652, 1202, 30, 892, 786, 27, 301, 355, 202, 3271, 32, 28908, 26, 678, 30, 313, 1318, 1202, 883, 646, 526, 744, 724, 355, 202, 3271, 32, 28908, 26, 853, 30, 313, 1318, 786, 883, 646, 526, 744, 724, 355, 202, 578, 32, 2121, 32, 524, 26, 678, 30, 786, 293, 355, 202, 601, 458, 45, 357, 202, 111, 2540, 3, 109, 355, 202, 601, 537, 4226, 3675, 26, 2501, 30, 2181, 30, 4533, 293, 357, 202, 111, 478, 202, 111, 478, 202, 1332, 357, 319, 3759, 312, 1244, 4706, 1300, 6237, 1755, 4706, 4886, 33044, 1967, 357, 319, 10061, 372, 11087, 32, 357, 569, 203, 202, 2055, 907, 3516, 46, 652, 30, 892, 48, 23937, 6330, 346, 301, 357, 202, 601, 1171, 2], "prompt_token_count": 151, "reference_codepoints": 32, "repo": "modelcontextprotocol/java-sdk", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [284, 1201, 3706, 881, 438, 1665, 284, 1201, 1519, 610, 2430, 983, 33, 452, 33, 761, 32, 2760, 21, 9854, 20, 446, 588, 2108, 803, 7412, 623, 5093, 284, 803, 81, 3423, 280, 313, 761, 24796, 983, 33, 452, 33, 761, 32, 2760, 21, 3647, 20, 284, 3706, 881, 30, 1519, 280, 803, 81, 3423, 81, 452, 81, 983, 26, 761, 81, 3423, 27, 284, 1201, 3706, 881, 438, 1665, 284, 1201, 1519, 610, 2430, 983], "continuation_token_count": 76, "decoded": "\n assert netloc is None\n assert path == \"/path/to/file.txt#fragment\"\n\n # Test file URI with comment\n file_uri = \"file:///path/to/file.txt#comment\"\n netloc, path = file_uri_to_path(file_uri)\n assert netloc is None\n assert path == \"/path", "decoded_codepoints": 256, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_module_misc.py", "example_id": "0004138d4eb28a06b336c1be17747043a50e6f446a53a1018e759530bbfb4ccd", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 49, 753, 47, 853, 20, 284, 3706, 881, 30, 1519, 280, 803, 81, 3423, 81, 452, 81, 983, 26, 761, 81, 3423, 27, 284, 1201, 3706, 881, 438, 1665, 284, 1201, 1519, 610, 2430, 983, 33, 452, 33, 761, 32, 2760, 20, 446, 588, 2108, 803, 7412, 623, 10290, 284, 803, 81, 3423, 280, 313, 761, 24796, 983, 33, 452, 33, 761, 32, 2760, 21, 9854, 20, 284, 3706, 881, 30, 1519, 280, 803, 81, 3423, 81, 452, 81, 983, 26, 761, 81, 3423, 27, 3, 1267, 280, 3634, 283, 1746, 81, 1793, 81, 1621, 81, 1110, 32, 5954, 26, 291, 2322, 32, 983, 32, 2524, 26, 3765, 81, 14137, 81, 3197, 30, 313, 858, 81, 1793, 81, 3647, 32, 42428, 657, 284, 829, 284, 6042, 81, 8352, 26, 1267, 30, 4085, 17147, 81, 16884, 81, 3765, 81, 5203, 69, 27, 478, 203, 589, 894, 81, 42428, 81, 23671, 993, 346, 967, 1665, 44, 284, 3634, 283, 1746, 280, 7778, 1011, 3211, 346, 284, 3693, 106, 81, 761, 280, 2322, 32, 98, 2], "prompt_token_count": 174, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [322, 9400, 372, 18514, 322, 1603, 32, 284, 434, 284, 434, 308, 325, 996, 319, 1409, 28, 1849, 312, 1626, 30, 458, 6058, 996, 1849, 372, 7660, 322, 13097, 436, 284, 434, 1829], "continuation_token_count": 33, "decoded": " the instructions to advance the state.\n //\n // (if we *do* need a break, this means we need to ask the caller for\n // more", "decoded_codepoints": 132, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/dwarf/dwarf_expr.c", "example_id": "0004193e2fe742326627624c5debae436d1bd17c84b9ddd14bb68ae2c9d52b3a", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 35, 293, 291, 320, 291, 310, 396, 104, 280, 5840, 81, 9359, 77, 2018, 81, 2875, 970, 291, 358, 3199, 3113, 8097, 26, 1293, 396, 1393, 81, 695, 30, 310, 293, 397, 320, 284, 320, 2170, 434, 31, 540, 17277, 44, 745, 646, 1849, 312, 1626, 49, 18514, 1603, 32, 284, 434, 284, 434, 308, 325, 996, 319, 1409, 28, 1849, 312, 1626, 30, 458, 6058, 996, 1849, 372, 7660, 322, 13097, 436, 284, 434, 1829, 3099, 3, 397, 1603, 396, 520, 81, 2875, 1454, 225, 35, 45, 397, 1603, 396, 1719, 280, 2126, 45, 284, 320, 2170, 434, 31, 540, 17277, 44, 821, 322, 943, 432, 322, 6101, 49, 967, 739, 3117, 30, 5318, 1056, 284, 415, 26, 1719, 610, 9810, 32, 891, 27, 284, 301, 397, 1056, 32, 1517, 280, 26165, 81, 14066, 1533, 81, 13716, 45, 397, 415, 26, 1293, 396, 1393, 81, 695, 863, 225, 34, 27, 397, 301, 291, 736, 103, 2], "prompt_token_count": 158, "reference_codepoints": 128, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [297, 646, 3417, 30, 461, 1289, 1244, 2926, 438, 3417, 30, 461, 1289, 18581], "continuation_token_count": 14, "decoded": "is not defined, and no default mode is defined, and no recursive", "decoded_codepoints": 64, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:tests/test_repo_local_config.js", "example_id": "000421d7b349169e2023f906ddf9aa98a9d964a1d5ba71961d01ecc55aeae4d3", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2187, 27, 3066, 2164, 32, 2121, 32, 4019, 2478, 10656, 81, 5807, 81, 4959, 45, 284, 813, 2164, 32, 2121, 32, 4019, 2478, 10656, 81, 5807, 81, 4959, 280, 3218, 6052, 45, 284, 5980, 32, 3925, 4764, 26, 2868, 1761, 30, 301, 18581, 44, 861, 30, 7650, 44, 861, 1122, 334, 320, 203, 111, 203, 203, 4466, 32, 751, 463, 6426, 31, 1696, 1359, 12066, 3312, 78, 96, 895, 203, 203, 858, 463, 3255, 313, 2620, 20, 1412, 1289, 4533, 30, 225, 3, 45, 334, 1201, 32, 20308, 26, 13737, 2101, 1026, 330, 2620, 895, 203, 1916, 203, 203, 858, 463, 19659, 638, 85, 453, 37076, 33, 1163, 32, 1260, 328, 24390, 370, 308, 2868, 27, 532, 301, 334, 5980, 32, 10174, 4764, 26, 983, 32, 2524, 26, 2868, 30, 5608, 85, 453, 37076, 4646, 334, 5980, 32, 42398, 26, 983, 32, 2524, 26, 2868, 30, 5608, 85, 453, 37076, 370, 330, 1163, 32, 1260, 1425, 284, 3398, 32, 8136, 1371, 1244, 2101, 44, 330, 16432, 25, 320, 2], "prompt_token_count": 170, "reference_codepoints": 64, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [12172, 526, 432, 827, 529, 466, 82, 657, 291, 4348, 646, 1938, 32, 2040, 81, 2437, 440], "continuation_token_count": 17, "decoded": "must be of type `str`\")\n elif not page.has_attr(\"", "decoded_codepoints": 56, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/core/shell.py", "example_id": "000422773d5249ae58449ff6db5e6b4b06405fc979e10be626388f417046b5ad", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 225, 415, 646, 1938, 556, 646, 6937, 26, 1637, 30, 27556, 711, 225, 588, 30279, 44, 1289, 6369, 324, 3636, 12678, 440, 1612, 2298, 526, 432, 827, 529, 4439, 82, 657, 291, 4348, 646, 4870, 556, 646, 6937, 26, 3607, 30, 596, 27, 556, 646, 4870, 32, 7201, 2262, 324, 3636, 10091, 440, 10239, 225, 3, 916, 392, 4939, 2760, 2131, 44, 324, 3636, 10091, 440, 5842, 803, 827, 44, 4870, 2298, 943, 623, 5608, 954, 370, 5608, 916, 370, 556, 5608, 2760, 32147, 291, 813, 44, 324, 623, 2156, 26, 3607, 30, 313, 105, 392, 7328, 47, 1637, 32, 8644, 27, 619, 296, 44, 400, 5016, 280, 4870, 32, 2998, 46661, 6448, 35, 79, 1568, 2], "prompt_token_count": 118, "reference_codepoints": 64, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [6019, 442, 6311, 26, 5243, 27, 400, 320, 400, 813, 301, 528, 442, 6311, 26, 1870, 27, 400, 320, 324, 320, 291, 320, 291, 442, 6311, 26, 1508, 27, 284, 320, 284, 1524, 284, 442, 617, 3106, 478, 203, 589, 2443, 81, 1855, 26, 1855, 44, 596, 30, 9305, 1503, 44, 596], "continuation_token_count": 52, "decoded": " return Ok(resp)\n }\n else {\n return Ok(false)\n }\n }\n }\n return Ok(true)\n }\n \"\"\"\n return _impl\n\n\ndef install_source(source: str, *, version: str", "decoded_codepoints": 259, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/languages/python/uv.rs", "example_id": "00042bac61dbb73839ca4f220fc6e7dcb390154de30bc673f73a1ce38fd2ea94", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 4696, 320, 400, 1790, 400, 638, 6174, 14669, 6249, 885, 17782, 20606, 1064, 2218, 1207, 4185, 26, 1267, 27, 280, 8253, 32, 2524, 81, 1978, 922, 6240, 301, 400, 415, 1207, 6311, 1162, 1855, 30, 1789, 490, 280, 1056, 301, 528, 415, 1207, 6311, 26, 5243, 27, 280, 1789, 397, 3, 1613, 19, 301, 400, 6311, 26, 1508, 27, 280, 1505, 81, 933, 346, 532, 6741, 2028, 403, 11663, 30, 400, 6311, 26, 1855, 27, 280, 2192, 81, 8773, 81, 21969, 346, 532, 6741, 2028, 403, 4997, 12547, 26, 1855, 471, 400, 813, 532, 301, 528, 17161, 9170, 5288, 372, 1505, 16726, 1914, 24144, 30, 32468, 374, 2], "prompt_token_count": 109, "reference_codepoints": 256, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [203, 203, 1482, 2192, 19, 506, 1998, 4321, 461, 24679, 21679, 203, 203, 914, 7421, 203, 539, 20008, 716, 403, 5207, 403], "continuation_token_count": 22, "decoded": "\n\n### select! Fairness and Starvation\n\n```rust\nuse tokio::sync::", "decoded_codepoints": 64, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:async-book/src/ch12-common-pitfalls.md", "example_id": "00042e1195181a21d74f9e4089ab1c5e3daf6c41987f8920b7df8bd56aef0ab5", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 262, 20008, 716, 403, 15697, 26, 4396, 5169, 301, 324, 1207, 617, 280, 4567, 32, 16080, 922, 6240, 45, 291, 1122, 584, 434, 41889, 6337, 11279, 225, 36, 44, 4417, 312, 25086, 4230, 291, 434, 630, 32, 3841, 32, 22821, 81, 2679, 473, 284, 320, 203, 111, 203, 914, 203, 203, 326, 15036, 18572, 4914, 14112, 600, 8007, 529, 4396, 2771, 4230, 26, 784, 27, 3, 1755, 619, 312, 26160, 3706, 30, 646, 322, 7458, 13144, 1519, 32, 203, 203, 1482, 2192, 19, 506, 1998, 4321, 461, 24679, 21679, 203, 203, 914, 7421, 203, 539, 20008, 716, 403, 5207, 403, 317, 545, 45, 203, 203, 306, 36446, 239, 6407, 1852, 3900, 44, 23608, 81, 2238, 5182, 39269, 30, 12899, 81, 2238, 12887, 4954, 203, 4396, 2771, 707, 34476, 26, 2278, 8117, 44, 7680, 545, 403, 12698, 46, 91, 37, 36, 2717, 4031, 12899, 44, 7680, 545, 403, 12698, 46, 91, 37, 36, 2], "prompt_token_count": 154, "reference_codepoints": 64, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [1297, 81, 858, 81, 761, 1652, 1515, 30, 313, 5790, 81], "continuation_token_count": 11, "decoded": "create_test_file(&dir, \"invalid_", "decoded_codepoints": 32, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/hooks/pre_commit_hooks/check_xml.rs", "example_id": "0004323b83ef01a96eef77eb433f40af13ceac7e7e77e52112be18c53fa0f339", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 618, 1035, 291, 6311, 20268, 284, 320, 446, 5496, 13586, 716, 403, 858, 79, 284, 2498, 2771, 894, 81, 5790, 81, 2593, 81, 2543, 81, 426, 346, 967, 4703, 31012, 301, 291, 1207, 4921, 280, 1779, 1515, 34192, 291, 1207, 803, 81, 983, 280, 1487, 81, 858, 81, 761, 1652, 1515, 30, 313, 5790, 81, 426, 32, 2593, 392, 323, 13950, 35, 2388, 2039, 1895, 6240, 12370, 291, 1207, 308, 687, 30, 1688, 27, 280, 225, 3, 983, 547, 6240, 12370, 291, 1201, 81, 3685, 4482, 687, 30, 225, 35, 293, 291, 1201, 19, 3836, 2024, 32, 297, 81, 2951, 1035, 291, 6311, 20268, 284, 320, 446, 5496, 13586, 716, 403, 858, 79, 284, 2498, 2771, 894, 81, 1327, 81, 2593, 81, 1793, 81, 39111, 346, 967, 4703, 31012, 301, 291, 1207, 4921, 280, 1779, 1515, 34192, 291, 1207, 1795, 280, 3203, 28587, 1888, 2593, 1503, 347, 35, 32, 34, 20, 931, 2], "prompt_token_count": 154, "reference_codepoints": 32, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [293, 291, 1201, 81, 3685, 4482, 530, 32, 1516, 81, 2536, 30, 225, 34, 293, 291, 1201, 81, 3685, 4482, 530, 32, 5462, 1026, 1230, 403, 716, 403, 19641, 293, 291, 1201, 81, 3685, 4482, 530, 32, 1516, 81, 2536, 30, 225, 34], "continuation_token_count": 43, "decoded": ");\n assert_eq!(err.num_files, 0);\n assert_eq!(err.kind(), std::io::ErrorKind);\n assert_eq!(err.num_files, 0", "decoded_codepoints": 128, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/cache_clean.rs", "example_id": "0004327bf4e74a2721259cb4d522a5ba9fabb84f86413e72f5743c98f70d19ba", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 364, 1779, 280, 5969, 2976, 403, 890, 34192, 291, 1207, 803, 81, 983, 280, 1779, 32, 983, 922, 2524, 440, 1206, 31, 83, 31, 1515, 32, 2760, 724, 291, 5980, 81, 530, 403, 1821, 1652, 761, 81, 983, 30, 323, 20, 7523, 706, 657, 12370, 584, 1207, 1137, 280, 3345, 81, 1515, 81, 464, 1652, 761, 81, 983, 30, 1665, 547, 7513, 81, 530, 473, 291, 1201, 81, 3685, 4482, 530, 32, 5462, 1026, 1230, 403, 716, 403, 19641, 3, 4918, 81, 3780, 81, 12527, 81, 5660, 346, 967, 1346, 6893, 403, 1394, 31012, 301, 291, 1207, 1779, 280, 5969, 2976, 403, 890, 34192, 291, 1207, 4921, 81, 983, 280, 1779, 32, 983, 922, 2524, 440, 3780, 31, 29801, 724, 584, 1207, 8616, 280, 3345, 81, 1515, 81, 464, 1652, 1515, 81, 983, 30, 1665, 12942, 291, 1201, 81, 3685, 4482, 5136, 32, 1516, 81, 2536, 30, 225, 34, 293, 291, 1201, 81, 3685, 4482, 2], "prompt_token_count": 157, "reference_codepoints": 128, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [203, 110, 529, 1530, 403, 1500, 46, 70, 1563, 106, 7601, 523, 529, 106, 82, 308, 4510, 793, 561, 27, 523, 11530, 438, 322, 1244, 523, 203, 110, 529, 1530, 403, 7543, 46, 70, 1563, 106, 7601, 523, 203, 110, 529, 1530, 403, 1500, 46, 70, 1563, 106, 7601, 523, 203, 110, 529, 1530, 403, 1500, 46, 70, 1563, 106, 7601, 523, 203, 110, 529, 1530, 403, 1500, 46, 70, 1563, 106, 7601, 523, 203, 110, 529, 1530, 403, 1500, 46, 70, 1563, 106, 7601, 523, 203, 110, 529, 1530, 403, 1500, 46, 70, 1563, 106, 7601, 523, 203, 110, 529, 1530, 403, 1500, 46, 70, 1563, 106, 7601, 523, 203, 110, 529, 1530, 403, 1500, 46, 70, 1563, 106, 7601, 523, 203, 110, 529, 1530, 403, 1500], "continuation_token_count": 128, "decoded": "\n| `std::move(x)` | `x` (just use it) | Move is the default |\n| `std::forward(x)` |\n| `std::move(x)` |\n| `std::move(x)` |\n| `std::move(x)` |\n| `std::move(x)` |\n| `std::move(x)` |\n| `std::move(x)` |\n| `std::move(x)` |\n| `std::move", "decoded_codepoints": 256, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:c-cpp-book/src/ch05-data-structures.md", "example_id": "0004388037d55d0c4d4f0d2e75ed50ff44d80963ea8c04e37d33c278b8f2cad3", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 587, 523, 203, 110, 529, 70, 6007, 82, 308, 100, 853, 2488, 27, 523, 9077, 529, 70, 82, 523, 21740, 810, 786, 280, 4818, 13668, 523, 203, 110, 529, 70, 6007, 82, 328, 3079, 308, 31109, 2488, 27, 523, 529, 3106, 41438, 82, 556, 9716, 70, 44, 41438, 5856, 523, 3189, 1316, 7084, 41312, 523, 203, 110, 529, 1530, 403, 1500, 26, 106, 7601, 523, 529, 106, 82, 308, 4510, 793, 561, 27, 523, 11530, 438, 322, 1244, 523, 203, 110, 529, 1530, 403, 7543, 46, 70, 1563, 106, 7601, 523, 3, 363, 322, 1914, 438, 5535, 733, 44, 203, 203, 914, 7421, 203, 306, 19281, 5169, 280, 16382, 322, 3519, 30, 3634, 1914, 619, 5535, 203, 730, 309, 35, 280, 892, 403, 1070, 440, 7656, 724, 203, 730, 309, 36, 280, 309, 35, 45, 434, 18394, 432, 309, 35, 884, 14668, 372, 309, 36, 1182, 4138, 9848, 1090, 434, 309, 35, 438, 2464, 5535, 12011, 8980, 931, 39206, 458, 203, 306, 11662, 2], "prompt_token_count": 165, "reference_codepoints": 256, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [4867, 32, 1945, 346, 284, 442, 301, 291], "continuation_token_count": 8, "decoded": "agent.run()\n return {\n ", "decoded_codepoints": 32, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:tests/providers/llamacpp/structured_output.rs", "example_id": "00043f62d0ad359dc6873f252de756d17db5ac140feace875f2408bb7b024a97", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 96, 981, 81, 3958, 81, 25120, 81, 2024, 346, 301, 284, 1207, 2043, 280, 2193, 403, 980, 31016, 81, 1580, 473, 284, 1207, 1542, 280, 2193, 403, 1160, 81, 426, 473, 284, 1207, 7669, 280, 2043, 291, 638, 4867, 26, 1160, 27, 291, 638, 1001, 35758, 26, 4643, 41597, 81, 2883, 2210, 14507, 27, 291, 638, 17473, 26, 34, 32, 34, 27, 291, 638, 1832, 473, 446, 1207, 225, 3, 81, 19065, 14669, 17462, 32515, 1563, 324, 313, 2891, 3398, 20023, 706, 436, 33636, 43242, 1882, 623, 3829, 11297, 30, 1550, 32, 17473, 81, 88, 30, 1550, 32, 48251, 81, 25747, 30, 461, 1550, 32, 2310, 4414, 291, 829, 291, 638, 17042, 81, 3958, 346, 291, 638, 6240, 291, 638, 2358, 440, 17042, 13012, 2], "prompt_token_count": 126, "reference_codepoints": 32, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [302, 440, 8856, 436, 312, 3449], "continuation_token_count": 6, "decoded": "as(\"notification for a different", "decoded_codepoints": 32, "document_id": "modelcontextprotocol/java-sdk@fd004989b9484c9b81be6b03463396797b354804:mcp-test/src/test/java/io/modelcontextprotocol/server/ResourceSubscriptionTests.java", "example_id": "000444932177651fc324537dfa2509feb6b3a6441860970184cecc0a96b0979b", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 102, 1865, 1035, 357, 202, 9613, 2570, 32, 29766, 24137, 1175, 26, 7764, 1104, 26, 16948, 81, 6333, 876, 357, 202, 9613, 32, 3815, 10470, 6384, 473, 1314, 202, 3533, 24711, 355, 202, 32, 1297, 26, 1786, 32, 9353, 6054, 9032, 26, 890, 488, 2219, 3694, 32, 6054, 9032, 6253, 440, 858, 555, 2455, 33, 3142, 14036, 355, 202, 32, 3, 9613, 32, 13917, 10470, 6384, 1157, 355, 202, 32, 302, 440, 8856, 436, 312, 3449, 7412, 1395, 646, 15669, 312, 3523, 40267, 372, 312, 3449, 7412, 657, 355, 202, 32, 6393, 473, 1314, 202, 1786, 32, 2679, 48005, 4938, 922, 1521, 473, 203, 202, 111, 478, 202, 50, 1006, 203, 202, 1117, 11748, 6054, 9032, 81, 5483, 1061, 7764, 81, 13822, 1337, 11606, 903, 2], "prompt_token_count": 127, "reference_codepoints": 32, "repo": "modelcontextprotocol/java-sdk", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [45, 284, 1201, 26, 748, 32, 10300, 1020, 32, 1903, 81, 668, 81, 891, 610, 225, 35, 36, 42, 293, 225, 434, 1244, 308, 44240, 27, 284, 1201, 26, 748, 32, 10300, 1020, 32, 1903, 81, 668, 81, 891, 81, 1903, 610, 225, 36, 39, 40, 293, 284, 1201, 26, 748, 32, 10300, 1020, 32, 1903, 81, 668, 81, 891, 81, 3215, 610, 225, 40, 38, 293, 284, 1201, 26, 748, 32, 10300, 1020, 32, 1903, 81, 668, 81, 891, 81, 1903, 81, 668, 610, 225, 36, 39, 40, 293, 284, 1201, 26], "continuation_token_count": 93, "decoded": ";\n assert(col.diskann.search_list_size == 128); // default (unified)\n assert(col.diskann.search_list_size_search == 256);\n assert(col.diskann.search_list_size_insert == 64);\n assert(col.diskann.search_list_size_search_list == 256);\n assert(", "decoded_codepoints": 256, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:tests/test-unit.c", "example_id": "00044683822fc4d3fd38da672e2169989e266cf032c92d12ad739e5ae0968949", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 5804, 26, 3567, 14271, 52, 758, 81, 5221, 39361, 76, 527, 47, 17905, 15542, 284, 7631, 280, 4712, 34, 81, 2208, 81, 2402, 81, 2592, 26, 1131, 30, 308, 410, 27, 15460, 26, 1131, 471, 549, 748, 293, 284, 1201, 26, 899, 610, 4428, 2345, 81, 2950, 293, 284, 1201, 26, 748, 32, 1055, 81, 681, 610, 676, 6142, 34, 81, 9193, 81, 2319, 81, 5976, 12695, 64, 293, 284, 1201, 26, 748, 32, 10300, 1020, 32, 9768, 2265, 81, 681, 610, 676, 6142, 34, 81, 5976, 12695, 64, 81, 5221, 39361, 76, 527, 81, 17905, 293, 3, 81, 2592, 26, 1131, 30, 308, 410, 27, 15460, 26, 1131, 471, 549, 748, 293, 284, 1201, 26, 899, 610, 4428, 2345, 81, 2950, 293, 284, 1201, 26, 748, 32, 10300, 1020, 32, 1903, 81, 668, 81, 891, 610, 225, 35, 36, 42, 293, 225, 434, 1244, 308, 44240, 27, 284, 1201, 26, 748, 32, 10300, 1020, 32, 1903, 81, 668, 81, 891, 81, 1903, 610, 225, 36, 39, 40, 293, 284, 1201, 26, 748, 32, 10300, 1020, 32, 1903, 81, 668, 81, 891, 81, 3215, 610, 225, 40, 38, 293, 284, 2], "prompt_token_count": 192, "reference_codepoints": 256, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [601, 45, 291, 320, 291, 442, 45, 284, 320, 284, 442, 45, 203, 111, 203, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21, 203, 21], "continuation_token_count": 89, "decoded": "return;\n }\n return;\n }\n return;\n}\n\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#\n#", "decoded_codepoints": 128, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/install.rs", "example_id": "000452f83f92433d367746ac6806f44a784ff1d81982edb99308f98ff7153739", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 7188, 23307, 32, 8228, 1026, 715, 20062, 2537, 82, 438, 646, 12852, 810, 1406, 93, 30, 27246, 4414, 715, 11962, 81, 983, 32, 496, 81, 2751, 922, 31182, 346, 528, 829, 12370, 400, 320, 400, 4036, 45, 324, 320, 1802, 3, 1468, 23307, 32, 8228, 1026, 715, 20062, 2537, 82, 1957, 646, 2307, 30, 27246, 4414, 715, 11962, 81, 983, 32, 496, 81, 2751, 922, 31182, 346, 528, 829, 12370, 400, 320, 400, 4036, 45, 324, 320, 324, 7178, 26, 530, 27, 532, 442, 2], "prompt_token_count": 86, "reference_codepoints": 128, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [203, 823, 31672, 44, 284, 1524, 284, 31672, 443, 436, 3379, 3891, 25421, 32, 446, 499, 753, 6998, 44, 3379, 3891, 25421, 6998, 32, 284, 499, 753, 20217, 44, 3379, 3891, 25421, 20217, 32, 284, 499, 753, 30795, 81, 314, 44, 41621, 2484, 32, 284, 499, 753, 803, 81, 2516, 44, 2032, 3738, 32, 284, 1524, 446, 665, 1156], "continuation_token_count": 59, "decoded": "\nclass Converter:\n \"\"\"\n Converter class for Azure Key Vault.\n\n :param endpoint: Azure Key Vault endpoint.\n :param credential: Azure Key Vault credential.\n :param analyzer_id: Analyzer ID.\n :param file_types: File types.\n \"\"\"\n\n def __", "decoded_codepoints": 257, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_cu_converter.py", "example_id": "00045c4c7d23bc6106d0d370ab78c8615baacab02849fbd261b75862a85fd6a1", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 761, 81, 3867, 543, 328, 3447, 2812, 392, 313, 893, 3612, 284, 442, 803, 81, 3867, 543, 610, 30795, 81, 3867, 543, 478, 203, 21, 40595, 203, 21, 31672, 203, 21, 40595, 478, 3, 261, 665, 1156, 1664, 3207, 291, 630, 30, 291, 9305, 291, 6998, 44, 596, 30, 291, 20217, 44, 3379, 953, 13767, 523, 6512, 13767, 523, 1665, 280, 1665, 30, 291, 30795, 81, 314, 44, 5648, 77, 466, 79, 280, 1665, 30, 291, 803, 81, 2516, 44, 5648, 77, 720, 77, 1777, 12915, 17443, 18811, 3212, 280, 1665, 30, 284, 2], "prompt_token_count": 95, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [45, 355, 202, 25210, 81, 1613, 81, 2186, 81, 1161, 26, 53, 991, 505, 53, 30543, 30, 2357, 81, 5065, 30, 390, 6218, 1013, 81, 5918], "continuation_token_count": 26, "decoded": ";\n\t\t\tcairo_select_font_face(Clay__Cairo, font_family, CAIRO_FONT", "decoded_codepoints": 64, "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:renderers/cairo/clay_renderer_cairo.c", "example_id": "00046741971bbe0ff214831921ac80b2049111635f9d22d02c9c5dc68d71977c", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 87, 1652, 452, 31041, 293, 355, 202, 1594, 319, 2186, 81, 5065, 280, 23805, 77, 1163, 396, 2186, 606, 970, 2540, 202, 53, 991, 81, 26594, 18568, 280, 2016, 396, 28574, 1705, 45, 355, 202, 53, 991, 81, 1514, 1963, 280, 1359, 396, 43170, 45, 2540, 202, 25210, 81, 1613, 81, 2186, 81, 1161, 26, 53, 991, 505, 53, 30543, 30, 2357, 81, 5065, 30, 390, 6218, 1013, 81, 5918, 81, 3898, 4516, 81, 15644, 30, 390, 6218, 1013, 81, 5918, 81, 29045, 81, 15644, 293, 3, 26, 2446, 30, 18568, 32, 106, 30, 18568, 32, 107, 474, 18568, 32, 2273, 293, 2540, 202, 25210, 81, 470, 81, 1855, 81, 13885, 26, 2446, 30, 5042, 2730, 81, 1407, 81, 4019, 59, 1013, 26, 1489, 876, 355, 202, 25210, 81, 2245, 81, 878, 26, 2446, 30, 1344, 293, 355, 202, 25210, 81, 2679, 81, 983, 26, 2446, 293, 2540, 202, 3994, 26, 878, 293, 355, 202, 2969, 45, 357, 202, 111, 357, 202, 1732, 5042, 2730, 81, 23390, 81, 12252, 81, 2319, 81, 33425, 44, 301, 324, 390, 991, 81, 7251, 3121, 750, 319, 1163, 280, 549, 85, 2], "prompt_token_count": 189, "reference_codepoints": 64, "repo": "nicbarker/clay", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [294, 202, 8051, 603, 202, 79, 355, 202, 111, 357, 202, 79, 203, 202, 111, 203, 202, 2993, 203, 202, 601, 2908, 26, 1357, 30, 313, 2833, 32, 916], "continuation_token_count": 29, "decoded": "\t\t\t}},\n\t\t\t\t]\n\t\t\t}\n\t\t]\n\t}\n\t\"\"\"\n\treturn render(request, \"home.html", "decoded_codepoints": 64, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/browser/test_tabs.py", "example_id": "0004727d450046fd2560c922571ade543d154709864325ba613b42e3362086bf", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2833, 1938, 392, 603, 202, 20, 22574, 81, 8884, 81, 15848, 563, 313, 15624, 2899, 392, 603, 202, 20, 5566, 563, 313, 14799, 1741, 372, 6765, 1938, 392, 603, 202, 20, 1978, 81, 15848, 563, 313, 29207, 372, 6765, 1938, 392, 603, 202, 20, 1141, 563, 428, 577, 202, 1656, 1379, 202, 20, 20492, 563, 3335, 1488, 202, 20, 965, 563, 10698, 1439, 81, 965, 3188, 2833, 392, 1488, 202, 20, 890, 81, 3007, 563, 901, 1379, 202, 1540, 357, 3, 294, 202, 88, 2993, 355, 202, 1656, 603, 202, 20, 16462, 299, 563, 313, 33623, 1938, 225, 35, 328, 537, 4878, 392, 603, 202, 20, 22574, 81, 8884, 81, 15848, 563, 313, 4625, 1938, 3892, 392, 603, 202, 20, 5566, 563, 313, 33623, 1938, 225, 35, 392, 603, 202, 20, 1978, 81, 15848, 563, 313, 2961, 1938, 225, 35, 392, 603, 202, 20, 1141, 563, 428, 577, 202, 1656, 1379, 202, 20, 20492, 563, 3335, 1488, 202, 20, 965, 563, 10698, 1439, 81, 965, 3188, 1637, 35, 392, 355, 2], "prompt_token_count": 172, "reference_codepoints": 64, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [983, 392, 2430, 2215, 33, 2988, 31, 27275, 1446, 324], "continuation_token_count": 10, "decoded": "path\", \"/opt/custom-chromium\"]\n ", "decoded_codepoints": 42, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/cli/test_cli.py", "example_id": "0004740a6d28e42a0774b78e26e4685bee5686f6dde2f51b0c6c03f4ae1d0a50", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 584, 623, 7841, 440, 37795, 2920, 32, 5140, 483, 32, 15702, 4413, 107, 22662, 32, 5140, 657, 619, 4395, 81, 5140, 44, 324, 4395, 81, 5140, 32, 601, 81, 853, 280, 8488, 81, 9003, 81, 3613, 346, 1064, 1056, 280, 15684, 32, 7844, 26, 400, 14680, 4413, 107, 81, 5140, 30, 428, 916, 81, 965, 30, 596, 26, 2024, 81, 761, 471, 7915, 21823, 31, 3, 2264, 829, 324, 1201, 1056, 32, 4775, 81, 687, 610, 225, 34, 324, 1201, 4395, 81, 5140, 32, 1851, 81, 1132, 32, 5321, 1365, 21823, 81, 983, 1446, 610, 2430, 2215, 33, 2988, 31, 27275, 20, 584, 47410, 2675, 32, 470, 2121, 440, 5857, 1893, 31332, 81, 35629, 2147, 81, 4065, 392, 2430, 2215, 33, 2121, 31, 27275, 657, 291, 623, 7841, 440, 37795, 2920, 32, 1225, 2], "prompt_token_count": 135, "reference_codepoints": 32, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [2264, 415, 2069, 26, 10031, 27, 848, 225, 35, 44, 400, 415, 8710, 77, 35, 997, 7201, 922], "continuation_token_count": 18, "decoded": " if len(parts) > 1:\n if parts[1].strip().", "decoded_codepoints": 66, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/_markitdown.py", "example_id": "00047c88785b69886b75b241b6db2d08098a8ea8c6face99a38991007472ff1b", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 312, 1795, 31, 681, 3338, 30, 622, 322, 18346, 681, 461, 8485, 308, 325, 5024, 27, 291, 18346, 681, 44, 5648, 77, 466, 79, 280, 1665, 291, 8485, 44, 5648, 77, 466, 79, 280, 1665, 584, 415, 313, 1286, 31, 681, 20, 328, 1789, 32, 5078, 44, 324, 8710, 280, 1789, 32, 5078, 1365, 1286, 31, 681, 6494, 2998, 45321, 657, 334, 3, 266, 8710, 44, 400, 415, 1742, 32, 7201, 922, 15990, 440, 15245, 347, 711, 528, 617, 15245, 280, 1742, 32, 2998, 440, 347, 5594, 35, 997, 7201, 346, 528, 415, 2069, 2176, 15245, 27, 848, 225, 34, 44, 715, 8485, 280, 617, 15245, 584, 588, 1670, 2017, 438, 312, 1795, 31, 1285, 2705, 938, 2], "prompt_token_count": 119, "reference_codepoints": 64, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [291, 6833, 5713, 432, 322, 37196, 30, 601, 5436, 291, 1524, 291, 415, 2305, 438, 1665, 44, 324, 2305, 280, 1605, 291, 436, 376], "continuation_token_count": 24, "decoded": "\n Process children of the elm,return dict\n \"\"\"\n if include is None:\n include = []\n for st", "decoded_codepoints": 128, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converter_utils/docx/math/omml.py", "example_id": "00048027f1ae5d33124b526cb27442312178c29d26b5463092b917b8f84b0e0f", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1028, 322, 37196, 30, 601, 5436, 291, 1524, 291, 7678, 327, 81, 13000, 280, 5436, 346, 291, 436, 376, 481, 30, 273, 30, 484, 328, 630, 32, 2416, 81, 4915, 81, 668, 26, 19692, 30, 2305, 711, 324, 7678, 327, 81, 13000, 77, 270, 481, 79, 280, 273, 291, 442, 7678, 327, 81, 13000, 446, 665, 2164, 81, 4915, 26, 784, 30, 37196, 30, 2305, 47, 2521, 711, 291, 1524, 3, 6937, 26, 102, 30, 9130, 36, 1868, 27, 813, 596, 26, 102, 27, 400, 436, 376, 481, 30, 273, 30, 484, 328, 630, 32, 2416, 81, 4915, 81, 668, 26, 19692, 30, 2305, 27, 324, 829, 291, 829, 446, 665, 2164, 81, 2139, 2174, 26, 784, 30, 37196, 30, 376, 481, 711, 291, 442, 1665, 478, 203, 823, 5186, 26, 2633, 36, 1868, 711, 284, 1344, 280, 3330, 446, 1156, 695, 81, 3963, 280, 225, 2], "prompt_token_count": 148, "reference_codepoints": 128, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [101, 32, 3227, 26, 815, 1192, 9135, 30, 13353, 334, 309, 280, 309, 32, 3227, 26, 815, 1192, 9135, 30, 13353, 334, 309, 280, 309, 32, 3227, 26, 815, 1192, 9135, 30, 13353, 334, 309, 280, 309, 32, 3227, 26, 815, 1192, 9135, 30, 13353, 334, 309, 280, 309, 32, 3227, 26, 815, 1192, 9135, 30, 13353, 334, 309, 280, 309, 32, 3227, 26, 815, 1192, 9135, 30, 13353, 334, 309, 280, 309, 32, 3227, 26, 815, 1192, 9135, 30, 13353, 334, 309, 280, 309, 32, 3227, 26, 815, 1192, 9135, 30, 13353, 334, 309, 280, 309, 32, 3227, 26, 815, 1192, 9135], "continuation_token_count": 103, "decoded": "s.replace(LEADERS, '');\n s = s.replace(LEADERS, '');\n s = s.replace(LEADERS, '');\n s = s.replace(LEADERS, '');\n s = s.replace(LEADERS, '');\n s = s.replace(LEADERS, '');\n s = s.replace(LEADERS, '');\n s = s.replace(LEADERS, '');\n s = s.replace(LEADERS", "decoded_codepoints": 257, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/mcp-servers/caveman-shrink/compress.js", "example_id": "0004874105eedf22bac23be6e0b3338a8c7fedbaad9361c91896c3639e0a1cb5", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 4294, 81, 13381, 9069, 81, 30385, 21126, 45, 3097, 1987, 301, 284, 47122, 32, 2135, 1284, 280, 225, 34, 45, 284, 415, 1429, 34652, 32, 858, 26, 541, 490, 1626, 45, 284, 963, 280, 963, 32, 3227, 7009, 193, 4987, 86, 24913, 193, 33, 89, 30, 24565, 595, 27, 532, 17136, 23225, 91, 1989, 334, 320, 334, 442, 963, 45, 203, 111, 203, 203, 1126, 20918, 590, 277, 26, 878, 27, 301, 334, 1207, 309, 280, 1344, 45, 334, 309, 280, 309, 32, 3227, 26, 815, 1192, 9135, 30, 13353, 334, 309, 280, 225, 3, 101, 280, 309, 32, 3227, 20012, 96, 109, 37, 30, 3188, 89, 30, 3228, 96, 78, 96, 895, 334, 434, 16674, 4704, 518, 322, 1932, 11692, 432, 2504, 15430, 996, 1631, 1159, 2841, 27045, 32, 334, 309, 280, 309, 32, 3227, 7009, 43918, 10182, 32, 19, 49, 10854, 101, 24913, 2009, 83, 31, 108, 35335, 89, 30, 24565, 1406, 30, 663, 27, 532, 1406, 474, 663, 32, 18089, 1035, 334, 442, 309, 32, 5464, 473, 203, 111, 203, 203, 1126, 20918, 26, 878, 30, 617, 6363, 27, 301, 334, 415, 308, 618, 2], "prompt_token_count": 189, "reference_codepoints": 256, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [44, 529, 1508, 82, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 313, 464, 3134, 392, 355, 202, 1131, 44, 549, 3487, 1527, 720, 109, 603, 202, 1934, 44, 1605, 800, 2367, 1508, 3918, 355, 202, 835, 355, 202, 2024, 44, 1605, 2263, 44, 529, 1508, 82, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 313, 464, 8019, 392, 355, 202, 1131, 44, 549, 3487, 1527, 720, 109, 603, 202, 1934, 44, 1605, 800, 2367, 1508, 3918, 355, 202, 835, 355, 202, 2024, 44, 1605, 2263, 44, 529, 1508, 82, 357, 202, 835, 357, 202, 109, 355], "continuation_token_count": 101, "decoded": ": `true`\n\t\t},\n\t\t{\n\t\t\tname: \"all two\",\n\t\t\tinput: &ExpressionOrList{\n\t\t\t\tAll: []string{\"true\"},\n\t\t\t},\n\t\t\toutput: []byte: `true`\n\t\t},\n\t\t{\n\t\t\tname: \"all three\",\n\t\t\tinput: &ExpressionOrList{\n\t\t\t\tAll: []string{\"true\"},\n\t\t\t},\n\t\t\toutput: []byte: `true`\n\t\t},\n\t\t{\n\t\t", "decoded_codepoints": 256, "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:lib/config/expressionorlist_test.go", "example_id": "000489ec544103392c2425db15748158c27d5ce48d301c701a762dc2a10ccb0b", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 321, 44, 313, 464, 392, 355, 202, 1131, 44, 549, 3487, 1527, 720, 109, 603, 202, 1934, 44, 1605, 800, 2367, 1508, 392, 313, 1508, 3918, 355, 202, 835, 355, 202, 2024, 44, 1605, 2263, 4199, 464, 44, 284, 429, 313, 1508, 20, 284, 429, 313, 1508, 3171, 471, 355, 202, 530, 44, 1302, 30, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 313, 464, 1591, 392, 355, 202, 1131, 44, 549, 3487, 1527, 720, 109, 603, 202, 1934, 44, 1605, 800, 2367, 1508, 3918, 355, 202, 835, 355, 202, 2024, 44, 1605, 2263, 3, 44, 1605, 800, 2367, 1508, 3918, 355, 202, 835, 355, 202, 2024, 44, 1605, 2263, 4199, 20, 1508, 3171, 471, 355, 202, 530, 44, 264, 1302, 30, 357, 202, 835, 203, 202, 111, 301, 357, 202, 102, 32, 2529, 26, 2251, 32, 426, 30, 3420, 26, 102, 319, 4266, 32, 70, 27, 301, 355, 202, 1267, 30, 1137, 1025, 14465, 32, 8726, 26, 2251, 32, 1131, 27, 355, 202, 325, 653, 4275, 32, 1622, 26, 530, 30, 11944, 32, 530, 27, 301, 603, 202, 102, 32, 5497, 440, 32411, 32023, 1048, 44, 904, 104, 1273, 5424, 44, 904, 104, 392, 11944, 32, 530, 30, 1137, 2], "prompt_token_count": 204, "reference_codepoints": 256, "repo": "TecharoHQ/anubis", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [313, 7365, 20, 291, 1201, 617, 371, 81, 3867, 543, 26, 1777, 12915, 17443, 18811, 32, 1456, 37, 27, 610, 313, 7365, 20, 291, 1201, 617, 371, 81, 3867, 543, 26, 1777, 12915, 17443], "continuation_token_count": 34, "decoded": " \"audio\"\n assert _get_modality(ContentUnderstandingFileType.MP3) == \"audio\"\n assert _get_modality(ContentUnderstanding", "decoded_codepoints": 132, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_cu_converter.py", "example_id": "0004a5a5a4a4269e9311b57df461fcca14b585d6afbf613f1a2e42f3ebe3b9c0", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 307, 26, 784, 711, 291, 1201, 617, 371, 81, 3867, 543, 26, 1777, 12915, 17443, 18811, 32, 1456, 38, 27, 610, 313, 5000, 20, 291, 1201, 617, 371, 81, 3867, 543, 26, 1777, 12915, 17443, 18811, 32, 22443, 27, 610, 313, 5000, 20, 446, 665, 894, 81, 7365, 81, 2516, 26, 784, 711, 291, 1201, 617, 371, 81, 3867, 543, 26, 1777, 12915, 17443, 18811, 32, 73, 4570, 27, 610, 3, 1106, 287, 203, 21, 4483, 346, 4395, 3312, 203, 21, 40595, 478, 203, 823, 2108, 6720, 3660, 44, 284, 1524, 1006, 4483, 346, 623, 26966, 19527, 8781, 7103, 446, 665, 617, 1945, 81, 5954, 26, 784, 30, 5016, 30, 18346, 681, 30, 484, 2], "prompt_token_count": 116, "reference_codepoints": 128, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [262, 8735, 1454, 296, 20, 4220, 44, 301, 3153], "continuation_token_count": 9, "decoded": " md += f\"Category: {category", "decoded_codepoints": 32, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/src/markitdown_ocr/_pptx_converter_with_ocr.py", "example_id": "0004bf3a05e04bd404a6d77fa8617d0b79e44385bbc73cac0ce5c649fb91994a", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 5531, 44, 400, 8735, 1454, 296, 563, 301, 5836, 32, 5836, 81, 1311, 32, 878, 81, 1744, 32, 878, 3845, 324, 8735, 1454, 18474, 96, 1736, 96, 20, 324, 706, 280, 1605, 324, 6215, 81, 4243, 280, 428, 85, 32, 1172, 436, 281, 328, 7565, 32, 17110, 77, 34, 997, 6956, 79, 324, 9484, 81, 4243, 280, 428, 101, 32, 426, 436, 309, 328, 7565, 32, 8442, 79, 291, 3, 8442, 81, 4243, 27, 1064, 436, 5417, 30, 6215, 328, 10703, 26, 3153, 81, 4243, 711, 400, 2698, 280, 428, 3153, 79, 400, 436, 9484, 328, 7565, 32, 8442, 44, 528, 2698, 32, 1689, 26, 8442, 32, 2810, 77, 2875, 1130, 400, 706, 32, 1689, 26, 643, 27, 1064, 3634, 86, 441, 2], "prompt_token_count": 124, "reference_codepoints": 32, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [45, 1488, 202, 2291, 3100, 2291], "continuation_token_count": 6, "decoded": ";\n\t\t\t\t\t\t\tResource secondResource", "decoded_codepoints": 32, "document_id": "modelcontextprotocol/java-sdk@fd004989b9484c9b81be6b03463396797b354804:mcp-test/src/main/java/io/modelcontextprotocol/client/AbstractMcpAsyncClientTests.java", "example_id": "0004c05064673125339f1f9a14e7ebe32e7584906d77499ba55a0eb06854e3d6", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 3470, 2610, 603, 202, 32, 19885, 3353, 1554, 26, 5379, 967, 301, 577, 202, 17435, 26, 5379, 547, 38712, 922, 32906, 732, 26, 1267, 967, 301, 1379, 202, 17435, 26, 1267, 32, 5379, 4251, 38712, 473, 14130, 202, 325, 1429, 1267, 32, 5379, 922, 6393, 1157, 301, 1488, 202, 2291, 1932, 2291, 280, 1056, 32, 5379, 922, 371, 26, 34, 293, 3, 32, 3423, 4251, 38712, 473, 1488, 202, 17435, 26, 2232, 2291, 32, 426, 4251, 38712, 473, 1379, 202, 111, 577, 202, 1916, 603, 202, 1748, 603, 202, 32, 6967, 7371, 473, 357, 202, 1916, 203, 202, 111, 478, 202, 50, 1006, 203, 202, 1117, 894, 720, 1934, 6054, 346, 301, 357, 202, 1793, 1486, 26, 1297, 63, 2219, 9998, 1026, 345, 2219, 2981, 1486, 967, 301, 355, 202, 3533, 24711, 32, 1297, 26, 95, 2219, 2981, 53, 2], "prompt_token_count": 141, "reference_codepoints": 32, "repo": "modelcontextprotocol/java-sdk", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [86, 328, 322, 2432, 2926, 32, 334, 434, 334, 434, 886, 5750, 26285, 438, 313, 2620, 20, 461, 313, 16432, 20, 884, 313, 2620, 20, 461, 313, 16432, 20, 884, 313, 16432, 2296, 334, 434, 334, 434, 886, 5750, 26285, 438], "continuation_token_count": 41, "decoded": "d in the same mode.\n //\n // The rule bullet is \"full\" and \"lite\" are \"full\" and \"lite\" are \"lite\".\n //\n // The rule bullet is", "decoded_codepoints": 129, "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:pi-extension/test/helpers.test.js", "example_id": "0004c88314799aacfd5e5aaf9a76e3341febf952d33c21f23869b9d8ca21e3e7", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2010, 32, 1253, 26, 15688, 32, 6411, 440, 8381, 1628, 2974, 203, 1916, 203, 203, 858, 440, 2029, 18152, 3050, 1562, 2101, 1957, 646, 6278, 312, 5750, 26285, 13696, 2266, 8001, 312, 2926, 636, 392, 1404, 532, 301, 334, 434, 399, 5750, 26285, 2124, 4825, 13529, 44, 39695, 1401, 322, 2432, 313, 1172, 44, 1344, 20, 6024, 619, 312, 334, 434, 13096, 2280, 30, 1273, 7735, 1330, 1591, 3, 14511, 13529, 44, 745, 646, 3570, 539, 458, 5750, 2266, 623, 322, 2926, 636, 5327, 96, 31, 48225, 44, 2432, 19902, 30, 458, 438, 312, 4011, 5750, 26285, 5327, 96, 31, 48025, 44, 313, 4543, 13096, 2280, 7646, 96, 31, 8194, 2692, 44, 313, 4543, 13096, 2280, 3171, 45, 719, 660, 13996, 280, 2761, 18152, 3050, 1562, 2101, 26, 1548, 30, 313, 338, 2692, 724, 719, 1201, 32, 1253, 26, 15688, 32, 91, 2], "prompt_token_count": 144, "reference_codepoints": 128, "repo": "DietrichGebert/ponytail", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [6282, 26, 1286, 44, 596, 27, 967, 596, 44, 357, 202, 2993, 6720, 1256, 1474, 1795, 436, 29828, 7418, 14675, 7103, 357, 202, 325, 6937, 26, 1286, 30, 596, 711], "continuation_token_count": 30, "decoded": "serialize(content: str) -> str:\n\t\t\"\"\"Convert user message content for LangChain compatibility.\"\"\"\n\t\tif isinstance(content, str):", "decoded_codepoints": 128, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:examples/models/langchain/serializer.py", "example_id": "0004cbb6c8168326f620ca3776b60e198eff3e7dc898def0d0cda743649696c6", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 94, 30, 203, 202, 1240, 1175, 30, 203, 27, 203, 1070, 5427, 81, 539, 32, 611, 95, 32, 6286, 1188, 308, 203, 202, 1598, 1175, 619, 14161, 4391, 1598, 1175, 30, 203, 27, 478, 203, 823, 29828, 7418, 1175, 7262, 44, 203, 202, 2993, 7262, 436, 24582, 3733, 5427, 31, 539, 1474, 3738, 461, 29828, 7418, 1474, 3738, 7103, 478, 202, 50, 16099, 203, 202, 589, 225, 3, 20, 6720, 1256, 1474, 1795, 436, 29828, 7418, 14675, 7103, 357, 202, 325, 6937, 26, 1286, 30, 596, 711, 355, 202, 601, 1795, 1314, 202, 15665, 81, 10031, 280, 1605, 357, 202, 979, 1742, 328, 1795, 44, 355, 202, 325, 1742, 32, 681, 610, 330, 878, 950, 603, 202, 15665, 81, 10031, 32, 1689, 26, 577, 202, 109, 1379, 202, 1330, 411, 950, 330, 878, 370, 1379, 202, 1330, 407, 25, 2], "prompt_token_count": 141, "reference_codepoints": 128, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [262, 1344, 81, 1286, 280, 3634, 283, 1746, 32, 371, 81, 878, 81, 1286, 26, 4682, 81, 983, 27, 291, 5430], "continuation_token_count": 21, "decoded": " text_content = markitdown.get_text_content(pdf_path)\n lines", "decoded_codepoints": 71, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_pdf_tables.py", "example_id": "0004cff34317bc239e9a4eff3ef343e98fa71972ebdd977f333d4de8a49a9383", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 225, 665, 894, 81, 8523, 81, 1274, 81, 6057, 81, 8791, 81, 46499, 26, 784, 30, 3634, 283, 1746, 711, 291, 1524, 1006, 688, 2234, 31, 1621, 15341, 6090, 884, 18604, 623, 49098, 7103, 291, 17117, 81, 983, 280, 2322, 32, 983, 32, 2524, 26, 324, 5895, 81, 14137, 81, 3197, 30, 313, 48565, 31, 36, 34, 36, 38, 31, 27433, 31, 35, 36, 37, 38, 81, 3478, 2274, 81, 1274, 32, 4682, 20, 291, 829, 446, 3, 280, 1344, 81, 1286, 32, 2998, 5528, 96, 657, 291, 1858, 81, 2138, 280, 428, 324, 1628, 436, 1628, 328, 5430, 415, 1628, 32, 15990, 35619, 657, 461, 1628, 32, 20643, 35619, 657, 291, 1481, 584, 1201, 2069, 26, 1274, 81, 2138, 27, 848, 225, 34, 30, 313, 6469, 1159, 16316, 1858, 5760, 20, 584, 588, 3456, 688, 821, 6225, 1629, 5760, 420, 2], "prompt_token_count": 143, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [452, 312, 334, 588, 313, 1206, 13671, 2625, 20, 26160, 6346, 587, 31, 541, 32, 334, 330, 1131, 6850, 821, 18074, 28116, 370, 334, 330, 9217, 101, 706, 7699, 370, 334, 330, 4373, 370, 334, 330, 35509, 370, 334, 330, 18843, 1340, 2876, 2819, 1505, 438, 707, 15009, 370, 434, 1591, 31, 1553, 10678, 14192, 372, 31963, 203, 970, 203, 203, 913, 20838, 280, 1491, 463, 25071, 33, 98], "continuation_token_count": 69, "decoded": "to a\n # \"not lazy about\" safety carve-out.\n 'input validation at trust boundaries',\n 'prevents data loss',\n 'security',\n 'accessibility',\n 'Lazy code without its check is unfinished', // one-check promoted to headline\n];\n\nconst skill = read('skills/p", "decoded_codepoints": 256, "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:scripts/check-rule-copies.js", "example_id": "0004d06263b6a0d9f99fd616a1076fcc7fa6fb06e7c5514912dbe34d49412a01", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 587, 938, 31095, 370, 7693, 434, 10635, 10929, 31, 3647, 5750, 334, 330, 4431, 40475, 1505, 370, 4696, 434, 894, 2488, 1909, 334, 330, 88, 374, 874, 2487, 8218, 370, 4696, 434, 28819, 31, 7949, 5750, 334, 434, 322, 12074, 313, 1206, 13671, 2625, 20, 26160, 6346, 587, 31, 24568, 44, 9565, 2504, 1259, 312, 316, 1112, 225, 3, 330, 1131, 6850, 821, 18074, 28116, 370, 334, 330, 9217, 101, 706, 7699, 370, 334, 330, 4373, 370, 334, 330, 35509, 370, 334, 330, 18843, 1340, 2876, 2819, 1505, 438, 707, 15009, 370, 434, 1591, 31, 1553, 10678, 14192, 372, 31963, 203, 970, 203, 203, 913, 20838, 280, 1491, 463, 25071, 33, 98, 4359, 9793, 33, 9718, 13142, 32, 954, 895, 203, 913, 10849, 280, 20463, 25071, 2], "prompt_token_count": 128, "reference_codepoints": 256, "repo": "DietrichGebert/ponytail", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [287, 2888, 47, 5567, 36, 39, 40, 44, 34439, 78, 96, 392, 324, 2588, 324, 308, 400], "continuation_token_count": 17, "decoded": "--hash=sha256:abcd\\n\",\n ),\n (\n ", "decoded_codepoints": 67, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/hooks/pre_commit_hooks/requirements_txt_fixer.rs", "example_id": "0004d17cf7c6799d1be0bceabc0a97664e95bc14d347f71219dd609769ac5207", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2087, 78, 3258, 47, 37, 32, 34, 32, 34, 766, 1736, 96, 225, 769, 2888, 47, 5567, 36, 39, 40, 44, 83, 35, 84, 35, 85, 35, 86, 35, 392, 400, 323, 20, 83, 47, 37, 32, 34, 32, 34, 766, 1736, 96, 225, 769, 2888, 47, 5567, 36, 39, 40, 44, 83, 35, 84, 35, 85, 35, 86, 35, 78, 1490, 379, 35, 32, 34, 32, 34, 78, 6635, 47, 36, 32, 34, 32, 34, 766, 1736, 96, 769, 2888, 47, 5567, 36, 39, 40, 44, 34439, 78, 96, 392, 324, 2588, 324, 308, 400, 323, 20, 83, 47, 36, 32, 34, 32, 34, 766, 1736, 96, 769, 2888, 47, 5567, 36, 39, 40, 44, 34439, 78, 1490, 379, 35, 32, 34, 32, 34, 78, 96, 392, 400, 323, 20, 3, 263, 308, 84, 20, 3986, 78, 100, 78, 1490, 282, 78, 100, 78, 96, 392, 323, 20, 1632, 78, 100, 78, 96, 3986, 78, 100, 78, 96, 2113, 324, 308, 84, 40299, 3338, 78, 96, 3986, 766, 1736, 96, 78, 1490, 282, 78, 96, 392, 323, 40299, 3338, 78, 96, 78, 1490, 282, 78, 96, 2113, 324, 308, 400, 323, 20, 108, 2281, 78, 96, 31, 87, 5554, 29, 9404, 555, 965, 766, 1736, 96, 769, 1163, 22664, 21280, 47, 10985, 78, 96, 392, 400, 323, 24168, 87, 5554, 29, 9404, 555, 965, 766, 1736, 96, 769, 1163, 22664, 21280, 47, 1504, 98, 2], "prompt_token_count": 237, "reference_codepoints": 64, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [261, 8058, 10368, 446, 313, 4463, 36, 34, 35, 43, 31, 6569, 20, 523, 313, 4463, 36, 34, 35, 43, 31, 21815, 20, 523, 313, 4463, 36, 34, 35, 40, 31, 6569, 20, 523, 766, 284, 313, 4463, 36, 34, 35, 36, 100, 36, 31, 6569, 20, 523, 313, 4463, 36, 34, 35, 43, 31, 6569, 20, 523, 313, 4463, 36, 34, 35, 43, 31, 21815, 20, 829, 1687, 415], "continuation_token_count": 70, "decoded": " fi ;;\n\n \"win2019-eval\" | \"win2019-hv\" | \"win2016-eval\" | \\\n \"win2012r2-eval\" | \"win2019-eval\" | \"win2019-hv\" )\n\n if", "decoded_codepoints": 129, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/mido.sh", "example_id": "0004df1ceda534a5c4a13addb082cde1ec6d33a8f7b3ba0728a52acdb814418e", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1955, 12672, 1648, 20, 291, 442, 225, 34, 397, 8058, 10368, 446, 313, 4463, 36, 34, 36, 39, 31, 6569, 20, 523, 313, 4463, 36, 34, 36, 36, 31, 6569, 20, 523, 313, 4463, 36, 34, 35, 43, 31, 6569, 20, 523, 766, 284, 313, 4463, 36, 34, 35, 43, 31, 21815, 20, 523, 313, 4463, 36, 34, 35, 40, 31, 6569, 20, 523, 313, 4463, 36, 34, 35, 36, 100, 36, 31, 6569, 20, 829, 1687, 415, 5822, 2839, 14066, 3941, 1648, 20, 3941, 1581, 20, 3941, 31728, 866, 1615, 291, 488, 779, 65, 81, 8182, 12672, 1648, 20, 284, 3, 20, 3817, 20418, 3191, 30, 786, 40355, 1648, 1492, 438, 646, 27149, 11555, 397, 442, 225, 35, 397, 10368, 334, 2813, 329, 719, 488, 779, 65, 81, 2413, 9456, 25452, 7005, 3941, 1648, 20, 3941, 1581, 20, 7746, 334, 428, 429, 108, 3941, 20876, 65, 81, 2413, 20, 1481, 962, 442, 225, 35, 719, 415, 3813, 6313, 1648, 4781, 3845, 610, 313, 4463, 36, 34, 34, 42, 100, 36, 41731, 18154, 1615, 284, 488, 779, 65, 81, 8182, 347, 4463, 36, 34, 34, 42, 100, 36, 31, 6569, 2], "prompt_token_count": 192, "reference_codepoints": 128, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [45, 357, 202, 38368, 1757, 4925, 39279, 32, 22083, 81, 1082], "continuation_token_count": 11, "decoded": ";\n\t\tTRUNCATE TABLE silver.erp_px", "decoded_codepoints": 32, "document_id": "DataWithBaraa/sql-data-warehouse-project@92406686380cde6eca208c8b43e6fa40ecd26344:scripts/silver/proc_load_silver.sql", "example_id": "0004e22224e0a29249b03630823a69b296dd9f97acddcab69fd5f7904fc09c34", "language": "sql", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 267, 2939, 32, 22083, 81, 881, 81, 83, 35, 34, 35, 45, 3269, 5798, 477, 416, 81, 1003, 280, 6272, 5241, 473, 291, 24309, 330, 2005, 6830, 16685, 44, 330, 474, 9450, 26, 54, 8149, 38846, 26, 23790, 30, 477, 1366, 81, 1003, 30, 477, 416, 81, 1003, 27, 2469, 489, 28262, 27, 474, 330, 6791, 920, 291, 24309, 330, 2005, 15148, 920, 4086, 202, 287, 19504, 5097, 98, 81, 1082, 81, 2579, 81, 89, 35, 104, 36, 357, 202, 2695, 477, 1366, 81, 1003, 280, 6272, 5241, 346, 3, 41190, 32, 22083, 81, 1082, 81, 2579, 81, 89, 35, 104, 36, 920, 357, 202, 38368, 1757, 4925, 39279, 32, 22083, 81, 1082, 81, 2579, 81, 89, 35, 104, 36, 45, 357, 202, 11271, 330, 2005, 46219, 1054, 2398, 21075, 44, 39279, 32, 22083, 81, 1082, 81, 2579, 81, 89, 35, 104, 36, 920, 357, 202, 2631, 2641, 39279, 32, 22083, 81, 1082, 81, 2579, 81, 89, 35, 104, 36, 308, 355, 202, 314, 30, 355, 202, 2579, 30, 355, 202, 1113, 2579, 30, 355, 202, 31277, 357, 202, 27, 357, 202, 4620, 355, 202, 314, 30, 355, 202, 2579, 30, 355, 202, 1113, 2579, 30, 355, 202, 16565, 272, 1964, 2], "prompt_token_count": 203, "reference_codepoints": 32, "repo": "DataWithBaraa/sql-data-warehouse-project", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [322, 9182, 1098, 526, 10768, 328, 322, 5427, 32, 291, 499, 753, 4465], "continuation_token_count": 13, "decoded": " the selector will be executed in the browser.\n :param wait", "decoded_codepoints": 66, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/_browsers/_controllers.py", "example_id": "0004e684789020b8c2058485f753e65807369f9a8202242a15e9d38a05c3ae55", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2033, 7019, 32, 16010, 372, 322, 2664, 1244, 11259, 32, 291, 499, 753, 22158, 81, 314, 44, 14013, 322, 22158, 432, 322, 5427, 32, 16010, 372, 322, 2664, 22158, 32, 291, 499, 753, 4465, 81, 9003, 81, 1293, 44, 886, 1603, 372, 4465, 436, 322, 9182, 2702, 623, 529, 1684, 81, 9003, 2541, 886, 3, 1159, 312, 11766, 5427, 6713, 544, 1370, 3298, 30, 5352, 458, 30, 461, 322, 15574, 265, 1098, 11303, 600, 1980, 432, 1370, 5427, 461, 793, 561, 32, 291, 499, 753, 2454, 81, 4722, 44, 11516, 810, 1244, 30, 4465, 436, 1169, 9657, 544, 1938, 26, 101, 27, 372, 12086, 2454, 461, 5742, 32, 291, 499, 753, 281, 5974, 81, 2], "prompt_token_count": 116, "reference_codepoints": 64, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [800, 261, 529, 1260, 1924, 1813, 30, 6039, 20, 14465, 1924, 1813, 30, 6039, 3171, 203, 202, 111, 203, 111, 203, 203, 681, 10292, 720, 1671, 301, 203, 202, 3487, 802, 261, 529, 1260, 14487, 20, 14465, 6039, 203, 202, 1934, 351, 1605, 800, 529, 1260, 1924, 464, 30, 6039, 3171, 203, 202, 4277, 225, 802, 261, 529, 1260, 1924, 1813, 30, 6039, 3171, 203, 202, 111, 203, 111, 203, 203, 681, 10292, 720, 1671, 301, 203, 202, 3487], "continuation_token_count": 79, "decoded": "string `json:\"any,omitempty\" yaml:\"any,omitempty\"`\n\t}\n}\n\ntype ExpressionList struct {\n\tExpression string `json:\"-\" yamlomitempty\n\tAll []string `json:\"all,omitempty\"`\n\tAny string `json:\"any,omitempty\"`\n\t}\n}\n\ntype ExpressionList struct {\n\tExpression", "decoded_codepoints": 261, "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:lib/config/expressionorlist.go", "example_id": "0004e7860b6a5acd303a9188a00588332288a046f2a1085e174e58ceffd2b2eb", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 285, 53, 692, 9037, 25893, 3389, 280, 3878, 32, 1812, 440, 1163, 44, 6101, 2163, 883, 1330, 4799, 4609, 6101, 3738, 657, 203, 27, 203, 203, 681, 10292, 1527, 720, 1671, 301, 203, 202, 3487, 802, 261, 529, 1260, 14487, 20, 14465, 15951, 203, 202, 1934, 351, 1605, 800, 529, 1260, 1924, 464, 30, 6039, 20, 14465, 1924, 464, 30, 6039, 3171, 203, 202, 4277, 225, 3, 109, 355, 202, 325, 595, 863, 225, 34, 301, 603, 202, 3972, 32, 35808, 1652, 5682, 30, 313, 962, 7788, 355, 202, 111, 355, 202, 3972, 32, 35808, 1652, 5682, 30, 11608, 904, 101, 829, 392, 4626, 27, 357, 202, 111, 357, 202, 601, 6115, 32, 652, 346, 203, 202, 1732, 2069, 26, 42418, 32, 4277, 27, 863, 225, 34, 44, 357, 202, 869, 6115, 5852, 32, 1796, 357, 202, 979, 595, 30, 4626, 1025, 2155, 484, 362, 32, 4277, 301, 355, 202, 325, 595, 863, 225, 34, 301, 603, 202, 3972, 32, 35808, 1652, 5682, 30, 313, 1276, 7788, 355, 202, 111, 355, 202, 3972, 32, 56, 777, 266, 2], "prompt_token_count": 179, "reference_codepoints": 256, "repo": "TecharoHQ/anubis", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [4396, 225, 34, 293, 334, 561, 463, 13822, 646, 2163, 4871], "continuation_token_count": 11, "decoded": "async 0);\n it('does not block apply", "decoded_codepoints": 36, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/commands/workflow-instructions-skipped.test.ts", "example_id": "0004f213122f514ac92c6ec91e70adcce7793f51c4a9220b0c1cfbe8510e1aa0", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1433, 2976, 280, 5980, 32, 4765, 86, 1433, 4764, 26, 983, 32, 2524, 26, 500, 32, 30606, 1026, 330, 11593, 897, 31, 858, 31, 4646, 334, 1122, 719, 39935, 4114, 532, 301, 284, 5980, 32, 3925, 4764, 26, 1433, 2976, 30, 301, 18581, 44, 861, 30, 7650, 44, 861, 1122, 334, 1122, 719, 561, 463, 13822, 646, 2163, 4871, 544, 312, 20434, 12442, 1412, 322, 5365, 7171, 1169, 21419, 370, 2498, 225, 3, 4699, 2163, 39394, 1751, 372, 33783, 3638, 12442, 30, 284, 434, 6237, 322, 24082, 31, 510, 19524, 1591, 429, 322, 7116, 2298, 2385, 619, 5024, 32, 284, 660, 5365, 2976, 280, 1519, 32, 2524, 26, 1433, 2976, 30, 330, 11593, 897, 370, 330, 14331, 370, 330, 15920, 895, 284, 5980, 32, 10174, 4764, 26, 3968, 2976, 30, 301, 18581, 44, 861, 1122, 284, 5980, 2], "prompt_token_count": 139, "reference_codepoints": 32, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [261, 436, 308, 1112, 30, 2385, 27, 328, 8594, 32, 8005], "continuation_token_count": 11, "decoded": " for (word, count) in sorted.into", "decoded_codepoints": 35, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:csharp-book/src/ch15-2-incremental-adoption-strategy.md", "example_id": "0004f7a268c1762c8af6c9b650894b7beeeac21889f339246b4d83324b7ccffa", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 928, 328, 1795, 32, 4446, 346, 301, 291, 436, 3594, 328, 1628, 32, 2998, 81, 29903, 346, 301, 324, 1207, 3594, 280, 3594, 32, 452, 81, 37314, 473, 324, 319, 1112, 81, 998, 32, 3038, 26, 1112, 547, 271, 81, 3215, 26, 34, 27, 1454, 225, 35, 45, 291, 320, 284, 320, 2170, 1207, 4031, 8594, 44, 7479, 17782, 48, 280, 3594, 81, 998, 32, 8005, 81, 1731, 922, 6174, 473, 334, 3, 1652, 83, 32, 35, 876, 2170, 436, 308, 1112, 30, 2385, 27, 328, 8594, 32, 8005, 81, 1731, 922, 11814, 26, 1132, 32, 1393, 27, 301, 291, 11662, 9170, 2537, 44, 12263, 3594, 30, 2385, 293, 284, 320, 2170, 6311, 20268, 203, 111, 203, 914, 203, 203, 1482, 26159, 225, 36, 44, 16695, 23016, 31, 22736, 19486, 308, 11070, 101, 225, 39, 31, 42, 27, 203, 914, 7421, 203, 306, 16695, 10218, 31, 410, 18540, 706, 2164, 91, 2], "prompt_token_count": 153, "reference_codepoints": 32, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [8523, 82, 556, 1156, 466, 505, 7103, 291], "continuation_token_count": 8, "decoded": "markdown` or __str__.\"\"\"\n ", "decoded_codepoints": 32, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/_base_converter.py", "example_id": "0004fdc5d53725ea6c9ac1a9fa402f66cfcbaba9898030a902669d3ab583dc35", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 979, 529, 8523, 2541, 3136, 1340, 1395, 22646, 372, 1471, 529, 8523, 82, 556, 1156, 466, 505, 7103, 291, 442, 630, 32, 8523, 446, 477, 878, 81, 1286, 32, 16527, 284, 665, 1344, 81, 1286, 26, 784, 30, 16316, 44, 596, 711, 291, 1524, 14986, 31, 15040, 8813, 436, 529, 8523, 2541, 3136, 1340, 1395, 22646, 372, 1471, 529, 3, 630, 32, 8523, 280, 16316, 446, 665, 1156, 466, 3207, 784, 27, 967, 596, 44, 291, 1524, 2891, 322, 12785, 21047, 1344, 7103, 291, 442, 630, 32, 8523, 478, 203, 823, 6211, 6519, 44, 284, 1524, 5584, 37475, 432, 1169, 6211, 36218, 7103, 446, 665, 19201, 26, 291, 630, 30, 275, 2], "prompt_token_count": 113, "reference_codepoints": 32, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [45, 397, 2014, 5980, 32, 10174, 26, 16452, 2976, 30, 301, 18581, 44, 861, 1122, 45, 284, 1122, 334], "continuation_token_count": 19, "decoded": ";\n await fs.mkdir(specsDir, { recursive: true });;\n });\n ", "decoded_codepoints": 65, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/completions/completion-provider.test.ts", "example_id": "00050502d55aa6bffb1c6baddfed52b319055caa347e9bfd857453228aff5495", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 27, 532, 301, 284, 561, 463, 3163, 442, 4335, 1539, 461, 1374, 15342, 370, 2498, 1404, 532, 301, 397, 660, 3404, 2976, 280, 1519, 32, 2524, 26, 858, 2976, 30, 330, 11593, 897, 370, 330, 12764, 895, 397, 660, 24082, 2976, 280, 1519, 32, 2524, 26, 858, 2976, 30, 330, 11593, 897, 370, 330, 16452, 895, 397, 2014, 5980, 32, 10174, 26, 12764, 2976, 30, 301, 18581, 44, 861, 1122, 3, 1922, 312, 1539, 397, 2014, 5980, 32, 10174, 26, 983, 32, 2524, 26, 12764, 2976, 30, 330, 1772, 31, 2342, 1425, 301, 18581, 44, 861, 1122, 397, 2014, 5980, 32, 39052, 26, 983, 32, 2524, 26, 12764, 2976, 30, 330, 1772, 31, 2342, 370, 330, 25520, 32, 954, 1425, 5307, 5614, 895, 1687, 434, 2648, 312, 1374, 397, 2014, 5980, 32, 10174, 26, 983, 32, 2524, 26, 16452, 2976, 30, 330, 1772, 31, 28383, 2], "prompt_token_count": 147, "reference_codepoints": 64, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [262, 442, 225, 34, 45, 334, 320, 719, 1257, 27622, 12051, 569, 334, 629, 310, 280, 1929, 81, 26257, 45, 334, 1897, 319, 1146, 81, 31818, 77, 96, 319, 310, 319, 3744, 26, 1808, 2177, 280, 225, 34, 32, 34, 88, 45, 334, 1897], "continuation_token_count": 44, "decoded": " return 0;\n }\n\n /* Allocate arrays */\n int n = num_candidates;\n float *inter_distances[n * n * sizeof(float)] = 0.0f;\n float", "decoded_codepoints": 133, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:tests/fuzz/diskann-prune-direct.c", "example_id": "00051611b2417cfd77b240341db0954ada7b8436b7b784c90b61bfad9f5f6a76", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 495, 16713, 2078, 569, 334, 1727, 42, 81, 102, 7377, 81, 2875, 280, 296, 12856, 81, 2263, 1652, 605, 30, 549, 891, 30, 225, 34, 27, 904, 225, 42, 45, 334, 1897, 7377, 81, 2810, 1178, 280, 301, 34, 32, 34, 88, 30, 225, 34, 32, 39, 88, 30, 225, 35, 32, 34, 88, 30, 225, 35, 32, 36, 88, 30, 225, 35, 32, 39, 88, 30, 225, 36, 32, 34, 88, 30, 225, 35, 34, 32, 34, 88, 30, 225, 35, 34, 34, 32, 34, 88, 1255, 334, 1897, 7377, 280, 7377, 81, 2810, 77, 4893, 81, 2875, 970, 719, 415, 308, 1516, 81, 26257, 610, 225, 34, 27, 301, 284, 1257, 2108, 3502, 1135, 569, 334, 3, 3293, 30, 549, 541, 1534, 293, 284, 1201, 26, 899, 610, 225, 34, 1257, 4428, 2345, 81, 2950, 569, 293, 284, 1201, 26, 541, 1534, 610, 225, 34, 293, 284, 442, 225, 34, 45, 334, 320, 719, 1257, 27622, 12051, 569, 334, 629, 310, 280, 1929, 81, 26257, 45, 334, 1897, 319, 1146, 81, 31818, 280, 16658, 26, 96, 319, 310, 319, 3744, 26, 1808, 876, 334, 1897, 319, 98, 81, 31818, 280, 16658, 26, 96, 319, 3744, 26, 1808, 27, 2], "prompt_token_count": 202, "reference_codepoints": 128, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [202, 202, 869, 345, 2219, 4764, 2059, 32, 669, 3653, 26, 63, 2219, 2059, 9554, 32, 4764, 3653, 13903], "continuation_token_count": 19, "decoded": "\t\tvar mcpSyncServer.addTool(McpServerFeatures.SyncToolSpecification", "decoded_codepoints": 67, "document_id": "modelcontextprotocol/java-sdk@fd004989b9484c9b81be6b03463396797b354804:mcp-test/src/main/java/io/modelcontextprotocol/server/AbstractMcpSyncServerTests.java", "example_id": "00051d0e7b2a061fe325f8baebe542f122cb8a3a291f65bf2be3716361106baa", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 808, 473, 203, 202, 111, 478, 202, 50, 1006, 203, 202, 1117, 894, 1103, 18017, 3653, 1853, 346, 301, 357, 202, 3653, 12843, 3653, 280, 488, 2219, 3694, 32, 3653, 32, 4164, 26, 3765, 81, 15976, 81, 2474, 30, 29420, 81, 3265, 81, 20740, 547, 1311, 440, 18017, 4559, 1895, 1832, 473, 1314, 202, 869, 345, 2219, 4764, 2059, 280, 11656, 4764, 2059, 1796, 922, 1786, 1120, 440, 858, 31, 1786, 392, 313, 35, 32, 34, 32, 34, 657, 203, 3, 490, 355, 202, 32, 3732, 1853, 26, 19992, 3653, 30, 577, 202, 26, 11431, 30, 1326, 27, 967, 5640, 3653, 1394, 32, 4164, 922, 1286, 26, 720, 32, 1028, 4251, 45156, 26, 1870, 547, 1832, 1157, 355, 202, 32, 1832, 473, 1314, 202, 17435, 1227, 4114, 967, 345, 2219, 4764, 2059, 32, 669, 3653, 26, 63, 2219, 2059, 9554, 32, 4764, 3653, 13903, 32, 4164, 346, 355, 202, 32, 3732, 26, 19992, 705, 2], "prompt_token_count": 156, "reference_codepoints": 64, "repo": "modelcontextprotocol/java-sdk", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [267, 1057, 11592, 101, 312, 27045, 9909, 33, 12172, 328, 322, 3361, 308, 19807, 322, 3555, 816, 533, 533, 7243, 397, 3361, 1057, 2699, 397, 660, 3639, 280, 2014, 537, 19526], "continuation_token_count": 31, "decoded": "on='rejects a lowercase shall/must in the body (matching the del x y y)',\n body='''\n const report = await new Validator", "decoded_codepoints": 129, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/validation.test.ts", "example_id": "00051e334c460ceb00cf1008aaaa1f1d29f9a4bcf689937e11741d2605a19d12", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 102, 304, 293, 397, 660, 5654, 280, 9909, 25092, 26, 3734, 32, 4476, 293, 397, 1424, 26, 4476, 547, 13582, 2380, 26, 35, 293, 397, 1424, 26, 4476, 77, 34, 997, 1436, 547, 1206, 32, 38047, 463, 1206, 1755, 328, 322, 3338, 895, 284, 1122, 446, 561, 463, 13822, 646, 4655, 312, 20066, 13696, 3361, 1628, 4304, 322, 11659, 370, 2498, 3, 69, 78, 96, 31, 1115, 5873, 326, 816, 78, 96, 31, 1115, 43049, 326, 533, 25, 397, 1093, 397, 660, 3639, 280, 2014, 537, 19526, 922, 4635, 2710, 1777, 463, 6380, 370, 1795, 293, 397, 1424, 26, 8955, 25092, 26, 3734, 32, 4476, 3427, 13582, 2380, 26, 34, 293, 284, 1122, 446, 561, 463, 11592, 101, 312, 27045, 9909, 33, 12172, 328, 322, 3361, 308, 19807, 322, 3555, 2], "prompt_token_count": 132, "reference_codepoints": 128, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [27670, 1325, 633, 544, 322, 2818, 3523, 44, 301, 87, 15837, 577, 202, 21, 1670, 322, 3523, 438], "continuation_token_count": 18, "decoded": "screencast on the specific session: {e}')\n\t\t\t\t\t# If the session is", "decoded_codepoints": 66, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/browser/watchdogs/recording_watchdog.py", "example_id": "000523e5bf4587d1848ac595fe738948f0e8211cf0609f6d66416329ae635eda", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 268, 1325, 633, 544, 322, 2818, 3523, 577, 202, 6240, 630, 32, 7128, 81, 2848, 32, 2087, 98, 81, 1580, 32, 2714, 32, 1969, 32, 4048, 44102, 1325, 633, 26, 2848, 81, 314, 47, 784, 1114, 1700, 81, 2848, 81, 314, 27, 603, 202, 7343, 3268, 619, 484, 44, 577, 202, 21, 2030, 1182, 4195, 322, 3523, 438, 3425, 8777, 577, 202, 784, 32, 4073, 32, 2811, 26, 88, 25, 5288, 372, 4719, 225, 3, 784, 1114, 1700, 81, 2848, 81, 314, 280, 281, 5974, 81, 2848, 32, 2848, 81, 314, 2540, 202, 21, 4793, 23113, 544, 322, 537, 3523, 355, 202, 6240, 281, 5974, 81, 2848, 32, 2087, 98, 81, 1580, 32, 2714, 32, 1969, 32, 1366, 44102, 1325, 633, 26, 603, 202, 2132, 47, 784, 1114, 27670, 1325, 633, 81, 2132, 30, 225, 588, 827, 44, 5079, 603, 202, 2848, 81, 314, 47, 2087, 98, 81, 2848, 32, 2848, 81, 314, 30, 355, 202, 27, 355, 202, 784, 32, 315, 2], "prompt_token_count": 164, "reference_codepoints": 64, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [264, 2014, 1424, 26, 2501, 32, 1298, 26, 1637, 30, 301, 11659, 44, 330, 13948, 374, 370, 2723, 44], "continuation_token_count": 19, "decoded": " await expect(command.func(page, { keyword: 'opencli', limit:", "decoded_codepoints": 64, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/yahoo/search.test.js", "example_id": "00052497a333adc9bb24330c2510f854beae3bedf4ef621ca448252ef0cfbbf3", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 6137, 284, 1122, 446, 2014, 1424, 26, 2501, 32, 1298, 26, 1637, 30, 301, 11659, 44, 330, 13948, 374, 370, 2723, 44, 225, 35, 30, 1938, 44, 225, 36, 42709, 49115, 32, 7285, 36839, 397, 11263, 44, 225, 42, 30, 397, 1780, 44, 330, 2961, 8453, 370, 397, 1984, 44, 330, 641, 555, 933, 32, 508, 33, 10583, 105, 749, 33, 2961, 8453, 370, 397, 20085, 44, 330, 8453, 5427, 4559, 299, 370, 284, 41923, 334, 1122, 203, 3, 17388, 370, 2498, 1404, 532, 301, 284, 660, 1938, 280, 1487, 1969, 3660, 2009, 397, 428, 291, 330, 8418, 5668, 370, 291, 330, 641, 555, 100, 32, 1903, 32, 23643, 32, 508, 8501, 107, 2159, 47, 106, 33, 18137, 47, 4259, 23, 37, 51, 4792, 26, 35, 4165, 24981, 47, 36, 33, 10171, 47, 106, 370, 291, 330, 3163, 646, 526, 31398, 370, 397, 2505, 284, 6712, 446, 2014, 1424, 26, 2501, 32, 1298, 26, 1637, 30, 301, 2], "prompt_token_count": 159, "reference_codepoints": 64, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [784, 30, 2968, 44, 8809, 27, 967, 20758, 301, 291, 1207, 4031, 4774, 280, 20758, 403, 890, 1652, 784], "continuation_token_count": 19, "decoded": "self, store: Store) -> Cmd {\n let mut cmd = Cmd::new(&self", "decoded_codepoints": 65, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/languages/python/uv.rs", "example_id": "00052d8a931e42c181ccbc2bd72eceeb793fde384a3f4af657657b6e52396abb", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 48, 6609, 301, 291, 6609, 301, 1519, 320, 284, 320, 446, 2547, 26, 9822, 27, 2771, 4774, 1652, 784, 30, 2968, 44, 549, 2780, 27, 967, 20758, 301, 291, 1207, 4031, 4774, 280, 20758, 403, 890, 1652, 784, 32, 983, 293, 291, 4774, 32, 2121, 26, 6052, 12034, 403, 12232, 81, 14905, 81, 3197, 30, 2968, 32, 2613, 81, 983, 26, 2597, 9001, 403, 33800, 876, 291, 4774, 284, 320, 446, 2498, 2771, 2192, 81, 1855, 26, 3, 1394, 46, 2420, 48, 301, 324, 1207, 1984, 280, 2179, 4482, 400, 313, 641, 555, 933, 32, 508, 33, 22397, 279, 31, 615, 33, 7971, 33, 10722, 33, 4984, 5263, 7516, 81, 12232, 81, 4530, 3188, 7971, 31, 106, 42, 40, 81, 40, 38, 31, 6876, 31, 4783, 31, 10628, 32, 5366, 32, 6680, 20, 324, 1093, 324, 1207, 1789, 280, 10980, 37899, 81, 10923, 400, 638, 1816, 26, 965, 27, 1568, 2], "prompt_token_count": 152, "reference_codepoints": 64, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [225, 665, 894, 81, 371, 81, 1986, 81, 2613, 26, 784, 30, 3320, 711, 291, 337, 280, 5170, 42849, 26, 2613, 27, 584, 337, 32, 524, 26, 324, 313, 525, 555, 1499, 32, 2763, 32, 508, 33, 858, 33, 858, 32, 916, 392, 324, 313, 2788, 392, 324, 4826, 7814, 1286, 31, 681, 563, 313, 878, 33, 916, 3918, 324, 2287, 47, 36, 34, 34, 30, 324], "continuation_token_count": 67, "decoded": " def test_get_response_cache(self, cache):\n o = ResponseCacheManager(cache)\n\n o.put(\n \"http://www.example.com/test/test.html\",\n \"GET\",\n headers={\"content-type\": \"text/html\"},\n status=200,\n ", "decoded_codepoints": 258, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/spiders/test_cache.py", "example_id": "00053d33b4fdf7666c071d4c1ccb92217ce865f0d408b84000ce447e54a9c91d", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1548, 30, 291, 2287, 47, 1517, 30, 291, 5966, 347, 2950, 392, 291, 7328, 347, 3310, 31, 42, 392, 291, 21032, 34444, 291, 4826, 7814, 1286, 31, 681, 563, 313, 878, 33, 916, 3918, 291, 1326, 81, 5078, 7814, 496, 31, 4867, 563, 313, 858, 3918, 291, 1411, 347, 2788, 392, 284, 829, 478, 203, 823, 2108, 1397, 42849, 44, 3017, 3, 106, 35, 36, 78, 106, 35, 37, 78, 106, 35, 38, 20, 324, 4707, 280, 617, 2682, 81, 1986, 26, 1548, 47, 84, 13950, 916, 48, 858, 1795, 377, 916, 19830, 1064, 2014, 3320, 32, 524, 26, 4426, 30, 4707, 30, 313, 2788, 657, 324, 34264, 280, 2014, 3320, 32, 371, 26, 4426, 27, 1064, 1201, 34264, 438, 646, 1665, 324, 1201, 34264, 32, 965, 610, 337, 2], "prompt_token_count": 131, "reference_codepoints": 256, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [4788, 32, 3359, 922, 3613, 2891, 2272, 1026, 334, 8250, 44, 8943, 32, 3359, 922, 3613, 2891, 2272, 1026, 334], "continuation_token_count": 20, "decoded": "vi.fn().mockReturnThis(),\n cancel: vi.fn().mockReturnThis(),\n ", "decoded_codepoints": 63, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/auth-commands.test.ts", "example_id": "000540110eed1e19faa1659221297ecd6986c7a4d89e778d50f4689acae789a2", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 334, 4040, 81, 10539, 81, 45077, 81, 22812, 81, 18382, 44, 225, 39, 30, 203, 18284, 203, 203, 4788, 32, 3613, 15382, 2304, 33, 17095, 32, 754, 392, 1404, 532, 5989, 334, 4562, 1151, 44, 8943, 32, 3359, 1026, 203, 18284, 203, 203, 913, 4395, 19855, 280, 301, 334, 1477, 44, 8943, 32, 3359, 922, 3613, 2891, 2272, 1026, 334, 4719, 44, 8943, 32, 3359, 922, 3613, 2891, 2272, 1026, 334, 24490, 44, 8943, 32, 3359, 922, 3613, 2891, 2272, 1026, 334, 3547, 44, 225, 3, 1244, 44, 1404, 532, 4395, 19855, 10536, 203, 203, 913, 4395, 2961, 280, 8943, 32, 3359, 922, 3613, 17923, 882, 26, 6376, 293, 203, 4788, 32, 3613, 440, 1676, 392, 1404, 532, 5989, 1244, 44, 33326, 1132, 44, 8665, 9795, 532, 4395, 2961, 14705, 1132, 27, 10536, 203, 203, 4788, 32, 3613, 15382, 9777, 32, 754, 392, 1404, 532, 5989, 10070, 81, 10923, 81, 779, 44, 313, 858, 31, 1580, 31, 314, 20, 10536, 203, 4788, 32, 3613, 15382, 2], "prompt_token_count": 167, "reference_codepoints": 64, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [5426, 3050, 48, 280, 301, 284, 660, 1780, 44, 802, 30, 284, 660, 1650, 44, 629, 30, 284, 660, 3361, 44, 13630, 3050, 30, 284, 660, 3361, 1284, 44, 629, 30, 284, 660], "continuation_token_count": 33, "decoded": "SectionBody> = {\n const title: string,\n const index: int,\n const body: SectionBody,\n const bodyIndex: int,\n const", "decoded_codepoints": 128, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/parsers/requirement-blocks.ts", "example_id": "00054382332c06bf60eaf3c13a75151e9cd53257619884648cbd8dad7a91b4a0", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 262, 8844, 44, 8844, 10136, 32, 6264, 30, 397, 6556, 44, 6556, 10136, 32, 6264, 30, 397, 23008, 44, 23008, 10136, 32, 6264, 30, 284, 801, 334, 1472, 203, 111, 203, 203, 1126, 6122, 26412, 26620, 26, 4446, 44, 802, 10012, 296, 942, 6275, 44, 1905, 28237, 9803, 46, 800, 30, 13630, 3050, 48, 301, 334, 660, 1056, 44, 9803, 46, 800, 30, 225, 3, 415, 308, 40326, 6275, 77, 91, 1130, 4036, 45, 284, 660, 345, 280, 5430, 77, 91, 997, 2872, 26090, 26, 433, 5421, 101, 29, 13157, 29, 9501, 39593, 284, 415, 308, 95, 27, 301, 397, 10193, 32, 2018, 1371, 1780, 44, 345, 77, 36, 997, 5464, 1026, 1650, 44, 595, 1122, 284, 320, 334, 320, 334, 436, 308, 730, 595, 280, 225, 34, 45, 595, 333, 10193, 32, 1322, 45, 595, 1987, 301, 284, 660, 1550, 280, 10193, 77, 91, 970, 284, 660, 2354, 280, 10193, 77, 91, 2], "prompt_token_count": 155, "reference_codepoints": 128, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [32, 2413, 27, 357, 202, 862, 32, 1324, 26, 102, 30, 225, 43, 34, 30, 8444, 32], "continuation_token_count": 17, "decoded": ".URL)\n\t\tassert.Equal(t, 90, cfg.", "decoded_codepoints": 32, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/hub/heartbeat/heartbeat_test.go", "example_id": "0005530a4899f5e187ab52e9c6cf259452a1ac75ec76000505983f6ef2b510ab", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 47, 3420, 26, 678, 802, 27, 308, 800, 30, 1560, 27, 301, 355, 202, 104, 30, 3835, 1025, 4533, 77, 678, 79, 355, 202, 601, 354, 30, 3835, 357, 202, 111, 1314, 202, 11282, 1025, 39494, 32, 1812, 26, 725, 32, 1290, 30, 622, 6052, 27, 357, 202, 1981, 32, 29950, 26, 102, 30, 42470, 27, 357, 202, 4687, 1025, 42470, 32, 936, 1063, 346, 357, 202, 862, 32, 1324, 26, 102, 30, 313, 641, 555, 38570, 32, 2763, 32, 508, 33, 7075, 392, 8444, 32, 2413, 27, 357, 202, 862, 32, 1324, 26, 102, 30, 225, 43, 34, 30, 8444, 32, 3, 32, 1868, 7979, 30, 8444, 32, 1868, 27, 203, 202, 1748, 203, 111, 203, 203, 1298, 2108, 4863, 2788, 43279, 3797, 1290, 1527, 1996, 26, 102, 319, 4266, 32, 70, 27, 301, 203, 202, 725, 1025, 537, 1006, 4599, 26, 102, 27, 203, 202, 1786, 1025, 44795, 32, 1812, 2059, 26, 525, 32, 39101, 26, 1298, 26, 105, 1913, 32, 21725, 30, 540, 319, 525, 32, 1104, 27, 301, 357, 202, 862, 32, 1324, 26, 102, 30, 1913, 32, 1868, 936, 30, 540, 32, 1868, 27, 357, 202, 862, 32, 55, 2], "prompt_token_count": 196, "reference_codepoints": 32, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [351, 320, 813, 301, 291, 3366, 1139, 81, 24217, 6084, 2033, 5889, 81, 12881], "continuation_token_count": 14, "decoded": " } else {\n COFF_ParsedSymbol resolve_parsed", "decoded_codepoints": 66, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/linker/lnk_symbol_table.c", "example_id": "00055dd5afb3a096fbff5382b27e18b64224d702862f615282cdb54f12d5d4c6", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 362, 2264, 6977, 81, 12881, 280, 17656, 93, 81, 12881, 81, 1070, 81, 7010, 26, 7010, 293, 397, 3366, 1139, 81, 6084, 882, 37021, 620, 225, 6977, 81, 15576, 280, 281, 1719, 81, 15576, 81, 1070, 81, 12881, 81, 7010, 26, 7010, 81, 12881, 293, 397, 415, 308, 7010, 81, 15576, 610, 3366, 1139, 81, 6084, 882, 37021, 81, 20984, 27, 301, 291, 28933, 61, 81, 3273, 6084, 2084, 5889, 280, 301, 34, 1255, 203, 3, 490, 301, 616, 3366, 1139, 81, 24217, 6084, 2033, 5889, 81, 12881, 280, 17656, 93, 81, 12881, 81, 7010, 81, 1070, 81, 331, 486, 81, 7010, 81, 2875, 26, 5284, 32, 2067, 30, 5889, 32, 7010, 81, 2875, 293, 616, 3366, 1139, 81, 6084, 882, 37021, 620, 5889, 81, 15576, 280, 281, 1719, 81, 15576, 81, 1070, 81, 12881, 81, 7010, 26, 5284, 81, 12881, 293, 616, 415, 308, 5284, 81, 2], "prompt_token_count": 149, "reference_codepoints": 64, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [27, 397, 320, 397, 2615, 347, 5636, 5463], "continuation_token_count": 8, "decoded": ")\n }\n className=\"flex flex", "decoded_codepoints": 36, "document_id": "OpenCut-app/OpenCut@4d8c49ed0706c4dc145361e01c6b1f1a87cbb863:apps/web/src/components/ui/button-group.tsx", "example_id": "000564eefdb8631c9b63f2aa9262cc8ce83044756420dd446cbd257ab7159647", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 285, 30, 334, 2417, 2962, 203, 10696, 3475, 32, 42258, 46, 20, 507, 413, 549, 28704, 3913, 46, 5139, 3454, 1564, 41729, 5103, 301, 334, 442, 308, 284, 333, 507, 397, 4203, 347, 1363, 20, 397, 706, 31, 9040, 347, 1640, 31, 1363, 20, 397, 706, 31, 16536, 1279, 16536, 111, 397, 2615, 1279, 4977, 26, 1640, 1564, 41729, 1371, 14103, 1790, 3, 261, 1681, 334, 829, 203, 111, 203, 203, 1126, 7411, 1564, 1031, 1371, 334, 2615, 30, 334, 2908, 30, 334, 2417, 2962, 203, 10696, 793, 3121, 32, 42258, 46, 20, 507, 413, 27, 301, 334, 442, 793, 3121, 1371, 284, 1244, 14571, 44, 313, 507, 392, 284, 5576, 44, 3991, 3913, 46, 20, 507, 10614, 397, 301, 291, 2615, 44, 13011, 26, 616, 313, 5636, 3946, 31, 2390, 15948, 31, 36, 225, 2], "prompt_token_count": 137, "reference_codepoints": 32, "repo": "OpenCut-app/OpenCut", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [3359, 4251, 3613, 17923, 882, 1371, 324, 18767, 44, 861, 30, 324, 2276, 44, 225, 35, 30, 324, 803, 81, 4243, 44, 2107, 17972, 32, 1645, 2188, 324, 1760, 44, 13198, 605, 31, 858, 314, 347, 19716, 1446, 370, 291, 1122, 291, 2014, 1424, 26, 2501, 32, 3359, 4251, 3613, 17923, 882, 1371, 324, 18767, 44, 861, 30], "continuation_token_count": 58, "decoded": "fn()).mockResolvedValue({\n uploaded: true,\n files: 1,\n file_names: ['receipt.png'],\n target: '[data-testid=\"wrong\"]',\n });\n await expect(command.fn()).mockResolvedValue({\n uploaded: true,", "decoded_codepoints": 256, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/mercury/mercury.test.js", "example_id": "0005669ca12d01f559e07109ba714118e072fa9eb4b76a4d2f75b520febb81b3", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 93, 2009, 324, 12946, 383, 1078, 1026, 324, 1487, 8811, 1026, 324, 5021, 1394, 26, 1508, 471, 291, 2505, 301, 324, 7623, 3839, 44, 8943, 32, 3359, 922, 3613, 17923, 882, 1371, 18767, 44, 861, 30, 2276, 44, 225, 35, 30, 803, 81, 4243, 44, 2107, 2455, 32, 1645, 785, 7305, 291, 1122, 291, 2014, 1424, 26, 2501, 32, 3, 1026, 324, 5021, 1394, 26, 1508, 471, 291, 2505, 301, 324, 7623, 3839, 44, 8943, 32, 3359, 922, 3613, 17923, 882, 1371, 400, 18767, 44, 861, 30, 400, 2276, 44, 225, 35, 30, 400, 803, 81, 4243, 44, 2107, 17972, 32, 1645, 2188, 400, 1760, 44, 13198, 605, 31, 858, 314, 347, 19716, 1446, 370, 284, 2], "prompt_token_count": 118, "reference_codepoints": 256, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [202, 10340, 32, 1945, 26, 5057, 27, 478, 202, 306, 3456, 688, 322, 5216, 884, 3809, 32, 203, 202, 862, 32, 1324, 26, 102, 30, 225, 35, 30, 2069, 26, 5057, 490, 478, 202, 862, 32, 1324, 26, 102, 30, 225, 36, 30, 2069, 26, 5057, 490, 478], "continuation_token_count": 48, "decoded": "\trunner.run(events)\n\n\t// Check that the events are correct.\n\tassert.Equal(t, 1, len(events))\n\n\tassert.Equal(t, 2, len(events))\n\n", "decoded_codepoints": 128, "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/interrupt_test.go", "example_id": "000570da950ae1e723108fe778644958dba39066f44a9dbe06e4685e68980e15", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 973, 322, 21291, 44, 399, 438, 2935, 432, 551, 461, 390, 32, 203, 202, 4867, 51, 30, 1137, 1025, 1756, 1721, 41141, 26, 2095, 30, 7669, 51, 30, 1605, 6143, 109, 4867, 52, 30, 7669, 53, 1748, 203, 202, 862, 32, 15109, 26, 102, 30, 1137, 27, 478, 202, 306, 4489, 322, 894, 203, 202, 10340, 1025, 3136, 7981, 26, 2095, 30, 37183, 1063, 109, 357, 202, 6143, 44, 2264, 7669, 51, 30, 357, 202, 2140, 1943, 2780, 44, 537, 3758, 2780, 1026, 203, 202, 1748, 203, 3, 357, 202, 325, 653, 1253, 301, 355, 202, 2969, 357, 202, 111, 357, 202, 5057, 280, 5489, 26, 5057, 30, 1692, 27, 203, 202, 111, 478, 202, 306, 2688, 1424, 225, 37, 8872, 5216, 308, 51, 396, 52, 30, 551, 396, 51, 30, 399, 396, 53, 27, 461, 225, 35, 11264, 1692, 645, 390, 32, 203, 202, 862, 32, 1324, 26, 102, 30, 225, 38, 30, 2069, 26, 5057, 490, 478, 202, 15346, 1151, 1025, 5216, 77, 37, 79, 203, 202, 862, 32, 29950, 26, 102, 30, 11264, 1151, 32, 1711, 32, 19497, 87, 2], "prompt_token_count": 184, "reference_codepoints": 128, "repo": "cloudwego/eino", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [47, 14225, 26, 355, 202, 4867, 81, 314, 347, 4867, 81, 314, 392], "continuation_token_count": 13, "decoded": "= Agent(\n\t\t\tagent_id=\"agent_id\",", "decoded_codepoints": 32, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/browser/test_tabs.py", "example_id": "000576b8bdf0bf27e1afd5e7894b3e9d45095681b09d62a2127c4acf8345683e", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 202, 20, 1978, 81, 15848, 563, 313, 7371, 2899, 392, 603, 202, 20, 1141, 563, 428, 577, 202, 109, 1379, 202, 20, 5087, 563, 301, 1488, 202, 20, 878, 563, 313, 24724, 13197, 225, 38, 17002, 26671, 631, 2876, 5868, 392, 1488, 202, 20, 3127, 563, 861, 1379, 202, 111, 577, 202, 111, 603, 202, 79, 355, 202, 111, 355, 202, 37616, 357, 202, 79, 1314, 202, 3613, 81, 611, 95, 280, 1487, 81, 3613, 81, 611, 95, 26, 3543, 47, 3543, 27, 1314, 202, 4867, 225, 3, 10487, 26671, 631, 461, 6144, 5427, 1603, 25849, 17771, 370, 355, 202, 611, 95, 47, 3613, 81, 611, 95, 30, 355, 202, 7128, 81, 2848, 47, 7128, 81, 2848, 30, 357, 202, 27, 1314, 202, 21, 4489, 623, 5868, 429, 1395, 6153, 4797, 225, 36, 10135, 357, 202, 1270, 44, 355, 202, 6446, 280, 2014, 24495, 32, 1684, 81, 979, 26, 4867, 32, 1945, 26, 1449, 81, 7439, 47, 39, 471, 5868, 47, 35, 36, 34, 27, 603, 2], "prompt_token_count": 168, "reference_codepoints": 32, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [5127, 32, 1517, 81, 687, 610, 225, 36, 34, 34, 291, 1201, 19990, 610, 3037, 641, 555, 2763, 32, 508, 33, 85, 1446, 446, 665, 894, 81, 2988, 81, 3963, 81, 363, 81, 10407, 81, 979, 81, 270, 23182, 81, 979, 81, 270, 23182, 81, 979, 81, 270, 23182, 81, 979, 81, 270, 23182, 81, 979, 81, 270, 23182, 81, 979, 81, 270, 23182, 81, 979, 81, 270, 23182, 81, 979, 81, 270, 23182, 81, 979, 81, 270, 23182, 81, 979, 81, 270, 23182, 81, 979, 81, 270, 23182, 81, 979, 81, 270, 23182, 81, 979], "continuation_token_count": 96, "decoded": " resp.status_code == 200\n assert urls == [\"https://example.com/c\"]\n\n def test_custom_tags_and_attrs_for_styling_for_styling_for_styling_for_styling_for_styling_for_styling_for_styling_for_styling_for_styling_for_styling_for_styling_for_styling_for", "decoded_codepoints": 257, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/spiders/test_links.py", "example_id": "000591d6930441fc91b26e51bff20ccf516163b2a443b1956c5fb8b464577ae7", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1548, 48, 324, 333, 2172, 772, 83, 976, 3784, 2172, 31, 1204, 413, 96, 377, 83, 855, 2172, 48, 324, 333, 1831, 772, 83, 976, 3784, 1831, 31, 1204, 413, 95, 377, 83, 855, 1831, 48, 291, 576, 1548, 855, 916, 48, 291, 1524, 291, 5127, 280, 617, 2682, 81, 1986, 26, 916, 27, 291, 19990, 280, 6116, 16653, 26, 20757, 81, 2079, 347, 1831, 1895, 8281, 26, 5243, 27, 291, 1201, 3, 1548, 855, 916, 48, 291, 1524, 291, 5127, 280, 617, 2682, 81, 1986, 26, 916, 27, 291, 19990, 280, 6116, 16653, 26, 20757, 81, 16689, 1057, 306, 507, 13283, 314, 347, 1286, 20201, 8281, 26, 5243, 27, 291, 1201, 19990, 610, 3037, 641, 555, 2763, 32, 508, 33, 85, 1446, 478, 203, 823, 2108, 6751, 18724, 44, 284, 665, 894, 81, 2988, 81, 3963, 81, 363, 81, 10407, 81, 979, 81, 270, 2], "prompt_token_count": 147, "reference_codepoints": 256, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [261, 415, 1938, 81, 1338, 32, 297, 81, 731, 2262, 528, 1938, 81, 1338, 32, 1826, 81, 731, 346, 528, 415, 11549, 333, 630, 1114, 1163, 32, 268, 3926, 81, 5457, 44, 715, 1245, 32, 1338, 26, 88, 20, 435, 3926, 299, 301, 2132, 32, 1684, 81, 9003, 111, 21850, 715, 630, 1114, 268, 3926, 81, 1637, 26, 2132], "continuation_token_count": 59, "decoded": " if page_info.is_error():\n page_info.mark_error()\n if attempt < self._config.requeue_timeout:\n log.info(f\"Requeueing {params.wait_selector}...\")\n self._requeue_page(params", "decoded_codepoints": 257, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/_browsers/_controllers.py", "example_id": "00059e0e387d65ed1a0b6e5cc36586c51838d9e74f91342c152e0c48e53a6d34", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 4722, 30, 2803, 32, 4573, 81, 17431, 27, 715, 2940, 3268, 619, 484, 44, 225, 588, 30279, 44, 1289, 6369, 1014, 1245, 32, 731, 26, 88, 20, 924, 10774, 436, 9182, 301, 2132, 32, 1684, 81, 9003, 10696, 301, 87, 8474, 3688, 1938, 32, 1684, 81, 979, 81, 5457, 26, 2132, 32, 1684, 27, 5678, 3, 5866, 563, 7664, 835, 715, 20946, 81, 46456, 47, 23021, 81, 46456, 30, 528, 829, 528, 442, 1789, 2110, 2940, 3268, 619, 484, 44, 528, 1938, 81, 1338, 32, 1826, 81, 731, 346, 528, 415, 11549, 333, 630, 1114, 1163, 32, 268, 2], "prompt_token_count": 100, "reference_codepoints": 256, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [30, 324, 313, 2245, 81, 1637, 563, 2519, 81], "continuation_token_count": 9, "decoded": ",\n \"show_page\": show_", "decoded_codepoints": 32, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/core/shell.py", "example_id": "0005a8d092bb6d6bd38ea24202e285f2d49175c9d9f970057bcf912da9e7b93a", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 262, 313, 6686, 4413, 107, 81, 5140, 563, 14680, 4413, 107, 81, 5140, 30, 324, 313, 15702, 4413, 107, 22662, 563, 630, 3667, 15702, 4413, 107, 22662, 30, 324, 313, 4439, 563, 27556, 30, 324, 313, 1637, 563, 630, 32, 1637, 30, 324, 313, 1986, 563, 630, 32, 1637, 30, 324, 313, 5646, 563, 630, 32, 5646, 30, 324, 313, 1071, 563, 2519, 81, 1637, 3, 563, 630, 1114, 9511, 81, 3922, 32, 2208, 30, 324, 313, 9511, 36, 48496, 563, 10230, 36, 48496, 30, 324, 313, 4756, 563, 630, 32, 2245, 81, 4756, 30, 291, 320, 446, 665, 2519, 81, 4756, 26, 784, 711, 225, 588, 30279, 44, 1289, 6369, 291, 1524, 4311, 3049, 2471, 2993, 291, 1459, 26, 784, 32, 12006, 1157, 446, 665, 1477, 26, 784, 711, 225, 588, 1148, 481, 2], "prompt_token_count": 136, "reference_codepoints": 32, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [225, 309, 47, 101, 32, 3227, 440, 11468, 392, 18474, 657, 334, 309, 47, 101, 32, 3227, 440, 11468, 392, 18474, 657, 334, 309, 47, 101, 32, 3227, 440, 11468, 392, 18474, 657, 334, 309, 47, 101, 32, 3227, 440, 11468, 392, 18474, 657, 334, 309, 47, 101, 32, 3227, 440, 11468, 392, 18474, 657, 334, 309, 47, 101, 32, 3227, 440, 11468, 392, 18474, 657, 334, 309, 47, 101, 32, 3227, 440, 11468, 392, 18474, 657, 334, 309, 47, 101, 32, 3227, 440, 11468, 392, 18474, 657, 334, 309, 47, 101, 32, 3227, 440, 11468, 392, 18474, 657, 334, 309, 47], "continuation_token_count": 102, "decoded": " s=s.replace(\"\\\\\\\\\", \"\\\\\")\n s=s.replace(\"\\\\\\\\\", \"\\\\\")\n s=s.replace(\"\\\\\\\\\", \"\\\\\")\n s=s.replace(\"\\\\\\\\\", \"\\\\\")\n s=s.replace(\"\\\\\\\\\", \"\\\\\")\n s=s.replace(\"\\\\\\\\\", \"\\\\\")\n s=s.replace(\"\\\\\\\\\", \"\\\\\")\n s=s.replace(\"\\\\\\\\\", \"\\\\\")\n s=s.replace(\"\\\\\\\\\", \"\\\\\")\n s=", "decoded_codepoints": 256, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/answer.sh", "example_id": "0005a9e996cc9e936cb4ee3391eed5b0b832d52fe31f8cde5f69d20a0465a178", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1941, 4844, 40734, 645, 7592, 803, 11555, 397, 442, 225, 35, 284, 8058, 334, 8058, 719, 415, 653, 816, 95, 611, 410, 769, 3780, 364, 769, 1347, 541, 3941, 5474, 866, 1615, 284, 1048, 313, 1318, 4723, 7592, 803, 438, 646, 2080, 7402, 11555, 284, 442, 225, 35, 334, 8058, 719, 442, 225, 34, 203, 111, 203, 203, 11731, 38075, 882, 346, 301, 719, 2196, 309, 12672, 35, 20, 719, 309, 9104, 101, 306, 23, 33, 1784, 111, 334, 3, 24, 12809, 347, 436, 398, 3801, 20, 719, 415, 3813, 3941, 853, 20, 16078, 428, 2867, 4977, 6769, 46017, 18154, 1615, 284, 1048, 313, 1318, 398, 426, 2677, 4881, 4799, 3498, 7125, 22, 12420, 11555, 284, 442, 225, 35, 334, 8058, 719, 415, 3813, 3941, 853, 20, 610, 319, 7362, 38977, 18154, 1615, 284, 1048, 313, 1318, 398, 426, 2677, 4881, 4799, 2064, 22002, 22, 12420, 2], "prompt_token_count": 148, "reference_codepoints": 256, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [21633, 30, 324, 3443, 81, 1338, 47, 2238], "continuation_token_count": 8, "decoded": "stdin,\n stream_info=stream", "decoded_codepoints": 37, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/__main__.py", "example_id": "0005b2ea3970ed3d367d84fb8b4b4b996e1914d0240d6ec6a104da6d8eeab9b0", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1690, 584, 3634, 283, 1746, 280, 7778, 1011, 3211, 26, 4898, 81, 5558, 47, 1132, 32, 539, 81, 5558, 30, 1115, 9802, 81, 5321, 27, 284, 813, 44, 291, 3634, 283, 1746, 280, 7778, 1011, 3211, 26, 4898, 81, 5558, 47, 1132, 32, 539, 81, 5558, 27, 446, 415, 2181, 32, 3607, 438, 1665, 44, 291, 1056, 280, 3634, 283, 1746, 32, 5954, 81, 2238, 26, 324, 5237, 32, 21633, 32, 3, 2238, 81, 1338, 30, 324, 4986, 81, 605, 81, 26780, 47, 1132, 32, 10504, 81, 605, 81, 26780, 30, 291, 829, 284, 813, 44, 291, 1056, 280, 3634, 283, 1746, 32, 5954, 26, 324, 2181, 32, 3607, 30, 3443, 81, 1338, 47, 2238, 81, 1338, 30, 4986, 81, 605, 81, 26780, 47, 1132, 32, 10504, 81, 605, 81, 26780, 291, 829, 446, 617, 2956, 81, 2024, 26, 1132, 30, 1056, 27, 478, 203, 589, 617, 2], "prompt_token_count": 149, "reference_codepoints": 32, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [1981, 463, 6008, 81, 4775, 895, 203, 913, 390, 15658, 81, 14263, 81, 3521, 280, 225, 34, 45, 203, 913, 390, 15658, 81, 14263], "continuation_token_count": 24, "decoded": "require('clean_exit');\nconst CLEAN_EXIT_CODE = 0;\nconst CLEAN_EXIT", "decoded_codepoints": 66, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:tests/test_mode_tracker_stdin.js", "example_id": "0005b4adbd19eb7565718ea8a7a95475fcf3e7e18202cecbc4bd147f1985a9c3", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 463, 983, 895, 203, 913, 2322, 280, 1205, 463, 500, 895, 203, 913, 5980, 280, 1205, 463, 2548, 895, 203, 913, 1201, 280, 1205, 463, 862, 895, 203, 913, 301, 16611, 4764, 320, 280, 1205, 463, 2661, 81, 2416, 895, 203, 203, 913, 11551, 2950, 81, 4065, 280, 1519, 32, 5284, 4064, 7781, 30, 31001, 370, 330, 1617, 370, 330, 12329, 370, 330, 85, 453, 37076, 31, 2816, 31, 13610, 32, 754, 895, 203, 913, 390, 15658, 81, 14263, 280, 225, 3, 1596, 301, 284, 2771, 473, 284, 5403, 3334, 284, 2549, 32, 751, 4199, 225, 25146, 2283, 426, 12833, 334, 320, 2368, 308, 87, 27, 301, 284, 3803, 3334, 284, 2549, 32, 731, 4199, 225, 14392, 250, 2283, 426, 12833, 284, 2549, 32, 731, 4199, 264, 2283, 87, 32, 1436, 12833, 334, 320, 203, 111, 203, 203, 4466, 32, 751, 463, 85, 453, 37076, 31, 2816, 31, 13610, 24621, 1048, 9933, 78, 96, 895, 203, 203, 306, 6830, 322, 22757, 11962, 225, 2], "prompt_token_count": 165, "reference_codepoints": 64, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [81, 452, 81, 22733, 26, 3140, 27, 610, 2799, 478, 203, 21, 40595], "continuation_token_count": 13, "decoded": "_to_xlsx(expected) == expected\n\n\n# ---------------------------------------------------------------------------", "decoded_codepoints": 110, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown-ocr/tests/test_xlsx_converter.py", "example_id": "0005b9eb08cb645cdc93288a1beb2f13974783df425c561ef15e5b24790033df", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 262, 29425, 21644, 523, 21644, 29342, 96, 20, 291, 29425, 21644, 523, 21644, 29342, 96, 20, 291, 29425, 21644, 523, 21644, 29342, 96, 20, 291, 29425, 21644, 523, 21644, 29342, 96, 20, 291, 29425, 46573, 44, 523, 21644, 29342, 96, 78, 96, 20, 291, 313, 1482, 27648, 328, 458, 13063, 3491, 96, 78, 96, 20, 291, 11570, 77, 1658, 546, 3754, 10854, 96, 45878, 81, 43416, 81, 6016, 81, 35, 36, 37, 38, 39, 78, 96, 77, 2102, 546, 3754, 6603, 20, 284, 829, 284, 1201, 617, 5954, 3, 5877, 430, 203, 21, 816, 3246, 106, 81, 12565, 81, 2242, 32, 22733, 203, 21, 40595, 478, 203, 589, 894, 81, 22733, 81, 12565, 81, 2242, 26, 15762, 44, 7502, 43416, 1183, 27, 967, 1665, 44, 284, 2799, 280, 308, 291, 313, 433, 546, 104, 2], "prompt_token_count": 136, "reference_codepoints": 64, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [31, 11398, 26836, 58, 3493, 461, 629, 35, 40, 13292, 9229, 308, 1382, 4905, 1760, 1755, 3312, 3493, 27, 203, 319, 429, 506, 12856, 31, 42609, 2467, 16540, 308, 1206, 5253, 428, 35, 30, 34, 30, 34, 46470], "continuation_token_count": 38, "decoded": "- Tests BOTH bit and int16 quantizers (the existing target only tests bit)\n * - Fuzz-controlled query vectors (not fixed [1,0,0,...", "decoded_codepoints": 131, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:tests/fuzz/rescore-interleave.c", "example_id": "0005ce65e52004e5e14fe1bf91978110adf9a4b8a922d5cdf8e8720f20f10d27", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 292, 1974, 1340, 1519, 688, 322, 4905, 736, 1262, 31, 14663, 32, 85, 3980, 1464, 32, 203, 319, 203, 319, 3891, 21005, 645, 736, 1262, 31, 14663, 32, 85, 44, 203, 319, 429, 11398, 26836, 58, 3493, 461, 629, 42, 13292, 9229, 308, 1382, 4905, 1760, 1755, 3312, 3493, 27, 203, 319, 429, 506, 12856, 31, 42609, 2467, 16540, 308, 1206, 5253, 428, 35, 30, 34, 30, 34, 46470, 1130, 203, 319, 429, 3, 225, 13292, 1649, 5258, 27, 203, 319, 429, 4803, 43904, 1224, 5804, 3733, 33094, 372, 35655, 322, 11589, 81, 268, 1676, 1519, 203, 319, 261, 1412, 617, 575, 1262, 81, 24897, 5760, 1159, 2583, 8128, 33, 10454, 203, 569, 203, 410, 26333, 56, 11964, 4501, 1006, 3582, 1612, 26, 913, 1727, 42, 81, 102, 319, 605, 30, 1334, 81, 102, 1334, 27, 301, 334, 415, 308, 891, 333, 225, 42, 27, 442, 225, 34, 45, 719, 629, 7631, 45, 664, 2], "prompt_token_count": 156, "reference_codepoints": 128, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [22, 9328, 334, 2196, 4921, 12672, 1515, 20, 334, 2196, 5585, 12672, 3801, 20, 334, 2196, 20239, 7203], "continuation_token_count": 18, "decoded": "$iso\n local dir=\"$dir\"\n local desc=\"$desc\"\n local legacyInstall", "decoded_codepoints": 66, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/install.sh", "example_id": "0005d0c283dc97cad5c77e58f31d76bb8266df96cf8c9746d5de2990f5e7d212", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1231, 372, 6571, 13600, 11555, 962, 442, 225, 35, 284, 8058, 446, 41408, 9456, 9328, 1338, 429, 86, 429, 91, 3941, 761, 20, 523, 12109, 429, 96, 330, 101, 33, 6795, 804, 44, 434, 98, 683, 1276, 41408, 5487, 284, 10194, 429, 88, 3941, 761, 20, 1276, 17161, 313, 5288, 372, 3345, 14016, 19687, 803, 44, 398, 761, 20, 719, 8058, 719, 442, 225, 34, 203, 111, 203, 203, 470, 7090, 346, 301, 719, 2196, 804, 12672, 35, 20, 334, 2196, 26457, 47, 3, 19, 6869, 3941, 613, 9492, 866, 1615, 446, 1135, 6313, 314, 4781, 3845, 328, 397, 313, 4463, 36, 93, 41731, 829, 261, 20239, 347, 36, 93, 20, 10368, 397, 313, 4463, 13293, 41731, 829, 261, 20239, 347, 13293, 20, 10368, 397, 313, 4463, 36, 34, 34, 37, 41731, 829, 20239, 347, 36, 93, 37, 20, 10368, 284, 2813, 329, 446, 415, 428, 429, 96, 3941, 18244, 20, 4028, 1615, 397, 415, 653, 20239, 7203, 3941, 9328, 20, 3941, 1515, 20, 3941, 3801, 20, 3941, 18244, 866, 1615, 2], "prompt_token_count": 173, "reference_codepoints": 64, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [30, 2075, 32, 7128, 293, 334, 2549, 32, 751, 10920, 334, 2549, 32, 751, 26, 1970, 32, 3534, 440, 4282, 883, 2464, 793, 22714, 7049, 41, 5359, 34222, 203, 111, 203, 203, 1126, 4436, 5324, 26, 7128, 44, 1905, 27, 301, 334, 660, 2404, 280, 2014, 4436, 5324, 26, 7128, 293, 334, 415, 1429, 1956, 27, 301, 284, 2164, 32, 4775, 26, 35, 293, 334, 320, 334, 2549, 32, 751], "continuation_token_count": 70, "decoded": ", options.browser);\n console.log(\"\");\n console.log(pc.dim(\"You can now use authenticated Context7 features.\"));\n}\n\nfunction performLogin(browser: boolean) {\n const token = await performLogin(browser);\n if (!token) {\n process.exit(1);\n }\n console.log", "decoded_codepoints": 258, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/commands/auth.ts", "example_id": "0005d1cac6b9343645a780c73767bd3f04730bd73c70e50208d293cf590d92dd", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 924, 27, 2549, 32, 731, 26, 1970, 32, 1092, 26, 731, 32, 1436, 876, 397, 442, 744, 45, 284, 320, 334, 320, 719, 10774, 19855, 32, 5066, 26, 1970, 32, 1092, 440, 1227, 22054, 2876, 27869, 34222, 334, 442, 744, 45, 203, 111, 203, 203, 4396, 667, 6207, 2019, 26, 2184, 44, 301, 5427, 44, 1905, 47701, 4664, 46, 1117, 48, 301, 334, 4562, 1151, 440, 2501, 20, 3, 264, 442, 45, 334, 320, 334, 4233, 10911, 473, 719, 660, 2404, 280, 2014, 4436, 5324, 26, 2184, 32, 7128, 293, 334, 415, 1429, 1956, 27, 301, 284, 2164, 32, 4775, 26, 35, 293, 334, 320, 334, 2549, 32, 751, 10920, 334, 2549, 32, 751, 26, 1970, 32, 3534, 440, 4282, 883, 2464, 793, 22714, 7049, 41, 5359, 34222, 203, 111, 203, 203, 1126, 20641, 2019, 2262, 763, 225, 2], "prompt_token_count": 140, "reference_codepoints": 256, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [30, 330, 1318, 9320, 370, 225, 38, 36, 37, 30, 225, 38, 32, 39, 471, 334, 308, 43, 30, 13198, 43, 16249, 330, 88, 41415, 370, 330, 1318, 9320, 370, 225, 38, 36, 37, 30, 225, 38, 32, 39, 471, 334, 308, 35, 34, 30, 13198, 35, 34, 16249, 330, 19252, 5782, 370, 330, 1318, 9320, 370, 225, 38, 36, 37, 30, 225, 38, 32, 39, 471, 334, 308, 35, 35, 30, 13198, 35, 35, 16249, 330, 331, 1967, 107, 370, 330, 1318, 9320, 370, 225, 38, 36, 37, 30, 225, 38, 32, 39, 471, 334, 308, 35, 36, 30, 13198, 35, 36, 16249, 330, 19252, 5782, 370, 330, 1318, 9320, 370, 225, 38, 36, 37, 30, 225, 38, 32, 39, 471, 334, 308, 35, 37, 30, 13198, 35, 37, 16249, 330, 331, 1967, 107, 370, 330, 1318, 9320], "continuation_token_count": 139, "decoded": ", 'The Matrix', 423, 4.5),\n (9, '[9]', 'fantasy', 'The Matrix', 423, 4.5),\n (10, '[10]', 'horror', 'The Matrix', 423, 4.5),\n (11, '[11]', 'comedy', 'The Matrix', 423, 4.5),\n (12, '[12]', 'horror', 'The Matrix', 423, 4.5),\n (13, '[13]', 'comedy', 'The Matrix", "decoded_codepoints": 262, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:test.sql", "example_id": "0005e34babbc84de225e74fc05ed520d7fb6fcc16e392b02cf3912a4bf27e474", "language": "sql", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 292, 559, 2052, 44, 886, 506, 9620, 4798, 432, 322, 32894, 370, 225, 36, 35, 34, 30, 225, 38, 32, 36, 471, 334, 308, 39, 30, 13198, 39, 16249, 330, 2812, 672, 370, 330, 1045, 701, 468, 2465, 1606, 1565, 860, 370, 225, 43, 37, 30, 225, 37, 32, 38, 471, 334, 308, 40, 30, 13198, 40, 16249, 330, 19252, 5782, 370, 330, 30332, 3176, 672, 370, 225, 35, 40, 41, 30, 225, 38, 32, 41, 471, 334, 308, 41, 30, 13198, 41, 16249, 330, 331, 1967, 107, 370, 330, 1045, 380, 494, 278, 44, 886, 46957, 432, 559, 267, 34630, 89, 642, 107, 370, 225, 38, 42, 36, 30, 225, 36, 32, 43, 471, 334, 308, 42, 30, 13198, 42, 16249, 330, 545, 1037, 25, 3, 32, 42, 471, 334, 308, 35, 37, 30, 13198, 35, 37, 16249, 330, 545, 1037, 370, 330, 1318, 9320, 370, 225, 38, 36, 37, 30, 225, 38, 32, 39, 471, 334, 308, 35, 38, 30, 13198, 35, 38, 16249, 330, 88, 41415, 370, 330, 15923, 2699, 101, 21905, 10352, 266, 349, 370, 225, 36, 41, 39, 30, 225, 37, 32, 40, 471, 334, 308, 35, 39, 30, 13198, 35, 39, 16249, 330, 2812, 672, 370, 330, 35, 37, 349, 370, 225, 35, 43, 35, 30, 225, 38, 32, 38, 471, 334, 308, 35, 40, 30, 13198, 35, 40, 16249, 330, 19252, 5782, 370, 330, 1011, 18756, 101, 370, 225, 37, 35, 38, 30, 225, 38, 32, 37, 471, 334, 308, 35, 41, 30, 13198, 35, 41, 16249, 330, 331, 1967, 107, 370, 330, 3533, 20848, 7492, 370, 225, 41, 38, 30, 225, 2], "prompt_token_count": 271, "reference_codepoints": 256, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [32, 2524, 26, 6426, 81, 983, 293, 324, 320, 324], "continuation_token_count": 10, "decoded": ".join(repo_path);\n }\n ", "decoded_codepoints": 43, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/languages/conda.rs", "example_id": "0005ec0b638649a0d7ab95f13312ffdd1e1c958361d4191f709c71874a411bc3", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 3789, 81, 3515, 280, 20758, 403, 890, 26, 14768, 293, 324, 2443, 81, 3515, 400, 638, 626, 440, 3789, 657, 400, 638, 626, 10359, 98, 657, 400, 638, 626, 1652, 1338, 32, 2121, 81, 983, 27, 400, 638, 1132, 1652, 7133, 32, 12187, 81, 10950, 293, 324, 415, 1207, 4185, 26, 6426, 81, 983, 27, 280, 11962, 32, 6426, 81, 983, 3, 32, 1700, 81, 1515, 26, 6426, 81, 983, 293, 324, 320, 324, 2443, 81, 3515, 400, 638, 1553, 26, 1508, 27, 400, 638, 2024, 346, 400, 638, 6240, 400, 638, 1819, 440, 5288, 372, 2443, 1336, 1804, 6440, 657, 12370, 291, 320, 584, 3099, 32, 20307, 81, 2121, 81, 983, 473, 446, 2], "prompt_token_count": 116, "reference_codepoints": 32, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [261, 6658, 44, 313, 465, 316, 78, 5441, 6042], "continuation_token_count": 9, "decoded": " bad: \"import re\\ndef validate", "decoded_codepoints": 32, "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:benchmarks/robustness-audit.js", "example_id": "0005eeba82b470790d4e10324df05683a09623329245071b029021ee24198245", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2188, 284, 13012, 44, 330, 2538, 312, 4865, 667, 688, 28896, 600, 17409, 38, 2965, 6418, 284, 6792, 44, 3813, 710, 35, 43, 36, 32, 35, 40, 42, 32, 35, 32, 35, 2188, 861, 614, 20463, 34, 32, 34, 32, 34, 32, 34, 2188, 861, 614, 20463, 36, 39, 39, 32, 36, 39, 39, 32, 36, 39, 39, 32, 36, 39, 39, 2188, 861, 614, 20463, 43, 43, 43, 32, 43, 43, 43, 32, 43, 43, 43, 32, 43, 43, 43, 2188, 901, 614, 20463, 36, 39, 40, 32, 35, 32, 35, 32, 35, 2188, 901, 614, 20463, 35, 32, 36, 32, 37, 2188, 901, 614, 20463, 8183, 2188, 901, 6137, 334, 3, 4635, 81, 12288, 38, 26, 101, 48775, 96, 264, 1596, 3491, 96, 351, 4749, 2468, 32, 21710, 38, 2438, 26, 101, 293, 442, 2933, 78, 96, 264, 2940, 3268, 44, 442, 3177, 370, 284, 6658, 44, 313, 465, 316, 78, 5441, 6042, 81, 12288, 38, 26, 101, 48775, 96, 264, 442, 1560, 26, 268, 32, 2872, 26, 100, 28249, 1736, 86, 109, 35, 30, 37, 24783, 41536, 86, 109, 35, 30, 37, 24783, 41536, 86, 109, 35, 30, 37, 24783, 41536, 86, 109, 35, 30, 37, 10598, 370, 309, 490, 20, 801, 203, 970, 203, 203, 1126, 3619, 52, 315, 2], "prompt_token_count": 215, "reference_codepoints": 32, "repo": "DietrichGebert/ponytail", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [958, 537, 5170, 26, 3265, 32, 8136], "continuation_token_count": 7, "decoded": " new Response(JSON.stringify", "decoded_codepoints": 34, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/lichess/lichess.test.js", "example_id": "0005f23ce01562c661b24a48a7f8e7c5909bef2cb58a0f782c11734d689ac05b", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 86, 44, 330, 10687, 31, 496, 370, 952, 44, 330, 13624, 1240, 370, 6869, 44, 861, 30, 291, 7305, 301, 2287, 44, 225, 36, 34, 34, 320, 4236, 291, 2014, 1424, 26, 3515, 32, 1298, 1371, 952, 44, 330, 13624, 1240, 25, 42709, 11592, 101, 32, 32000, 26, 2766, 1394, 924, 293, 284, 1122, 446, 561, 463, 98, 6758, 322, 4630, 31, 1066, 318, 24605, 619, 2663, 16923, 370, 2498, 1404, 532, 301, 334, 3, 32, 3359, 922, 3613, 17923, 882, 26, 890, 5170, 26, 3265, 32, 8136, 1371, 324, 804, 44, 330, 6060, 3840, 370, 324, 952, 44, 330, 7303, 3505, 370, 324, 25463, 44, 225, 35, 39, 38, 37, 34, 34, 34, 34, 34, 34, 34, 34, 34, 30, 324, 10925, 1076, 44, 225, 35, 41, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 30, 324, 2385, 44, 301, 1169, 44, 225, 35, 34, 34, 30, 8888, 44, 225, 39, 34, 30, 7699, 44, 225, 37, 34, 30, 5171, 44, 225, 36, 34, 801, 334, 2], "prompt_token_count": 172, "reference_codepoints": 32, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [225, 313, 2310, 563, 313, 1318, 1451, 372, 1015, 20, 400, 320, 324], "continuation_token_count": 13, "decoded": " \"description\": \"The number to add\"\n }\n ", "decoded_codepoints": 66, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:examples/rag_dynamic_tools_multi_turn/src/main.rs", "example_id": "00061b3643fddcdde314e180fe8fb6a11aa81e5489fca92648f4bbc82d9199c7", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 102, 392, 324, 313, 4642, 563, 301, 400, 313, 106, 563, 301, 528, 313, 681, 563, 313, 2171, 392, 528, 313, 2310, 563, 313, 1318, 1451, 372, 27799, 645, 20, 400, 801, 400, 313, 107, 563, 301, 528, 313, 681, 563, 313, 2171, 392, 4511, 3, 351, 320, 291, 1790, 284, 320, 446, 2498, 2771, 1476, 26, 291, 549, 784, 30, 291, 617, 1819, 44, 549, 2278, 34315, 403, 3732, 403, 3653, 1222, 30, 291, 2181, 44, 6609, 403, 3080, 30, 284, 829, 967, 4703, 46, 8171, 403, 2301, 30, 6609, 403, 924, 48, 301, 291, 1207, 1056, 280, 2181, 32, 106, 429, 2181, 32, 107, 45, 291, 6311, 26, 1267, 27, 284, 320, 203, 111, 203, 203, 3106, 10018, 55, 2], "prompt_token_count": 123, "reference_codepoints": 64, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [27, 301, 203, 202, 601], "continuation_token_count": 5, "decoded": ") {\n\treturn", "decoded_codepoints": 11, "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:lib/policy/expressions/environment.go", "example_id": "00061d57e16feaca2b5c029a5b7d7b260fe81503e88490bee907b8093688ec79", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1428, 26, 6386, 32, 1428, 64, 26, 4464, 490, 603, 202, 13431, 355, 202, 471, 357, 202, 471, 203, 202, 111, 478, 202, 1132, 280, 5489, 26, 1132, 30, 6410, 8006, 203, 202, 601, 25312, 32, 1812, 6052, 26, 1132, 8006, 203, 111, 203, 203, 306, 23917, 8727, 15633, 4706, 461, 8345, 4345, 1615, 47119, 600, 24963, 203, 306, 9919, 436, 6063, 32, 203, 1298, 23917, 26, 2121, 319, 3308, 32, 6052, 30, 1561, 802, 27, 308, 3308, 32, 5747, 3, 301, 357, 202, 601, 1302, 30, 1973, 32, 4309, 346, 203, 202, 111, 478, 202, 633, 30, 1973, 1025, 4533, 32, 2140, 26, 38989, 27, 203, 202, 325, 1973, 863, 1302, 301, 357, 202, 601, 1302, 30, 1973, 32, 4309, 346, 203, 202, 111, 478, 202, 601, 4533, 32, 5747, 26, 357, 202, 633, 30, 357, 202, 3308, 32, 14066, 2031, 26, 355, 202, 306, 22269, 10605, 15866, 2091, 2464, 4174, 432, 544, 322, 24349, 355, 202, 3308, 32, 5482, 39125, 30, 357, 202, 471, 203, 202, 27, 203, 111, 2], "prompt_token_count": 173, "reference_codepoints": 64, "repo": "TecharoHQ/anubis", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [30, 225], "continuation_token_count": 2, "decoded": ", ", "decoded_codepoints": 2, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:skills/cloud/references/api-v2.md", "example_id": "000636d51c650b372931bc613b412abc21cf1134e07e883b191e8034aea96db2", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 12336, 32, 1676, 18974, 48869, 1966, 31, 1719, 13350, 1107, 32, 1112, 9452, 696, 32, 2812, 1801, 529, 3164, 33, 12336, 32, 874, 31, 15138, 1801, 529, 3164, 33, 12336, 32, 1676, 18974, 48869, 1966, 31, 1719, 13350, 1107, 32, 35168, 696, 32, 7159, 1801, 529, 878, 33, 7355, 1801, 529, 878, 33, 4700, 1801, 529, 878, 33, 8523, 82, 523, 203, 203, 433, 5170, 358, 18173, 203, 203, 326, 2247, 1097, 1074, 4777, 804, 30, 32995, 3, 15009, 1076, 11155, 5035, 11155, 1688, 11155, 5427, 4391, 2062, 11155, 438, 4411, 49, 203, 203, 326, 2247, 1074, 4777, 2026, 4187, 1097, 1074, 474, 6655, 44, 4187, 3533, 1074, 10012, 1688, 3839, 44, 2032, 1074, 1178, 203, 203, 326, 2247, 3533, 1074, 4777, 1451, 30, 4117, 30, 11903, 11698, 17357, 30, 2354, 17357, 30, 1984, 30, 20240, 2205, 11155, 6885, 44, 802, 1178, 2], "prompt_token_count": 144, "reference_codepoints": 32, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [30, 203, 539, 34315, 403, 13232, 403, 1240, 1777, 30, 203, 539, 34315, 403, 13232, 403, 18249, 30, 203, 539, 34315, 403, 13232, 403, 18249, 1151, 30, 203, 539, 34315, 403, 13232, 403, 18249, 1397, 1151, 30, 203, 539, 34315, 403, 13232, 403, 18249, 1397, 1151, 30, 203, 539, 34315, 403, 13232, 403, 18249, 1397, 1151, 30, 203, 539, 34315, 403, 13232, 403, 18249, 1397, 1151, 30, 203, 539, 34315, 403, 13232, 403], "continuation_token_count": 73, "decoded": ",\nuse rig::prompt::UserContent,\nuse rig::prompt::Prompt,\nuse rig::prompt::PromptEvent,\nuse rig::prompt::PromptResponseEvent,\nuse rig::prompt::PromptResponseEvent,\nuse rig::prompt::PromptResponseEvent,\nuse rig::prompt::PromptResponseEvent,\nuse rig::prompt::", "decoded_codepoints": 256, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:tests/providers/deepseek/request_hook.rs", "example_id": "00063b1fb44b9ca4a3601974894d4a3062e6722e4f1755fd59e5b05c8fa95363", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 11580, 10721, 17139, 71, 891, 30, 37070, 1255, 203, 539, 1230, 403, 5207, 10721, 8776, 30, 42806, 1255, 203, 203, 539, 34315, 403, 4867, 10721, 284, 14225, 9824, 30, 32861, 1853, 1711, 30, 32861, 1853, 1151, 30, 32861, 1397, 1151, 30, 284, 5826, 9348, 1711, 30, 203, 1255, 203, 539, 34315, 403, 15825, 10721, 1175, 30, 39626, 1255, 203, 539, 34315, 403, 1436, 403, 1240, 1777, 3, 284, 1789, 81, 13842, 44, 17578, 46, 17139, 71, 891, 2717, 284, 10925, 81, 13232, 44, 17578, 46, 13219, 46, 2828, 46, 652, 2005, 2717, 284, 10925, 81, 1986, 44, 17578, 46, 13219, 46, 2828, 46, 652, 2005, 2717, 203, 111, 203, 203, 3106, 14225, 9824, 436, 6548, 606, 9824, 37696, 48, 301, 284, 2498, 2771, 544, 81, 15825, 81, 1851, 26, 291, 549, 784, 30, 291, 617, 2095, 44, 549, 849, 403, 4867, 403, 9824, 634, 2], "prompt_token_count": 146, "reference_codepoints": 256, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [1382, 2432, 2467, 4026, 203, 319, 429, 11398], "continuation_token_count": 8, "decoded": "the same query vector\n * - Tests", "decoded_codepoints": 32, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:tests/fuzz/rescore-interleave.c", "example_id": "0006425e3bd28bd0cabd9d7032055b911693aaaad3de6957a74b20268794ee19", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 27, 203, 319, 429, 506, 12856, 31, 42609, 2467, 16540, 308, 1206, 5253, 428, 35, 30, 34, 30, 34, 46470, 1130, 203, 319, 429, 1283, 22081, 322, 16424, 1519, 308, 928, 225, 43, 34, 42, 34, 29, 328, 17735, 31, 3137, 32, 85, 27, 203, 319, 429, 11398, 623, 225, 35, 40, 13135, 308, 7026, 4011, 5401, 30, 46413, 1829, 432, 322, 203, 319, 261, 13292, 1649, 5258, 27, 203, 319, 429, 4803, 43904, 1224, 5804, 3733, 33094, 372, 225, 3, 1412, 617, 575, 1262, 81, 24897, 5760, 1159, 2583, 8128, 33, 10454, 203, 569, 203, 410, 26333, 56, 11964, 4501, 1006, 3582, 1612, 26, 913, 1727, 42, 81, 102, 319, 605, 30, 1334, 81, 102, 1334, 27, 301, 334, 415, 308, 891, 333, 225, 42, 27, 442, 225, 34, 45, 719, 629, 7631, 45, 334, 17735, 37, 319, 1199, 45, 334, 17735, 37, 81, 6404, 319, 6404, 6738, 280, 1181, 45, 334, 17735, 37, 81, 6404, 319, 6404, 2333, 280, 1181, 45, 334, 17735, 37, 81, 270, 2], "prompt_token_count": 170, "reference_codepoints": 32, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [87, 81, 5000, 81, 7572, 44, 1560, 280, 3177, 357, 202, 784, 1114, 297, 81, 5000, 81, 7572, 81, 9771, 44, 1560], "continuation_token_count": 22, "decoded": "e_video_writer: bool = False\n\t\tself._is_video_writer_started: bool", "decoded_codepoints": 66, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/browser/video_recorder.py", "example_id": "000651f47933ca058d0bc7df26e858905e8e8c435af005da3dd9a5305cdf97f3", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 288, 17237, 322, 1861, 461, 2384, 432, 322, 6027, 32, 6986, 43923, 7309, 44, 886, 10848, 43923, 7309, 436, 322, 1688, 6027, 32, 357, 202, 2993, 357, 202, 784, 32, 2024, 81, 983, 280, 1688, 81, 983, 357, 202, 784, 32, 891, 280, 1334, 357, 202, 784, 32, 43579, 7309, 280, 43923, 7309, 357, 202, 784, 1114, 7572, 44, 5648, 710, 2207, 32, 3976, 785, 280, 1665, 357, 202, 784, 1114, 297, 3, 478, 202, 589, 1477, 26, 784, 27, 967, 1665, 44, 357, 202, 2993, 357, 202, 2626, 4535, 575, 461, 11187, 322, 6027, 7272, 32, 1314, 202, 2797, 322, 2129, 5302, 6440, 884, 646, 6713, 30, 458, 1411, 1098, 357, 202, 751, 600, 1048, 461, 745, 7553, 32, 357, 202, 2993, 357, 202, 325, 646, 25696, 2338, 81, 25431, 44, 355, 202, 4073, 32, 731, 26, 603, 202, 25, 1456, 38, 23113, 22437, 2], "prompt_token_count": 147, "reference_codepoints": 64, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [262, 1524, 1006, 3319, 1972, 32, 6008, 346, 623, 1289, 11740, 2993, 291, 1344], "continuation_token_count": 14, "decoded": " \"\"\"Test TextHandler.clean() with no entities\"\"\"\n text", "decoded_codepoints": 65, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/parser/test_parser_advanced.py", "example_id": "0006539a1f3ef0e4199fedb2c9ea80dd5efe96fba2ff0faa76bd3e753278a3d7", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2572, 657, 291, 28171, 280, 1344, 32, 6008, 26, 2546, 81, 9244, 47, 1815, 27, 291, 1201, 14248, 757, 7879, 646, 328, 28171, 291, 1201, 14248, 20, 328, 28171, 291, 1201, 2706, 102, 20, 646, 328, 28171, 291, 1201, 2706, 96, 20, 646, 328, 28171, 446, 665, 894, 81, 878, 81, 4531, 81, 6008, 81, 12655, 81, 9244, 26, 784, 711, 284, 3, 20, 291, 1344, 280, 3319, 1972, 440, 8279, 78, 102, 24, 757, 8871, 96, 6708, 657, 291, 28171, 280, 1344, 32, 6008, 26, 2546, 81, 9244, 47, 2700, 27, 291, 1201, 14248, 757, 7879, 328, 28171, 446, 665, 894, 81, 878, 81, 4531, 81, 1260, 81, 1327, 26, 784, 711, 291, 1524, 1006, 3319, 1972, 32, 1260, 346, 623, 2080, 3398, 2993, 291, 1344, 280, 3319, 2], "prompt_token_count": 131, "reference_codepoints": 64, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [2524, 26, 1433, 2976, 30, 313, 28322, 69, 32, 21273, 724, 284, 660, 22728, 1215, 280, 7140, 26, 1433, 2976, 30, 313, 9718, 1466, 4900, 32, 954, 724, 284, 660, 1619, 41, 1215, 280, 7140, 26, 1433, 2976, 30, 313, 13952], "continuation_token_count": 41, "decoded": "join(tempDir, \"AGENTS.toml\");\n const skillsPath = join(tempDir, \"SKILLS.md\");\n const context7Path = join(tempDir, \"CONTEXT", "decoded_codepoints": 128, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/remove.test.ts", "example_id": "000668156f334332bf99f72cbbe8369b43aaa158a3aa0e1da4fa6b3a8d3f8346", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2546, 392, 301, 397, 25136, 44, 3037, 331, 651, 3439, 397, 4576, 44, 313, 2250, 392, 397, 19405, 44, 3037, 4538, 3439, 284, 1122, 334, 1122, 719, 894, 440, 13822, 646, 1245, 646, 2431, 3946, 1412, 1604, 21419, 4528, 6556, 392, 2498, 1404, 532, 301, 284, 660, 25136, 1215, 280, 7140, 26, 1433, 2976, 30, 313, 28322, 69, 32, 954, 724, 284, 660, 372, 696, 1215, 280, 225, 3, 446, 2014, 13947, 26, 2524, 26, 1433, 2976, 30, 4939, 331, 651, 2113, 301, 18581, 44, 861, 1122, 284, 2014, 13947, 26, 2524, 26, 1433, 2976, 30, 4939, 22705, 392, 313, 25071, 392, 313, 1819, 41, 31, 95, 2219, 2113, 301, 18581, 44, 861, 1122, 284, 2014, 2866, 974, 26, 397, 25136, 1215, 30, 397, 5100, 16900, 78, 96, 78, 96, 2904, 1619, 41, 1101, 78, 96, 5275, 3361, 78, 96, 2904, 1619, 41, 2], "prompt_token_count": 145, "reference_codepoints": 128, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [2506, 32, 3726, 26, 4573, 30, 2965, 30, 14186], "continuation_token_count": 9, "decoded": "ln.Bind(network, address, formatted", "decoded_codepoints": 35, "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:internal/setuplistener.go", "example_id": "00068e749f32534503b852a62b47afbf4fbd07016633e77e0e483db20954b34b", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2239, 26, 2468, 30, 10685, 657, 301, 434, 10014, 561, 1182, 2258, 312, 2601, 484, 32, 89, 32, 499, 38, 36, 39, 43, 355, 202, 18752, 2438, 280, 313, 525, 555, 5007, 20, 474, 2965, 357, 202, 111, 813, 301, 355, 202, 18752, 2438, 280, 313, 525, 35437, 474, 2965, 357, 202, 111, 203, 202, 1536, 44, 357, 202, 18752, 2438, 280, 4550, 32, 8716, 4199, 7846, 101, 27, 904, 101, 1801, 3984, 30, 2965, 27, 203, 202, 111, 478, 202, 2506, 30, 1137, 1025, 225, 3, 1137, 863, 1302, 301, 357, 202, 601, 1302, 30, 4320, 4550, 32, 5497, 440, 7815, 372, 5111, 372, 904, 101, 44, 904, 105, 392, 14186, 2438, 30, 1137, 27, 203, 202, 111, 478, 202, 306, 5388, 6501, 9933, 436, 28837, 36790, 203, 202, 325, 3984, 610, 313, 16705, 20, 301, 357, 202, 2816, 30, 1137, 1025, 21939, 32, 4480, 9868, 26, 4817, 2101, 30, 225, 42, 30, 225, 34, 27, 357, 202, 325, 1137, 863, 1302, 301, 355, 202, 81, 280, 17656, 32, 11166, 2], "prompt_token_count": 173, "reference_codepoints": 32, "repo": "TecharoHQ/anubis", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [958, 2196, 31605, 9483, 4254, 4104, 28, 11033, 291, 2196, 5257, 9483, 5607], "continuation_token_count": 13, "decoded": " local edition=\"${prefix}\\*$\"\n local pattern=\"${pattern", "decoded_codepoints": 68, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/image.sh", "example_id": "000698b2c9751bc94ee6c8461f8292c4d3a2053ee3719c6e11ce5055ad86e393", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 19994, 1491, 429, 100, 617, 9958, 15103, 33838, 3941, 3038, 20, 446, 436, 5257, 328, 398, 15719, 45, 745, 1687, 415, 428, 3941, 5607, 20, 280, 6640, 1536, 20, 4028, 1615, 291, 428, 429, 108, 3941, 31728, 20, 1481, 1276, 4036, 291, 6793, 47, 35, 397, 4348, 3813, 3941, 5607, 20, 610, 46760, 22189, 18154, 1615, 291, 2196, 5202, 9483, 5607, 16822, 28, 3845, 334, 3, 48889, 21, 5607, 3845, 397, 4348, 428, 3941, 31728, 20, 280, 3941, 5607, 20, 4028, 1615, 291, 6793, 9483, 21, 5607, 3845, 397, 813, 291, 4036, 397, 8058, 1687, 415, 1833, 6793, 848, 5273, 81, 5020, 11975, 1615, 291, 1056, 12672, 9786, 20, 291, 5273, 81, 5020, 12672, 5020, 20, 397, 8058, 446, 3390, 719, 3390, 719, 2248, 313, 2], "prompt_token_count": 127, "reference_codepoints": 64, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [264, 1424, 26, 1267, 547, 7285, 440, 3694], "continuation_token_count": 8, "decoded": " expect(result).toEqual(\"Schema", "decoded_codepoints": 34, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/commands/artifact-workflow.test.ts", "example_id": "0006a2f67c0b1d0a5c2a7ef4f74b33a57ddfab1ffffc14b6f97d76a8b97a2b5b", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1260, 32, 25520, 32, 983, 547, 38047, 463, 25520, 32, 954, 895, 397, 1424, 26, 1260, 32, 25520, 32, 1855, 547, 5492, 463, 1320, 895, 284, 1122, 446, 561, 463, 4275, 436, 8665, 5365, 370, 2498, 1404, 532, 301, 397, 660, 1056, 280, 2014, 1420, 8453, 4901, 8881, 370, 11363, 3968, 370, 330, 3780, 29801, 2188, 301, 24390, 44, 1779, 2976, 1122, 275, 3, 293, 397, 660, 1688, 280, 622, 2301, 26, 1267, 293, 397, 1424, 26, 2024, 547, 38047, 440, 3694, 330, 3780, 29801, 25, 646, 2431, 724, 284, 1122, 334, 1122, 719, 5510, 463, 890, 1539, 2016, 370, 1404, 532, 301, 284, 561, 463, 35622, 312, 537, 1539, 3362, 370, 2498, 1404, 532, 301, 397, 660, 1056, 280, 2014, 1420, 8453, 4901, 2], "prompt_token_count": 126, "reference_codepoints": 32, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [2076, 20, 334, 3099, 3941, 2076, 32, 891, 20, 334, 3099, 3941, 2076, 32, 891, 20, 334, 3099, 3941, 2076, 32, 891, 20, 334, 3099, 3941, 2076, 32, 891, 20, 334, 3099, 3941, 2076, 32, 891, 20, 334, 3099, 3941, 2076, 32, 891, 20, 334, 3099, 3941], "continuation_token_count": 47, "decoded": "msg\"\n info \"$msg.size\"\n info \"$msg.size\"\n info \"$msg.size\"\n info \"$msg.size\"\n info \"$msg.size\"\n info \"$msg.size\"\n info \"$", "decoded_codepoints": 128, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/install.sh", "example_id": "0006a509ebf79bd05f91c74cbbde3148d98231f6298a014a820940a585ba22c1", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 4754, 11995, 11624, 334, 2196, 341, 449, 4754, 341, 449, 11624, 334, 2196, 2443, 1250, 1334, 334, 2196, 31605, 4791, 43428, 719, 2196, 1847, 1250, 47, 35, 34, 34, 34, 34, 34, 34, 34, 34, 334, 2196, 3741, 5135, 47, 43, 40, 34, 40, 35, 36, 41, 37, 40, 34, 334, 2196, 11995, 12970, 47, 40, 34, 34, 34, 34, 34, 34, 34, 334, 2196, 2443, 12970, 47, 37, 34, 34, 34, 34, 34, 34, 719, 2196, 3124, 347, 10067, 299, 398, 3801, 11995, 10300, 20, 334, 3099, 3941, 2076, 32, 3, 601, 225, 35, 334, 8058, 719, 415, 1833, 1334, 333, 1847, 1250, 11975, 1615, 284, 1048, 313, 1318, 17236, 19687, 803, 438, 5133, 5532, 11555, 284, 442, 225, 35, 334, 8058, 719, 415, 653, 10194, 429, 4918, 769, 3941, 1515, 866, 1615, 284, 1048, 313, 5288, 372, 3345, 3362, 40355, 1515, 1492, 653, 20, 284, 442, 225, 35, 334, 8058, 719, 415, 653, 1930, 2976, 3941, 1515, 866, 1615, 284, 1048, 313, 21783, 2], "prompt_token_count": 167, "reference_codepoints": 128, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [284, 313, 731, 392, 284, 1048, 1562, 44, 284, 313], "continuation_token_count": 10, "decoded": "\n \"error\",\n errorFor:\n \"", "decoded_codepoints": 33, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/store/foundation.ts", "example_id": "0006bd1b55236c603ec9ac3a67b5fddc2410da320f34cc814afb3b7b78fc3da2", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 418, 1125, 46, 2780, 5378, 1078, 2717, 334, 2075, 44, 8809, 1215, 2031, 280, 2149, 203, 711, 4664, 46, 2780, 5378, 1078, 48, 301, 334, 660, 10880, 1215, 280, 622, 2780, 5378, 1215, 26, 2184, 293, 334, 660, 5440, 1215, 280, 8704, 8200, 1215, 4009, 809, 7839, 334, 660, 5440, 280, 2014, 20912, 974, 4631, 1371, 284, 5440, 1215, 30, 284, 1048, 1562, 44, 3, 225, 1596, 301, 284, 660, 2354, 280, 2014, 42771, 26, 6240, 1491, 2780, 5378, 1078, 26, 2184, 876, 284, 2014, 2866, 2780, 5378, 1078, 26, 1978, 30, 2075, 293, 284, 442, 2354, 45, 334, 320, 8295, 301, 284, 2014, 3621, 974, 4631, 26, 809, 30, 5440, 1215, 293, 334, 320, 203, 111, 203, 203, 1358, 2498, 667, 1491, 2780, 4097, 1078, 26, 203, 2], "prompt_token_count": 130, "reference_codepoints": 32, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [25, 306, 683, 397, 660, 19043, 2101, 280], "continuation_token_count": 8, "decoded": "'//')\n const effectiveMode =", "decoded_codepoints": 33, "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:hooks/ponytail-instructions.js", "example_id": "0006c6fdd8816757d7a68385bcfadd785e30317e900ea8375b4e7782f59d44bc", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 87, 33, 2620, 33, 338, 2692, 547, 399, 26285, 13696, 2266, 438, 334, 434, 646, 312, 2926, 12011, 484, 32, 89, 32, 313, 2023, 707, 22115, 1399, 34875, 44, 39695, 12011, 438, 312, 4302, 5750, 334, 434, 461, 2298, 526, 21301, 2643, 25862, 32, 334, 442, 2876, 10112, 23229, 284, 638, 2998, 20012, 100, 21194, 96, 4242, 284, 638, 2029, 1162, 928, 27, 532, 301, 397, 660, 1858, 2168, 280, 1628, 32, 2872, 26, 3, 261, 415, 308, 1274, 2168, 27, 301, 291, 660, 2266, 2101, 280, 13316, 2101, 26, 1274, 2168, 77, 35, 997, 5464, 1035, 291, 415, 308, 1172, 2101, 27, 442, 2266, 2101, 1720, 19043, 2101, 45, 397, 320, 1687, 434, 8032, 312, 34210, 786, 44, 3638, 13096, 2280, 438, 14511, 48025, 44, 313, 13585, 2541, 31621, 397, 434, 458, 30, 600, 556, 1323, 2], "prompt_token_count": 139, "reference_codepoints": 32, "repo": "DietrichGebert/ponytail", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [3732, 225, 35, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34], "continuation_token_count": 61, "decoded": "tool 10000000000000000000000000000000000000000000000000000000000", "decoded_codepoints": 64, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/tools-ai-sdk/src/index.test.ts", "example_id": "0006cd5a9ace142d978b8fc593834ee0dfd4e83a135c65c85f6ae216925b76c7", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 45, 397, 660, 4559, 1394, 280, 1056, 32, 3732, 5472, 77, 34, 79, 619, 8665, 619, 301, 1688, 44, 802, 1472, 397, 1424, 26, 5139, 4559, 1394, 32, 2024, 547, 5492, 440, 800, 724, 397, 1424, 26, 3732, 1394, 32, 2024, 547, 38047, 440, 1222, 41, 31, 14600, 4253, 2484, 724, 284, 801, 225, 37, 34, 34, 34, 34, 293, 446, 894, 440, 1217, 10113, 4559, 225, 3, 6240, 4450, 1031, 1371, 291, 1542, 44, 23065, 22262, 440, 278, 349, 42259, 32, 8475, 795, 31, 37, 31, 4945, 44464, 31, 36, 34, 36, 38, 34, 37, 34, 41, 31, 104, 35, 44, 34, 2113, 291, 8684, 44, 301, 616, 2467, 10113, 44, 2467, 10113, 1026, 291, 801, 291, 4559, 13860, 44, 301, 827, 44, 313, 3732, 392, 4559, 558, 44, 313, 1217, 10113, 20, 801, 291, 4719, 5786, 44, 3111, 1534, 1622, 26, 36, 471, 291, 10678, 2], "prompt_token_count": 149, "reference_codepoints": 64, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [32043, 11198, 44, 901, 30, 276, 29211, 661, 11198, 44, 901, 30, 276, 32043], "continuation_token_count": 14, "decoded": "readOnlyHint: false,\n destructiveHint: false,\n readOnly", "decoded_codepoints": 69, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/mcp/src/index.ts", "example_id": "0006cf3d68d42dbab97807a5697a073f2dc9830e6efc329cc020209fde7b26de", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 672, 636, 623, 7240, 40136, 12011, 484, 32, 89, 4317, 330, 3353, 32, 754, 25, 4174, 432, 330, 1978, 754, 370, 330, 7940, 32, 716, 25, 4174, 432, 330, 7123, 716, 370, 330, 17803, 32, 754, 25, 4174, 432, 330, 12192, 754, 2473, 20, 616, 2588, 397, 801, 397, 14695, 44, 301, 291, 34701, 11198, 44, 861, 30, 291, 42670, 661, 11198, 44, 901, 30, 276, 3, 835, 284, 2498, 5989, 2467, 30, 4253, 558, 23557, 301, 2467, 44, 802, 45, 4253, 558, 44, 802, 1790, 532, 301, 397, 660, 3692, 280, 622, 43576, 473, 397, 660, 3233, 1397, 280, 2014, 3233, 31820, 26, 1217, 30, 4253, 558, 30, 3692, 293, 1687, 415, 1429, 1903, 1397, 32, 4295, 1276, 3233, 1397, 32, 575, 338, 2], "prompt_token_count": 126, "reference_codepoints": 64, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [44, 1591, 1505, 8158, 370, 1404, 532, 301, 334, 660], "continuation_token_count": 10, "decoded": ": one check fails', () => {\n const", "decoded_codepoints": 35, "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:tests/behavior.test.js", "example_id": "0006d03be46a128a42f915a5c2dcd7887bd4ed1af3a4bc75314874abdd2b946f", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2958, 78, 5441, 32117, 4119, 81, 2627, 86, 26, 2138, 48775, 96, 264, 442, 428, 106, 1365, 83, 1446, 319, 225, 36, 436, 816, 328, 5760, 415, 816, 32, 371, 440, 83, 392, 225, 34, 27, 848, 225, 34, 10854, 96, 914, 78, 96, 25, 474, 284, 330, 34106, 44, 322, 5258, 32, 32231, 1453, 31256, 561, 11960, 334, 1201, 32, 2228, 26, 100, 32, 4617, 30, 901, 293, 203, 1916, 203, 203, 306, 5094, 544, 735, 806, 44, 11883, 1591, 40475, 1505, 5094, 203, 203, 858, 463, 658, 1553, 3, 48, 301, 334, 660, 540, 280, 1505, 463, 658, 1553, 370, 284, 330, 914, 2958, 78, 5441, 372, 81, 6360, 26, 101, 48775, 96, 264, 2417, 78, 96, 78, 96, 862, 372, 81, 6360, 440, 35, 90, 37, 34, 95, 657, 610, 225, 39, 38, 34, 34, 78, 96, 914, 895, 334, 1201, 32, 2228, 26, 100, 32, 4617, 30, 861, 293, 203, 1916, 203, 203, 858, 463, 658, 1553, 44, 1289, 1505, 8158, 370, 1404, 532, 301, 334, 660, 540, 280, 1505, 463, 658, 1553, 370, 284, 330, 914, 2958, 78, 5441, 372, 81, 4215, 2], "prompt_token_count": 189, "reference_codepoints": 32, "repo": "DietrichGebert/ponytail", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [101, 32, 3044, 33, 2180, 33, 5558, 21, 5057, 32, 334, 1692, 44, 2498, 5989, 1692, 320, 280, 2149, 829, 301, 284, 434, 886, 1692, 4899, 438, 341, 3911, 30, 1259, 322, 1692, 4899, 27356, 3980, 1464], "continuation_token_count": 37, "decoded": "s.ai/docs/plugins#events.\n event: async ({ event } = {} ) {\n // The event handler is wired, so the event handler alone misses", "decoded_codepoints": 129, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/plugins/opencode/plugin.js", "example_id": "0006da8b56700c5d6abbb677f4c11d05dafe4fd7ea3a77db238bb970541a3bc6", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1570, 1692, 7520, 438, 341, 3911, 30, 334, 434, 1259, 322, 1692, 4899, 27356, 3980, 1464, 561, 32, 886, 7763, 31, 1003, 2866, 31256, 688, 334, 434, 22048, 45, 322, 1692, 4899, 316, 31, 862, 101, 544, 3638, 6125, 3523, 328, 1946, 31, 374, 2236, 334, 434, 394, 2284, 13185, 32, 334, 2887, 3135, 6873, 473, 719, 442, 301, 334, 434, 2156, 687, 3, 1182, 2411, 32, 4524, 25, 1202, 438, 45889, 10302, 32, 33009, 3523, 31, 1664, 3919, 334, 434, 2442, 6058, 322, 4655, 438, 316, 15557, 544, 3638, 537, 3523, 30, 646, 2258, 5049, 1412, 334, 434, 322, 3973, 2297, 20748, 32, 2802, 1678, 555, 1676, 687, 32, 3044, 33, 2180, 33, 5558, 21, 5057, 32, 334, 1692, 44, 2498, 5989, 1692, 320, 280, 2149, 2], "prompt_token_count": 129, "reference_codepoints": 128, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [297, 646, 6660, 372, 8329, 276, 319, 886, 14786, 4121, 529, 83, 82, 438, 646, 6660, 372, 8329, 276, 319, 886, 14786, 4121, 529, 84, 82, 438], "continuation_token_count": 27, "decoded": "is not allowed to compile\n * The mutable reference `a` is not allowed to compile\n * The mutable reference `b` is", "decoded_codepoints": 128, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:c-cpp-book/src/ch05-data-structures.md", "example_id": "0006ddb18bf709f30dbff250300df2b8dedc6d283ce109481fa033e4991a4b8f", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2712, 26346, 308, 6268, 27, 4121, 372, 312, 14786, 2677, 438, 15010, 461, 561, 2298, 646, 18714, 623, 1346, 1604, 4121, 32, 203, 914, 7421, 203, 3359, 2575, 346, 301, 284, 1207, 4031, 312, 280, 225, 38, 36, 45, 284, 301, 291, 1207, 323, 280, 549, 83, 45, 291, 1207, 281, 280, 323, 45, 291, 11662, 9170, 2537, 12263, 319, 84, 30, 319, 85, 293, 434, 886, 8980, 225, 3, 3170, 322, 276, 319, 3460, 372, 646, 8329, 30, 3301, 529, 84, 82, 438, 1654, 276, 319, 2218, 322, 14786, 4121, 529, 86, 82, 438, 10912, 328, 322, 1550, 4576, 276, 319, 13105, 319, 2448, 4881, 1159, 312, 14786, 461, 26055, 4121, 328, 793, 328, 322, 2432, 4576, 276, 319, 821, 322, 20781, 2], "prompt_token_count": 125, "reference_codepoints": 128, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [6042, 27, 301, 603, 202, 862, 32, 1324, 26, 102, 30, 313, 2781, 10506, 102, 428, 68, 1525, 267, 225, 40, 42, 34, 63, 9166, 20800, 32], "continuation_token_count": 27, "decoded": " validate) {\n\t\t\t\tassert.Equal(t, \"Rembrandt [Radeon 680M]\", gpu.", "decoded_codepoints": 64, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/gpu_test.go", "example_id": "0006df655b5c3f844fbf781035a007c18da3e970f29712815d43b30fe785d59c", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 392, 313, 26035, 2484, 563, 313, 34, 106, 42, 83, 36, 36, 392, 313, 3033, 33191, 563, 313, 34, 3077, 42, 392, 313, 1212, 2484, 563, 313, 35, 392, 313, 11989, 563, 313, 37, 38, 41, 39, 40, 392, 313, 37043, 3036, 563, 313, 23217, 35, 34, 37, 39, 14944, 19023, 603, 202, 325, 1137, 1025, 2322, 32, 47196, 26, 983, 30, 1605, 2263, 26, 1423, 471, 225, 34, 41, 39, 39, 293, 1137, 863, 1302, 301, 577, 202, 601, 1137, 603, 202, 111, 603, 202, 601, 1302, 355, 202, 835, 355, 202, 4635, 44, 3420, 26, 102, 319, 4266, 32, 70, 30, 3, 202, 862, 32, 1815, 26, 102, 30, 5375, 27, 603, 202, 325, 5375, 301, 577, 202, 862, 32, 1324, 26, 102, 30, 313, 2781, 10506, 102, 428, 68, 1525, 267, 225, 40, 42, 34, 63, 9166, 20800, 32, 558, 27, 577, 202, 862, 32, 383, 9189, 26, 102, 30, 225, 38, 43, 32, 34, 30, 20800, 32, 19412, 30, 225, 34, 32, 34, 35, 27, 577, 202, 862, 32, 383, 9189, 26, 102, 30, 225, 36, 42, 32, 35, 39, 43, 30, 20800, 32, 6768, 30, 225, 34, 32, 34, 35, 27, 603, 202, 111, 355, 202, 835, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 264, 313, 3923, 633, 1966, 26013, 392, 357, 2], "prompt_token_count": 222, "reference_codepoints": 64, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [81, 2848, 32, 371, 81, 10487, 346, 355, 202, 862, 2069, 26, 10487, 27, 2377, 225, 38, 30, 330, 6143, 1395, 1159, 9435, 821, 6225, 225, 38, 17002, 25, 2540, 202, 21, 12072, 996, 1159, 225, 38, 17002, 8777, 355, 202, 10487, 280, 2014, 5427, 81, 2848, 81, 2848, 32, 371, 81, 10487, 346, 355, 202, 862, 2069, 26, 10487, 27, 2377, 225, 38, 30, 330, 6143, 1395, 1159, 9435, 821, 6225, 225, 38, 17002, 25, 2540, 202, 21, 12072], "continuation_token_count": 80, "decoded": "_session.get_tabs()\n\t\t\tassert len(tabs) >= 4, 'Agent should have completed at least 4 tabs'\n\n\t\t\t# Verify we have 4 tabs closed\n\t\t\ttabs = await browser_session_session.get_tabs()\n\t\t\tassert len(tabs) >= 4, 'Agent should have completed at least 4 tabs'\n\n\t\t\t# Verify", "decoded_codepoints": 262, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/browser/test_tabs.py", "example_id": "0006e1ec9e96f7f34eb8ca4924e1d22462f12f3c499dfd1f8a47f4b04dc3a05b", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 429, 1395, 6153, 4797, 225, 36, 10135, 357, 202, 1270, 44, 355, 202, 6446, 280, 2014, 24495, 32, 1684, 81, 979, 26, 4867, 32, 1945, 26, 1449, 81, 7439, 47, 39, 471, 5868, 47, 35, 36, 34, 27, 355, 202, 862, 2069, 26, 6446, 27, 2377, 225, 38, 30, 330, 6143, 1395, 1159, 9435, 821, 6225, 225, 38, 6655, 25, 2540, 202, 21, 12072, 996, 1159, 225, 38, 17002, 2156, 355, 202, 10487, 280, 2014, 5427, 81, 2848, 3, 330, 24724, 25, 328, 1158, 81, 1267, 30, 330, 6143, 1395, 3639, 3117, 25, 357, 202, 7343, 20955, 924, 44, 355, 202, 12408, 32, 5066, 463, 1006, 28877, 963, 2685, 225, 36, 10135, 429, 5427, 1603, 28877, 963, 5929, 26671, 4878, 7373, 683, 478, 202, 4396, 665, 894, 81, 12565, 81, 3007, 81, 1586, 21073, 81, 363, 81, 2679, 26, 784, 30, 5427, 81, 6690, 2], "prompt_token_count": 146, "reference_codepoints": 256, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [264, 313, 1427, 21066, 392, 528, 313, 1427, 21066, 81, 1237, 81, 1648, 392, 528, 3693, 21066, 81, 1132, 30, 400, 829, 2110], "continuation_token_count": 23, "decoded": " \"docintel\",\n \"docintel_api_version\",\n docintel_args,\n )\n\n ", "decoded_codepoints": 129, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/_markitdown.py", "example_id": "0006e2d180eaa71e4eac840fb23e3bdcb7ad70f6d955db7c701ba54ded9c9046", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 10597, 81, 2516, 2110, 3693, 21066, 81, 1648, 280, 10306, 32, 371, 440, 1427, 21066, 81, 1237, 81, 1648, 657, 400, 415, 3693, 21066, 81, 1648, 438, 646, 1665, 44, 528, 3693, 21066, 81, 1132, 1365, 1237, 81, 1648, 1446, 280, 3693, 21066, 81, 1648, 2110, 630, 32, 3317, 81, 13956, 26, 353, 3, 322, 2663, 432, 322, 4138, 415, 6998, 438, 3943, 324, 14234, 81, 7986, 280, 10306, 32, 371, 440, 9802, 81, 7986, 657, 324, 415, 14234, 81, 7986, 438, 646, 1665, 44, 400, 14234, 81, 1132, 44, 14580, 77, 466, 30, 6204, 79, 280, 2149, 400, 14234, 81, 1132, 1365, 7986, 1446, 280, 14234, 81, 7986, 2110, 14234, 81, 1220, 2], "prompt_token_count": 115, "reference_codepoints": 128, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [225, 638, 3356, 26, 2416, 81, 4351, 27, 291, 638, 3356, 26, 24737, 403, 8443, 403, 1260, 1652, 2416, 81, 4351, 32, 452, 81, 1260, 5156, 291, 638, 3356, 26, 24737, 403, 11592, 403, 2988, 26, 11415, 924], "continuation_token_count": 38, "decoded": " .then(process_route)\n .then(warp::reply::json(&process_route.to_json()))\n .then(warp::reject::custom(ProcessingError", "decoded_codepoints": 132, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:csharp-book/src/ch15-2-incremental-adoption-strategy.md", "example_id": "0006fc3fe43587f8e37c871b1095d69feb87c493b6c94310d283098dc8ece22e", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 12942, 2170, 6311, 26, 11415, 1397, 301, 291, 11451, 81, 893, 44, 3112, 30, 291, 8202, 81, 1003, 81, 874, 44, 1477, 32, 17517, 922, 302, 81, 36916, 346, 619, 1044, 40, 38, 30, 284, 1790, 203, 111, 203, 203, 6357, 13586, 716, 403, 1831, 79, 203, 4396, 2771, 2575, 346, 301, 284, 1207, 2164, 81, 4351, 280, 32209, 403, 983, 440, 2416, 657, 291, 638, 363, 26, 24737, 403, 1526, 1157, 1568, 3, 2071, 6311, 26, 1986, 27, 532, 6311, 26, 24737, 403, 8443, 403, 1260, 1652, 1986, 3662, 400, 7178, 26, 87, 27, 532, 7178, 26, 24737, 403, 11592, 403, 2988, 26, 11415, 924, 26, 87, 32, 452, 81, 800, 5156, 471, 324, 320, 291, 1122, 446, 32209, 403, 6455, 26, 2416, 81, 4351, 27, 291, 638, 1945, 37254, 35, 36, 41, 30, 225, 34, 30, 225, 34, 30, 225, 35, 614, 225, 37, 34, 37, 34, 490, 291, 638, 83, 2], "prompt_token_count": 155, "reference_codepoints": 128, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [25, 357, 202, 862, 9146, 12474, 9417, 14612, 1114, 27974, 81, 4984, 81, 3607, 463, 761, 31, 1793, 81, 642, 483, 7391, 32, 4700, 683, 610, 330, 761, 31, 1793, 81, 642, 483, 7391, 32, 4700, 25, 357, 202, 862, 9146], "continuation_token_count": 41, "decoded": "'\n\t\tassert DownloadsWatchdog._sanitize_download_filename('file-with_underscores.csv') == 'file-with_underscores.csv'\n\t\tassert Down", "decoded_codepoints": 130, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/security/test_download_filename_sanitization.py", "example_id": "0006fdb27cfadcc56216db464abfcac54961400f3bbd4d6a68417d6d2158cecf", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2309, 463, 3734, 32, 4682, 683, 610, 330, 3734, 32, 4682, 25, 357, 202, 862, 9146, 12474, 9417, 14612, 1114, 27974, 81, 4984, 81, 3607, 463, 761, 623, 13922, 32, 4682, 683, 610, 330, 761, 623, 13922, 32, 4682, 25, 357, 202, 862, 9146, 12474, 9417, 14612, 1114, 27974, 81, 4984, 81, 3607, 463, 761, 31, 1793, 81, 642, 483, 7391, 32, 4700, 683, 610, 330, 761, 31, 1793, 81, 642, 483, 7391, 32, 4700, 3, 47, 5608, 44533, 25, 478, 202, 589, 894, 81, 9941, 81, 1001, 4106, 26, 784, 27, 967, 1665, 44, 357, 202, 21, 37960, 101, 623, 2979, 31, 20957, 7125, 1395, 34511, 661, 308, 2282, 436, 595, 35, 42, 96, 26719, 547, 357, 202, 862, 9146, 12474, 9417, 14612, 1114, 27974, 81, 4984, 81, 3607, 463, 42740, 1036, 1309, 32, 4682, 683, 610, 330, 42740, 1036, 1309, 32, 4682, 25, 357, 202, 862, 9146, 12474, 9417, 14612, 1114, 17828, 2], "prompt_token_count": 156, "reference_codepoints": 128, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [109, 577, 202, 10300, 12090, 26225, 44, 301, 1379, 202, 10300, 12090, 26225, 44, 301, 1488, 202, 10300, 12090, 26225], "continuation_token_count": 20, "decoded": "{\n\t\t\t\t\tdiskIoCounters: {\n\t\t\t\t\t\tdiskIoCounters: {\n\t\t\t\t\t\t\tdiskIoCounters", "decoded_codepoints": 70, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/disk_test.go", "example_id": "00070b34f21d51ea7487a6819373e2c16d10368ff7654a1944b16f7e31164f10", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 202, 102, 32, 2529, 440, 41860, 3051, 645, 17163, 9778, 15133, 392, 3420, 26, 102, 319, 4266, 32, 70, 27, 301, 357, 202, 4867, 1025, 549, 6143, 109, 2548, 5773, 44, 1930, 26, 1110, 77, 800, 6603, 2946, 32, 15516, 5773, 4370, 357, 202, 21533, 1025, 9519, 17323, 109, 355, 202, 4867, 44, 7669, 30, 355, 202, 2095, 44, 5980, 11512, 1222, 109, 603, 202, 297, 2839, 44, 901, 30, 603, 202, 10300, 12090, 26225, 44, 225, 3, 30, 4841, 3644, 44, 225, 35, 34, 34, 34, 30, 5950, 3644, 44, 225, 35, 34, 34, 34, 835, 603, 202, 835, 355, 202, 835, 357, 202, 111, 1314, 202, 1253, 1025, 21067, 32, 669, 10728, 4058, 15516, 4207, 1902, 33, 9692, 289, 34, 96, 35, 98, 36, 392, 44332, 1314, 202, 862, 32, 1815, 26, 102, 30, 3835, 27, 357, 202, 5136, 30, 5375, 1025, 7669, 32, 2548, 5773, 1365, 9692, 289, 34, 96, 35, 1446, 357, 202, 862, 32, 1815, 26, 102, 30, 5375, 27, 357, 202, 862, 32, 1815, 26, 102, 30, 8616, 32, 4058, 27, 357, 202, 862, 32, 1324, 26, 102, 30, 2430, 2], "prompt_token_count": 188, "reference_codepoints": 64, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [49, 6553, 324, 786, 30, 324, 1244, 32, 302, 81, 612, 1026, 291, 1093], "continuation_token_count": 14, "decoded": "?}\",\n value,\n default.as_ref(),\n );", "decoded_codepoints": 64, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/languages/rust/rustup.rs", "example_id": "000716cb110082bae80693d6c5c233facb66fce1e179d6b39844422070ecc4fe", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 102, 6311, 26, 853, 27, 280, 4533, 81, 6862, 32, 869, 26, 6052, 12034, 403, 2883, 61, 81, 68, 6902, 81, 21448, 27, 813, 301, 291, 442, 19281, 417, 4290, 403, 1536, 473, 284, 1472, 446, 786, 32, 2208, 922, 7513, 81, 271, 81, 1824, 12143, 19289, 301, 291, 1207, 1244, 280, 19281, 417, 4290, 403, 1536, 473, 291, 17161, 81, 496, 4482, 324, 313, 3817, 786, 436, 2149, 44, 7325, 49, 3, 30, 324, 23471, 12034, 403, 2883, 61, 81, 68, 6902, 81, 21448, 30, 324, 786, 30, 324, 1244, 32, 302, 81, 612, 1026, 291, 1093, 291, 1244, 284, 1790, 203, 111, 203, 203, 3106, 19281, 417, 301, 284, 2547, 26, 9822, 27, 2771, 20456, 417, 81, 2833, 1652, 784, 27, 967, 549, 1215, 301, 291, 549, 784, 32, 7421, 417, 81, 2833, 284, 320, 446, 889, 6741, 20456, 417, 415, 646, 743, 100, 2], "prompt_token_count": 148, "reference_codepoints": 64, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [262, 660, 4559, 32, 470, 3653, 26, 3732, 293, 397, 660, 4559, 32, 470, 3653, 1788, 26], "continuation_token_count": 17, "decoded": " const tool.setTool(tool);\n const tool.setToolOverride(", "decoded_codepoints": 64, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/update.ts", "example_id": "000717399cf8637cf6bf694d48807e958a46d0b4937a2289e5e8046c84e5bf2d", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1738, 19043, 6274, 29, 15480, 32, 284, 660, 16381, 30096, 44, 802, 1178, 280, 4312, 284, 660, 10153, 25936, 44, 34165, 15492, 1394, 710, 9874, 25936, 785, 280, 5330, 446, 436, 308, 913, 4559, 606, 432, 4324, 7923, 27, 301, 397, 660, 4559, 280, 19551, 81, 31081, 32, 1809, 1162, 102, 27, 532, 273, 32, 853, 1720, 4559, 606, 293, 334, 3, 82, 7085, 973, 2283, 3732, 32, 426, 111, 1179, 15383, 1366, 473, 1687, 1596, 301, 291, 660, 22728, 2976, 280, 1519, 32, 2524, 26, 2250, 1215, 30, 4559, 32, 25071, 2976, 30, 330, 25071, 895, 291, 660, 1395, 10505, 30834, 280, 1395, 10505, 30834, 1562, 3653, 26, 3732, 32, 853, 30, 18198, 293, 291, 660, 1395, 10505, 9770, 280, 309, 2], "prompt_token_count": 124, "reference_codepoints": 64, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [471, 7140, 26, 2833, 1515, 1026, 4939, 300, 15920, 392, 313, 1163, 392, 313, 3264, 81, 1163, 32, 1260, 657, 614, 397, 7669, 9651, 44, 428, 2524, 26, 2833, 1515, 1026, 4939, 300, 15920, 392, 313, 1163, 392, 313, 4867, 81, 1163, 32, 1260, 657, 614, 397, 3649, 9651, 44, 428, 2524, 26, 2833, 1515, 1026, 4939, 300, 15920, 392, 313, 1163, 392, 313, 3264, 81, 1163, 32, 1260, 657, 614, 397, 7669, 620, 44, 313, 4867, 392, 397, 7669], "continuation_token_count": 80, "decoded": "), join(homedir(), \".gemini\", \"config\", \"global_config.json\")],\n agentPaths: [join(homedir(), \".gemini\", \"config\", \"agent_config.json\")],\n globalPaths: [join(homedir(), \".gemini\", \"config\", \"global_config.json\")],\n agentType: \"agent\",\n agent", "decoded_codepoints": 261, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/setup/agents.ts", "example_id": "00071b62aa733163fba89c78c4f72a4a13c2f75ed0ddcd3f3e9a3e3f0798a629", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 306, 1359, 30, 1259, 2074, 9651, 438, 3502, 461, 4705, 6143, 39394, 1751, 372, 3649, 32, 334, 17112, 6329, 13960, 44, 301, 284, 636, 44, 313, 692, 6329, 13960, 392, 284, 23085, 44, 313, 12382, 6329, 13960, 392, 284, 345, 2219, 44, 301, 397, 2074, 9651, 44, 5518, 397, 3649, 9651, 44, 428, 2524, 26, 2833, 1515, 1026, 4939, 300, 15920, 392, 313, 1163, 392, 313, 95, 2219, 81, 1163, 32, 1260, 20, 3, 1018, 7140, 26, 2833, 1515, 1026, 4939, 300, 15920, 392, 313, 3055, 4683, 59, 32, 954, 657, 499, 313, 3055, 4683, 59, 32, 954, 2113, 397, 4169, 11125, 44, 313, 2904, 1619, 41, 1101, 392, 284, 801, 284, 20838, 44, 301, 397, 636, 44, 313, 1819, 41, 31, 95, 2219, 392, 397, 4921, 44, 308, 3473, 27, 532, 291, 4576, 1720, 313, 3264, 20, 1018, 7140, 26, 2833, 1515, 1026, 4939, 4867, 392, 313, 25071, 657, 499, 7140, 5791, 4867, 392, 313, 1990, 2], "prompt_token_count": 159, "reference_codepoints": 256, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [264, 320, 284, 320, 284, 442, 744, 45, 203, 111, 203, 1358, 667, 2099, 106, 387, 3192, 26, 1217, 30, 2723, 30, 2266, 30, 1769, 882, 27, 301, 284, 660, 2266, 280, 892, 26, 1172, 1276, 31248, 2754, 2840, 299, 473, 284, 660, 1769, 882, 280, 892, 26, 1449, 882, 1276, 31248, 2754, 2840, 299, 473, 284, 660, 2467, 280, 892, 26, 1217, 1276, 31248, 2754, 2840, 299, 473, 284, 660], "continuation_token_count": 71, "decoded": " }\n }\n return null;\n}\nexport function arxivSearch(query, limit, label, maxValue) {\n const label = String(label || '').trimming();\n const maxValue = String(maxValue || '').trimming();\n const query = String(query || '').trimming();\n const", "decoded_codepoints": 257, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/arxiv/utils.js", "example_id": "00071cebdff9ce6e5bb30c06f32aaabf0ae4fa59cc12d2a84b88fca0257471e5", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2498, 667, 2099, 106, 387, 8675, 26, 2132, 27, 301, 284, 660, 5127, 280, 2014, 5630, 14029, 783, 74, 5091, 81, 6177, 37613, 1667, 2132, 12833, 284, 415, 1429, 5243, 32, 1253, 27, 301, 291, 1422, 537, 5718, 6136, 924, 4199, 48085, 2330, 4808, 2283, 5243, 32, 1517, 13045, 330, 2140, 1370, 3233, 5615, 556, 12517, 2484, 895, 284, 320, 284, 442, 5127, 32, 878, 473, 203, 3, 12172, 526, 312, 11557, 4991, 9796, 284, 320, 284, 415, 308, 3248, 848, 39159, 27, 301, 291, 1422, 537, 29499, 4199, 20583, 2283, 1172, 111, 2298, 526, 2511, 2283, 1449, 882, 12833, 284, 320, 284, 442, 2723, 45, 203, 111, 203, 1358, 667, 13316, 3421, 106, 387, 4220, 26, 853, 27, 301, 284, 660, 6215, 280, 892, 26, 853, 1276, 31248, 2754, 2], "prompt_token_count": 132, "reference_codepoints": 256, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [88, 44, 355, 202, 6240, 296, 32, 1821, 26, 88, 15907, 339, 81, 1286, 4104, 96, 78, 96, 39861, 16928, 1296, 3491, 96, 683, 355, 202, 6240, 296, 32, 1821, 26, 11382, 81, 983, 27, 1314, 202, 1286, 81, 983, 280, 630, 32, 2024, 81, 1515, 517, 296, 25, 1286], "continuation_token_count": 50, "decoded": "f:\n\t\t\tawait f.write(f'{ad_content}\\n\\nANALYSIS:\\n')\n\t\t\tawait f.write(analysis_path)\n\n\t\tcontent_path = self.output_dir / f'content", "decoded_codepoints": 129, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:examples/apps/ad-use/ad_generator.py", "example_id": "000722928f238211c599ec7747042b74769eddb6a3cf1481107906fffdcba5b2", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 784, 32, 2024, 81, 1515, 517, 296, 25, 339, 5290, 5561, 4009, 317, 38, 25, 1314, 202, 4396, 623, 38576, 2536, 32, 1676, 26, 1286, 81, 983, 30, 330, 12108, 683, 619, 296, 44, 355, 202, 6240, 296, 32, 1821, 26, 339, 81, 1286, 27, 1314, 202, 11382, 81, 983, 280, 630, 32, 2024, 81, 1515, 517, 296, 25, 11382, 5290, 5561, 4009, 2760, 25, 357, 202, 4396, 623, 38576, 2536, 32, 1676, 26, 11382, 81, 983, 30, 330, 105, 370, 7328, 1057, 3310, 31, 42, 683, 619, 225, 3, 78, 96, 78, 96, 36328, 4158, 37754, 3491, 96, 683, 355, 202, 6240, 296, 32, 1821, 26, 13232, 27, 1314, 202, 601, 596, 26, 1286, 81, 983, 27, 478, 203, 589, 2156, 81, 761, 26, 761, 81, 983, 44, 596, 711, 203, 202, 2993, 2961, 803, 623, 1244, 2664, 23952, 2993, 203, 202, 1270, 44, 357, 202, 325, 5237, 32, 5134, 32, 15990, 463, 24917, 7831, 355, 202, 27958, 32, 1945, 4901, 1676, 370, 803, 81, 983, 614, 1505, 47, 1815, 27, 357, 202, 87, 2], "prompt_token_count": 177, "reference_codepoints": 128, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [26, 400, 313, 3215, 1991, 23877], "continuation_token_count": 6, "decoded": "(\n \"insert into embedding", "decoded_codepoints": 40, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:crates/rig-lancedb/examples/vector_search_local_ann.rs", "example_id": "00072bb7c6dd185c64e3b92b8d24a0be8682b988140e047ef5fb3fb5ecdc70da", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 686, 2471, 284, 415, 1858, 32, 1055, 81, 5136, 440, 20711, 1895, 6240, 4972, 297, 81, 4108, 346, 301, 291, 1858, 324, 638, 1297, 81, 1055, 26, 400, 549, 1365, 20711, 3439, 400, 456, 6087, 84, 403, 1055, 403, 1284, 403, 59, 17261, 45863, 26, 59, 17261, 45863, 1284, 1796, 403, 1536, 6182, 324, 829, 324, 638, 4526, 3, 261, 434, 14054, 3233, 81, 2132, 2803, 688, 1098, 526, 1654, 810, 322, 4026, 2968, 372, 4436, 322, 4026, 3233, 32, 284, 1207, 3233, 81, 2132, 280, 7422, 2778, 403, 1536, 473, 284, 1207, 4026, 81, 2157, 81, 1055, 280, 498, 723, 5141, 2863, 1284, 403, 890, 26, 1274, 30, 1542, 30, 313, 314, 392, 3233, 81, 2132, 547, 6240, 12370, 446, 1207, 225, 2], "prompt_token_count": 125, "reference_codepoints": 32, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [81, 85, 44476, 81, 1267, 26, 400, 313, 30595, 81, 8795, 33, 8281, 81, 363, 81, 28943], "continuation_token_count": 17, "decoded": "_cassette_result(\n \"extractor_usage/extract_and_extr", "decoded_codepoints": 67, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:tests/providers/xai/extractor_usage.rs", "example_id": "00073354e2799adf52b35c1f17c440751d3c60836e1bca75a583c43b5063b09a", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2264, 1346, 6893, 403, 12830, 4482, 1986, 32, 605, 32, 5702, 32, 302, 81, 26601, 346, 610, 4185, 440, 12422, 1495, 2974, 324, 1346, 6893, 403, 12830, 4482, 1986, 32, 605, 32, 1293, 32, 302, 81, 26601, 346, 610, 4185, 440, 1466, 2974, 324, 1346, 6893, 403, 12830, 4482, 1986, 32, 605, 32, 3969, 81, 687, 32, 302, 81, 26601, 346, 610, 4185, 440, 40, 36, 41, 34, 35, 2974, 324, 1346, 6893, 3, 12830, 4482, 1986, 32, 8795, 32, 2999, 81, 8395, 848, 225, 34, 293, 1064, 6311, 20268, 291, 801, 284, 829, 284, 638, 6240, 203, 111, 203, 203, 6357, 13586, 716, 403, 858, 79, 203, 4396, 2771, 6571, 81, 363, 81, 8281, 81, 1793, 81, 8795, 81, 601, 81, 8786, 81, 605, 346, 967, 4703, 31012, 301, 284, 623, 81, 2925, 91, 81, 85, 44476, 81, 1267, 26, 291, 313, 30595, 81, 8795, 33, 8281, 81, 363, 81, 28943, 329, 2], "prompt_token_count": 155, "reference_codepoints": 64, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [20, 371, 81, 965, 563, 296, 9588, 525, 1771, 32, 965, 3188, 371, 392], "continuation_token_count": 14, "decoded": "\"get_url\": f\"{httpbin.url}/get\",", "decoded_codepoints": 32, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/fetchers/async/test_requests.py", "example_id": "00073875fd9e99bbcb3481fb667b062515c6e336091132c894241fa547162c8f", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 4154, 30, 1913, 1771, 711, 291, 442, 301, 324, 313, 1517, 81, 36, 34, 34, 563, 296, 9588, 525, 1771, 32, 965, 3188, 1517, 33, 36, 34, 34, 392, 324, 313, 1517, 81, 38, 34, 38, 563, 296, 9588, 525, 1771, 32, 965, 3188, 1517, 33, 38, 34, 38, 392, 324, 313, 1517, 81, 39, 34, 35, 563, 296, 9588, 525, 1771, 32, 965, 3188, 1517, 33, 39, 34, 35, 392, 324, 313, 6390, 81, 965, 563, 296, 9588, 525, 1771, 32, 965, 3188, 371, 392, 1802, 3, 392, 324, 313, 524, 81, 965, 563, 296, 9588, 525, 1771, 32, 965, 3188, 524, 392, 324, 313, 2560, 81, 965, 563, 296, 9588, 525, 1771, 32, 965, 3188, 2560, 392, 324, 313, 916, 81, 965, 563, 296, 9588, 525, 1771, 32, 965, 3188, 916, 392, 291, 320, 446, 2498, 665, 894, 81, 6390, 81, 371, 26, 784, 30, 5630, 265, 30, 19990, 711, 291, 1524, 1006, 8113, 6550, 622, 1326, 623, 17476, 2], "prompt_token_count": 163, "reference_codepoints": 32, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [1255, 203, 111, 203, 203, 1358, 667, 1968, 3782, 26, 44889, 30, 3992, 27, 301, 284, 442, 8704, 2418, 8703, 81, 28310, 3188, 10331, 9164, 44889, 16484, 3245, 16963, 203, 111, 203, 203, 1358, 667, 1968, 3782, 2205, 26, 44889, 27, 301, 284, 442, 8704, 2418, 8703, 81, 28310, 3188, 10331, 9164, 44889, 16963, 203, 111, 203, 203, 1358, 667, 20440, 8357, 3999, 26, 3007, 27, 301, 284, 442, 390, 2027], "continuation_token_count": 71, "decoded": "};\n}\n\nexport function buildJob(ciphertext, job) {\n return `${UPWORK_ORIGIN}/jobs/${ciphertext}/${job}`;\n}\n\nexport function buildJobUrl(ciphertext) {\n return `${UPWORK_ORIGIN}/jobs/${ciphertext}`;\n}\n\nexport function isValidFeedTab(tab) {\n return CIP", "decoded_codepoints": 257, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/upwork/utils.js", "example_id": "00073e267951b874ede04c54f615265cc5b7321d3382e64110e35e491e5a369b", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 308, 3323, 962, 3844, 3326, 330, 4875, 2362, 683, 2803, 32, 470, 463, 3323, 370, 3844, 293, 284, 415, 308, 462, 1969, 962, 1292, 1969, 3326, 225, 35, 34, 27, 2803, 32, 470, 463, 462, 81, 1637, 370, 892, 26, 462, 1969, 876, 284, 415, 308, 1637, 962, 1938, 848, 225, 35, 27, 2803, 32, 470, 463, 1637, 370, 892, 26, 1637, 876, 284, 442, 8704, 2418, 8703, 81, 28310, 3188, 8462, 33, 1903, 33, 10331, 8172, 1667, 2132, 32, 3108, 346, 3, 19, 102, 27, 1422, 537, 29499, 4199, 6876, 6985, 4878, 6313, 3007, 111, 3171, 293, 284, 442, 273, 32, 1293, 45, 203, 111, 203, 203, 1358, 667, 1968, 3782, 2205, 26, 44889, 27, 301, 284, 442, 8704, 2418, 8703, 81, 28310, 3188, 10331, 9164, 44889, 16963, 203, 111, 203, 203, 1358, 667, 20440, 53, 14691, 22399, 26, 853, 27, 301, 284, 442, 390, 2027, 3184, 6016, 81, 21589, 32, 858, 26, 501, 2], "prompt_token_count": 157, "reference_codepoints": 256, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [3389, 576, 1621, 48, 400], "continuation_token_count": 5, "decoded": " \n ", "decoded_codepoints": 39, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/infrastructure/test_registry_action_parameter_injection.py", "example_id": "000758ec6be4097dda7294c3a6943214e1ed84abbbc32ff6cbc456abbd742a45", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 225, 333, 1816, 48, 400, 333, 1311, 48, 5600, 2108, 377, 1311, 48, 400, 333, 1621, 48, 528, 3361, 301, 2384, 44, 225, 37, 34, 34, 34, 1082, 45, 320, 528, 638, 8539, 301, 2747, 44, 7976, 45, 320, 528, 588, 1393, 301, 2663, 44, 225, 34, 45, 320, 528, 588, 10511, 301, 2663, 44, 225, 35, 34, 34, 34, 1082, 45, 320, 334, 3, 44, 225, 36, 34, 34, 34, 1082, 45, 320, 400, 576, 1621, 48, 324, 576, 1816, 48, 324, 333, 1548, 48, 400, 333, 507, 804, 347, 1393, 20, 443, 347, 8539, 413, 3155, 432, 322, 1938, 377, 507, 48, 400, 333, 507, 804, 347, 10511, 20, 443, 347, 8539, 413, 18358, 432, 322, 1938, 377, 507, 48, 400, 333, 507, 804, 347, 3462, 20, 443, 347, 2], "prompt_token_count": 133, "reference_codepoints": 32, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [2033, 308, 1117, 27, 14107, 37, 81, 2592, 81, 2627, 26, 6404, 61, 3997, 30, 225, 36, 293, 616, 308, 1117, 27, 14107, 37, 81, 2592, 81, 2627, 26, 6404, 61, 3997, 30, 225, 37, 293, 616, 308, 1117, 27, 14107, 37, 81, 2592, 81, 2627, 26, 6404, 61, 3997, 30, 225, 38, 293, 616, 308, 1117, 27, 14107, 37, 81, 2592, 81, 2627, 26, 6404, 61, 3997, 30, 225, 39, 293, 616, 308, 1117, 27, 14107, 37, 81, 2592, 81, 2627, 26, 6404, 61, 3997, 30, 225, 40, 293, 616], "continuation_token_count": 91, "decoded": " (void)sqlite3_column_double(stmtKnn, 2);\n (void)sqlite3_column_double(stmtKnn, 3);\n (void)sqlite3_column_double(stmtKnn, 4);\n (void)sqlite3_column_double(stmtKnn, 5);\n (void)sqlite3_column_double(stmtKnn, 6);\n ", "decoded_codepoints": 264, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:tests/fuzz/rescore-interleave.c", "example_id": "00076168aeb3b59569b5df0a8e9a4a89015a31cf17bd1d53cd48b29a2c0d379e", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 17735, 37, 81, 4534, 26, 6404, 61, 3997, 293, 291, 17735, 37, 81, 2539, 81, 3006, 26, 6404, 61, 3997, 30, 225, 35, 30, 2678, 3137, 30, 3744, 26, 99, 3137, 471, 4428, 2345, 81, 14673, 293, 291, 2218, 308, 14107, 37, 81, 2997, 26, 6404, 61, 3997, 27, 610, 4428, 2345, 81, 9317, 27, 301, 616, 308, 1117, 27, 14107, 37, 81, 2592, 81, 410, 40, 38, 26, 6404, 61, 3997, 30, 225, 34, 293, 616, 308, 1117, 27, 14107, 37, 81, 2592, 81, 2627, 26, 6404, 61, 3997, 30, 225, 35, 293, 664, 3, 33, 225, 40, 32, 34, 88, 45, 291, 320, 291, 17735, 37, 81, 4534, 26, 6404, 2333, 293, 291, 17735, 37, 81, 2539, 81, 3006, 26, 6404, 2333, 30, 225, 35, 30, 4712, 30, 3744, 26, 3137, 471, 4428, 2345, 81, 8265, 2123, 1438, 293, 291, 17735, 37, 81, 2539, 81, 410, 40, 38, 26, 6404, 2333, 30, 225, 36, 30, 2698, 314, 293, 291, 17735, 37, 81, 2997, 26, 6404, 2333, 293, 291, 1626, 45, 397, 320, 397, 1135, 225, 38, 44, 301, 664, 2], "prompt_token_count": 183, "reference_codepoints": 256, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [15823, 6092, 438, 312, 319, 3780, 31, 15823, 6092, 8440, 203, 1126, 2290, 22945, 23020, 26, 15615, 27, 301, 334, 660, 11847, 280, 4312, 334, 436, 308, 913, 4921, 432, 29141, 27, 301, 284, 1207, 8036, 45, 284, 1596, 301, 8036, 280, 5980, 32, 43288, 4764, 26, 1515, 30, 301, 623, 974, 2424, 44, 861, 1122, 320, 284, 2368, 301, 4036, 45, 320, 284, 436, 308, 913, 3414], "continuation_token_count": 68, "decoded": "compressed pair is a *non-compressed pair*.\nfunction findCompressedPairs(dirs) {\n const pairs = [];\n for (const dir of dirs) {\n let entries;\n try { entries = fs.readdirSync(dir, { withFileTypes: true }); }\n catch { continue; }\n for (const entry", "decoded_codepoints": 258, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/hooks/caveman-stats.js", "example_id": "000773a95a040a6d47431ffdbf5bd336685f8db7fadf3e658a1863a20bb6bd4b", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 44, 5104, 32, 297, 40643, 26, 1421, 27, 1018, 8349, 499, 744, 30, 397, 1688, 10911, 44, 6886, 32, 2024, 81, 8395, 1276, 225, 34, 30, 284, 1122, 334, 320, 334, 442, 301, 1688, 10911, 30, 3320, 2230, 10911, 30, 22565, 30, 1542, 30, 5218, 1472, 203, 111, 203, 203, 306, 25967, 17969, 7318, 32, 954, 517, 17969, 954, 11847, 2841, 16980, 810, 281, 453, 37076, 31, 12447, 32, 886, 203, 306, 20812, 432, 312, 319, 3, 203, 1126, 2290, 22945, 23020, 26, 15615, 27, 301, 334, 660, 11847, 280, 4312, 334, 436, 308, 913, 4921, 432, 29141, 27, 301, 284, 1207, 8036, 45, 284, 1596, 301, 8036, 280, 5980, 32, 43288, 4764, 26, 1515, 30, 301, 623, 974, 2424, 44, 861, 1122, 320, 284, 2368, 301, 4036, 45, 320, 284, 436, 308, 913, 3414, 432, 8036, 27, 301, 397, 415, 1429, 3038, 32, 41778, 346, 225, 2], "prompt_token_count": 149, "reference_codepoints": 256, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [2912, 82, 334, 2276, 32, 203, 31, 7013, 299, 312, 44538, 3051, 2876, 10625, 29010, 1421, 436, 11741, 32, 203, 31, 7013, 299, 312, 44538, 3051, 2876, 10625, 29010, 1421, 436, 11741, 32, 203, 31, 7013, 299, 312, 44538, 3051, 2876, 10625, 29010, 1421, 436, 11741, 32, 203, 31, 7013, 299, 312, 44538, 3051, 2876], "continuation_token_count": 55, "decoded": "git`\n files.\n- Registering a healthy root without identity prompts for conversion.\n- Registering a healthy root without identity prompts for conversion.\n- Registering a healthy root without identity prompts for conversion.\n- Registering a healthy root without", "decoded_codepoints": 260, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:openspec/work/simplify-context-and-workspace-model/slices/store-root-parity/plan.md", "example_id": "000792be53999940db8e817cea47a25e1096f1a85bc70bf8cb1e796470baa19d", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 102, 3096, 32, 203, 203, 1482, 5718, 11398, 203, 203, 2333, 529, 858, 33, 7621, 33, 1819, 31, 2157, 32, 858, 32, 1421, 6083, 203, 203, 31, 10819, 3398, 436, 312, 5816, 3362, 23119, 322, 3536, 3051, 6024, 461, 334, 529, 4524, 81, 2536, 2541, 203, 31, 10819, 19201, 600, 3502, 3362, 32, 203, 31, 10819, 19201, 312, 5575, 31, 2585, 3362, 461, 1406, 33123, 10396, 2912, 33, 3, 30, 6237, 322, 3610, 18978, 2684, 1519, 32, 203, 31, 7013, 299, 312, 14917, 4844, 2464, 8158, 32, 203, 31, 7013, 299, 312, 26886, 44538, 1619, 2968, 34098, 2876, 26116, 31, 761, 334, 19664, 32, 203, 31, 7013, 299, 312, 44538, 3051, 2876, 10625, 29010, 1421, 436, 11741, 32, 203, 31, 18492, 19068, 2], "prompt_token_count": 124, "reference_codepoints": 256, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [563, 313, 7371, 2899, 392, 603, 202, 20, 5566, 563, 313, 23764, 1550, 4878, 392, 603, 202, 20, 1978, 81, 15848, 563, 313, 4173, 1550, 4878, 392, 603, 202, 20, 1141, 563, 428, 577, 202, 109, 1379, 202, 20, 5087], "continuation_token_count": 40, "decoded": "\": \"Complete task\",\n\t\t\t\t\"memory\": \"Closing current tab\",\n\t\t\t\t\"next_goal\": \"Close current tab\",\n\t\t\t\t\"action\": [\n\t\t\t\t\t{\n\t\t\t\t\t\t\"done", "decoded_codepoints": 129, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/browser/test_tabs.py", "example_id": "000793041c9c5d3d1f6f4942156f99dea4f4c1bf81f90b41cafa27aa3b51ee9a", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 101, 81, 15848, 563, 313, 1969, 225, 35, 13197, 328, 537, 4878, 392, 603, 202, 20, 5566, 563, 313, 23764, 1550, 4878, 392, 603, 202, 20, 1978, 81, 15848, 563, 313, 4173, 1550, 4878, 392, 603, 202, 20, 1141, 563, 428, 577, 202, 109, 1379, 202, 20, 2679, 563, 301, 1488, 202, 20, 3007, 81, 314, 563, 313, 34, 34, 34, 35, 20, 1379, 202, 111, 577, 202, 111, 603, 202, 79, 355, 202, 111, 355, 202, 37616, 355, 202, 21, 5245, 225, 38, 44, 16694, 355, 202, 2993, 355, 202, 109, 603, 202, 20, 16462, 299, 20, 3, 202, 20, 1978, 81, 15848, 563, 313, 7371, 2899, 392, 603, 202, 20, 1141, 563, 428, 577, 202, 109, 1379, 202, 20, 5087, 563, 301, 1488, 202, 20, 878, 563, 313, 24724, 8777, 322, 4878, 392, 1488, 202, 20, 3127, 563, 861, 1379, 202, 111, 577, 202, 111, 603, 202, 79, 355, 202, 111, 355, 202, 37616, 357, 202, 79, 1314, 202, 3613, 81, 611, 95, 280, 1487, 81, 3613, 81, 611, 95, 26, 3543, 47, 3543, 27, 1314, 202, 4867, 280, 14225, 26, 355, 202, 2795, 47, 88, 25, 6646, 91, 2], "prompt_token_count": 193, "reference_codepoints": 128, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [264, 415, 308, 3369, 3325, 32, 106, 2377, 225, 34, 32, 34, 962, 8267, 3325, 32, 106, 2511, 47147, 962, 8267, 3325, 32, 107, 2377, 225, 34, 32, 34, 962, 8267, 3325, 32, 107, 2511, 37395, 5421, 96, 20, 284, 313, 351, 27411, 8871, 96, 20, 284, 313], "continuation_token_count": 48, "decoded": " if (innerLocal.x >= 0.0 && innerLocal.x <= iw && innerLocal.y >= 0.0 && innerLocal.y <= ih)\\n\"\n \" discard;\\n\"\n \"", "decoded_codepoints": 129, "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:renderers/GLES3/clay_renderer_gles3.h", "example_id": "0007a198dffc3cff638f563d2cec78796917031e06099e7cd794f78c1048c9b0", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 100, 3325, 32, 106, 2377, 225, 34, 32, 34, 962, 8267, 3325, 32, 106, 2511, 47147, 962, 8267, 3325, 32, 107, 2377, 225, 34, 32, 34, 962, 8267, 3325, 32, 107, 2511, 37395, 5421, 96, 20, 284, 313, 1468, 27411, 8871, 96, 20, 284, 313, 351, 17854, 280, 354, 1514, 8871, 96, 20, 284, 313, 351, 442, 8871, 96, 20, 284, 313, 264, 14713, 96, 20, 284, 313, 264, 434, 24618, 12495, 31, 3478, 19345, 556, 1778, 24618, 78, 96, 20, 284, 313, 264, 3, 225, 313, 351, 415, 308, 9040, 610, 225, 34, 27, 17854, 280, 8925, 26, 103, 9929, 34, 30, 354, 12232, 21814, 96, 20, 284, 313, 351, 415, 308, 9040, 610, 225, 35, 27, 17854, 280, 8925, 26, 103, 9929, 35, 30, 354, 12232, 21814, 96, 20, 284, 313, 351, 415, 308, 9040, 610, 225, 36, 27, 17854, 280, 8925, 26, 103, 9929, 36, 30, 354, 12232, 21814, 96, 20, 284, 313, 351, 415, 308, 9040, 610, 225, 37, 27, 17854, 280, 8925, 26, 103, 9929, 37, 30, 354, 12232, 21814, 96, 20, 284, 313, 264, 14713, 96, 20, 284, 313, 4104, 96, 2], "prompt_token_count": 189, "reference_codepoints": 128, "repo": "nicbarker/clay", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [334, 320, 719, 442, 1619, 203, 111, 203, 203, 1126, 793, 55, 1232, 3075, 30681, 26, 334, 301, 284, 42662, 2084, 44, 313, 507, 392, 284, 4125, 44, 313, 13358, 392, 284, 6410, 44, 313, 10630, 392, 334, 801], "continuation_token_count": 39, "decoded": "\n }\n\n return context\n}\n\nfunction useEmblaCarousel(\n {\n carouselRef: \"div\",\n api: \"carousel\",\n opts: \"horizontal\",\n },", "decoded_codepoints": 130, "document_id": "OpenCut-app/OpenCut@4d8c49ed0706c4dc145361e01c6b1f1a87cbb863:apps/web/src/components/ui/carousel.tsx", "example_id": "0007a488624f389b099125ffa3d7d6f879efd91c7b5698b9a03b8de839ea9d8a", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 539, 94, 3913, 203, 203, 913, 7074, 10223, 1222, 280, 3475, 32, 1297, 1222, 46, 30681, 1222, 3913, 523, 744, 1563, 1693, 27, 203, 203, 1126, 793, 30681, 346, 301, 334, 660, 1619, 280, 3475, 32, 539, 1222, 26, 30681, 1222, 27, 719, 415, 1429, 1819, 27, 301, 284, 1422, 537, 3081, 440, 539, 30681, 2298, 526, 1654, 4797, 312, 333, 30681, 1681, 657, 3, 30, 334, 2417, 2962, 203, 10696, 3475, 32, 42258, 46, 20, 507, 413, 549, 7074, 10223, 3913, 27, 301, 334, 660, 428, 13358, 2084, 30, 4125, 79, 280, 793, 55, 1232, 3075, 30681, 26, 284, 301, 397, 2417, 6363, 30, 397, 6013, 44, 14103, 1720, 313, 10630, 20, 1018, 313, 106, 20, 499, 313, 107, 392, 284, 801, 284, 10252, 334, 829, 334, 660, 428, 3374, 5600, 14122, 30, 739, 4445, 5600, 14122, 79, 280, 902, 329, 2], "prompt_token_count": 144, "reference_codepoints": 128, "repo": "OpenCut-app/OpenCut", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [70, 280, 225, 35, 34, 34, 30, 638, 887, 2611, 280, 225, 35, 34, 34, 30, 638, 887, 3024], "continuation_token_count": 19, "decoded": "T = 100, .minWidth = 100, .minHeight", "decoded_codepoints": 36, "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:examples/clay-official-website/main.c", "example_id": "0007a536e5327e664b27e486eec6429ca684b394c748f1499625d9f6370f0857", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 368, 280, 225, 42, 320, 1790, 301, 324, 5042, 2730, 81, 6016, 26, 1583, 2730, 81, 5203, 440, 7554, 23016, 2113, 5042, 2730, 81, 6016, 81, 6191, 1371, 638, 23180, 280, 225, 38, 42, 30, 638, 2186, 606, 280, 506, 4824, 81, 779, 81, 13777, 81, 39, 40, 30, 638, 43170, 280, 9351, 81, 18863, 10536, 324, 5042, 2730, 26, 1583, 2730, 81, 779, 440, 14674, 41526, 2113, 301, 638, 3086, 280, 301, 638, 19134, 280, 301, 5042, 2730, 81, 31367, 1392, 81, 8135, 73, 13157, 1449, 3, 81, 6016, 26, 1583, 2730, 81, 5203, 440, 12200, 8448, 372, 316, 7924, 1370, 9449, 5316, 3638, 3118, 26551, 5042, 2730, 81, 6016, 81, 6191, 1371, 638, 23180, 280, 225, 36, 42, 30, 638, 2186, 606, 280, 506, 4824, 81, 779, 81, 16938, 81, 37, 40, 30, 638, 43170, 280, 9351, 81, 18863, 10536, 324, 5042, 2730, 81, 6016, 26, 1583, 2730, 81, 5203, 440, 12470, 4117, 22788, 1216, 308, 37, 32, 39, 1232, 1244, 27, 623, 907, 1169, 2], "prompt_token_count": 169, "reference_codepoints": 32, "repo": "nicbarker/clay", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [901, 30, 7650, 44, 901, 1122, 334, 1122, 719], "continuation_token_count": 9, "decoded": " false, force: false });\n });\n\n ", "decoded_codepoints": 33, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/core/references.test.ts", "example_id": "0007a93813642b33cb3e631e6502fa68e6f040bf45bde606cb9795c55b68bad1", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 647, 2164, 32, 2121, 32, 74, 19771, 81, 4601, 81, 8439, 280, 7511, 74, 12579, 750, 4625, 45, 284, 320, 284, 5980, 32, 3925, 4764, 26, 1433, 2976, 30, 301, 18581, 44, 861, 30, 7650, 44, 861, 1122, 334, 1122, 719, 667, 13947, 26, 9535, 1215, 44, 802, 711, 802, 301, 284, 660, 4921, 280, 1519, 32, 2524, 26, 1433, 2976, 30, 6491, 1215, 293, 284, 5980, 32, 10174, 4764, 26, 1515, 30, 301, 18581, 44, 3, 2498, 667, 3909, 2780, 26, 284, 804, 44, 802, 30, 284, 2075, 44, 301, 44538, 4058, 2805, 1905, 45, 5035, 606, 2805, 802, 523, 744, 320, 280, 2149, 334, 8063, 4664, 46, 800, 48, 301, 284, 660, 2968, 4058, 280, 13947, 4199, 26231, 9164, 314, 12833, 284, 415, 308, 2184, 32, 36436, 4058, 3326, 901, 27, 301, 397, 1487, 2961, 2710, 4058, 26, 15504, 2], "prompt_token_count": 143, "reference_codepoints": 32, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [5866, 392, 291, 313, 2798, 48946, 810, 10362, 392, 291, 313, 2798], "continuation_token_count": 12, "decoded": "proxy\",\n \"Connection refused by peer\",\n \"Connection", "decoded_codepoints": 65, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/fetchers/test_proxy_rotation.py", "example_id": "0007ad260fd2400fc813674018868017ad1eb974d5a95cbdbcc22577375e3d5b", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1872, 392, 428, 291, 313, 1299, 403, 530, 81, 5866, 81, 3841, 81, 7815, 392, 291, 313, 4773, 403, 2203, 81, 26681, 81, 9036, 81, 10815, 392, 291, 313, 1299, 403, 530, 81, 25169, 81, 3841, 81, 7815, 392, 291, 313, 2798, 48946, 810, 7664, 392, 291, 313, 2798, 5657, 810, 10362, 392, 291, 313, 2798, 28877, 963, 2218, 22422, 225, 3, 20, 9752, 646, 5889, 7664, 3408, 392, 284, 8834, 284, 665, 894, 81, 5866, 81, 4275, 81, 38309, 26, 784, 30, 1048, 81, 2076, 711, 291, 1524, 1006, 688, 7664, 31, 10513, 3878, 884, 14098, 2993, 291, 1201, 438, 81, 5866, 81, 731, 26, 984, 26, 731, 81, 2076, 490, 438, 2933, 446, 477, 12408, 32, 1826, 32, 28913, 440, 731, 81, 2076, 392, 428, 334, 2], "prompt_token_count": 130, "reference_codepoints": 64, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [14458, 81, 268, 81, 2951, 81, 1793, 81, 2951, 81, 878], "continuation_token_count": 11, "decoded": "handlers_re_empty_with_empty_text", "decoded_codepoints": 33, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/parser/test_parser_advanced.py", "example_id": "0007c141e61cd7b701d93824b3994ef25510300b8df88f708d25dff6e5aba29c", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 878, 81, 14458, 81, 268, 81, 2951, 26, 784, 711, 291, 1524, 1006, 3319, 15556, 32, 268, 346, 544, 3502, 1149, 2993, 291, 15098, 280, 3319, 15556, 24562, 291, 3276, 280, 15098, 32, 268, 26, 100, 7646, 86, 36998, 291, 1201, 6937, 26, 4295, 30, 3319, 15556, 27, 291, 1201, 2069, 26, 4295, 27, 610, 225, 34, 446, 665, 894, 81, 878, 81, 3, 647, 1524, 1006, 3319, 15556, 32, 268, 346, 1412, 1289, 1994, 8001, 2993, 291, 15098, 280, 3319, 15556, 2009, 1031, 1972, 440, 8183, 2113, 3319, 1972, 440, 589, 657, 1130, 291, 3276, 280, 15098, 32, 268, 26, 100, 7646, 86, 36998, 291, 1201, 2069, 26, 4295, 27, 610, 225, 34, 446, 665, 894, 81, 878, 81, 14458, 81, 8281, 26, 784, 711, 291, 313, 2], "prompt_token_count": 130, "reference_codepoints": 32, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [20, 9511, 20, 203, 3474, 313, 9511, 429, 101, 429, 74, 8083, 429, 86, 330, 1777, 31, 620, 44, 3022, 33, 1260, 25], "continuation_token_count": 23, "decoded": "\"curl\"\necho \"curl -s -X POST -d 'Content-Type: application/json'", "decoded_codepoints": 64, "document_id": "steipete/agent-scripts@bb3688355a4c1894dd53b4ed867d1600918fadf0:skills/clawsweeper-status/scripts/clawsweeper-status.test.sh", "example_id": "0007c3ce6a546b0e2ea4eceb832fa3721d51d1632901695fec179c174f388826", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 36, 34, 43, 43, 31, 34, 35, 31, 34, 35, 70, 34, 34, 44, 34, 34, 44, 34, 34, 76, 1461, 16471, 3637, 10638, 5459, 28052, 26296, 2510, 36, 34, 43, 43, 31, 34, 35, 31, 34, 35, 70, 34, 34, 44, 34, 34, 44, 34, 34, 76, 1461, 3260, 10638, 3615, 2510, 573, 812, 1586, 21603, 14944, 40255, 40255, 8129, 284, 10368, 334, 2941, 284, 2248, 313, 22562, 28472, 1476, 44, 398, 22189, 25228, 36, 284, 4323, 225, 35, 284, 10368, 203, 307, 329, 203, 9471, 203, 26030, 474, 106, 3941, 30606, 33, 3141, 20, 203, 203, 2579, 848, 25526, 30606, 33, 9511, 20, 1264, 25, 9471, 25, 203, 8756, 3, 20, 5066, 20, 4028, 1615, 334, 4323, 225, 36, 36, 203, 12106, 428, 6313, 46201, 81, 3765, 81, 4959, 5979, 3845, 280, 313, 3596, 304, 20, 4028, 1615, 334, 5242, 6611, 101, 78, 96, 25, 31167, 9671, 563, 36, 2360, 7147, 299, 563, 37, 2360, 1315, 86, 563, 39, 2360, 1977, 81, 5136, 28052, 1977, 81, 6426, 2510, 858, 33, 2455, 1461, 9671, 563, 35, 2360, 7147, 299, 563, 36, 2360, 1315, 86, 563, 38, 49108, 25, 334, 4323, 225, 34, 203, 5501, 203, 2949, 6611, 101, 78, 96, 25, 31167, 9671, 563, 36, 2], "prompt_token_count": 208, "reference_codepoints": 64, "repo": "steipete/agent-scripts", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [81, 2208, 26, 784, 30, 1789, 27, 446, 2498, 665, 3185, 81, 1526, 26, 784, 30, 1789, 711], "continuation_token_count": 18, "decoded": "_parse(self, response)\n\n async def parse_post(self, response):", "decoded_codepoints": 65, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/spiders/test_sitemap.py", "example_id": "0007cdd77e632fdb5e6a4f6eced01bdbe2e700fb5fad984907eb6b0c7a54bb62", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 264, 443, 358, 26, 69, 23078, 44907, 711, 324, 636, 280, 313, 101, 20, 324, 309, 23078, 81, 11400, 280, 3037, 641, 555, 2763, 32, 508, 33, 33565, 32, 2593, 1446, 1064, 665, 7019, 26, 784, 711, 400, 442, 428, 53, 17734, 3842, 26, 2359, 16653, 26, 4568, 47, 100, 9663, 8224, 33, 2113, 3309, 47, 784, 32, 2208, 81, 1526, 2177, 1064, 2498, 3, 1986, 32, 965, 111, 584, 1869, 1391, 280, 358, 346, 291, 963, 280, 2014, 617, 6174, 26, 35585, 1114, 2208, 81, 33565, 2176, 2682, 81, 1986, 26, 2413, 2695, 81, 5732, 2610, 291, 2364, 81, 2403, 280, 2354, 26, 100, 436, 540, 328, 963, 415, 2430, 8224, 5681, 328, 540, 32, 965, 27, 291, 1603, 280, 2364, 81, 2403, 3667, 371, 1293, 16369, 291, 1201, 1603, 1365, 81, 4383, 81, 426, 1446, 2], "prompt_token_count": 139, "reference_codepoints": 64, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [853, 32, 302, 81, 466, 1026, 313, 264, 7170, 324], "continuation_token_count": 10, "decoded": "value.as_str(), \" \");\n ", "decoded_codepoints": 36, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/yaml_to_toml.rs", "example_id": "0007db975c09a4c8c317b326e4b39203f770bdc063cf585bf05e16af18b109d4", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 882, 5103, 967, 29662, 1599, 301, 284, 1207, 4031, 1858, 280, 29662, 1599, 403, 890, 473, 284, 436, 308, 678, 30, 786, 27, 328, 2078, 301, 291, 1207, 786, 280, 2530, 786, 301, 324, 26024, 81, 1260, 403, 882, 403, 1261, 26, 2810, 27, 532, 301, 400, 2361, 81, 955, 81, 452, 81, 853, 81, 1793, 81, 9378, 26, 2810, 30, 313, 647, 3003, 313, 264, 3003, 225, 3, 617, 532, 2361, 81, 452, 81, 21273, 81, 853, 26, 853, 471, 291, 1472, 291, 1858, 32, 3215, 26, 678, 32, 302, 81, 466, 1026, 786, 293, 284, 320, 284, 2179, 81, 3221, 81, 1274, 81, 7740, 17333, 1652, 2278, 1858, 30, 313, 264, 3003, 313, 225, 7170, 284, 1858, 203, 111, 203, 203, 3359, 2179, 81, 3221, 81, 1274, 81, 7740, 17333, 26, 1274, 44, 549, 2278, 29662, 1599, 30, 1695, 81, 9378, 44, 549, 466, 30, 13734, 81, 21706, 2], "prompt_token_count": 152, "reference_codepoints": 32, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [1667, 9378, 111, 264, 1122, 397, 5430, 32, 2018, 14029, 9378, 111, 264, 320, 1916, 397, 5430, 32, 2018, 14029, 9378, 111, 264, 415, 1886, 452, 479, 87, 27, 301, 9796, 397, 5430, 32, 2018, 14029, 9378, 111, 351, 398, 5961, 3353, 280, 398, 1508, 9796, 397, 5430, 32, 2018, 14029, 9378, 111, 351, 4036, 9796, 397, 5430, 32, 2018, 14029, 9378, 111, 264, 320, 1916, 397, 5430, 32, 2018], "continuation_token_count": 70, "decoded": "${indent} });\n lines.push(`${indent} }});\n lines.push(`${indent} if ($tokee) {`);\n lines.push(`${indent} $skipNext = $true`);\n lines.push(`${indent} continue`);\n lines.push(`${indent} }});\n lines.push", "decoded_codepoints": 256, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/completions/generators/powershell-generator.ts", "example_id": "0007dbac6cf3b7e747eba179327ccbb4f526f38b5b4463383028af2146180d95", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1571, 279, 1284, 280, 225, 34, 9796, 284, 5430, 32, 2018, 14029, 9378, 10598, 5961, 3353, 280, 398, 1870, 9796, 284, 5430, 32, 2018, 14029, 9378, 111, 979, 1886, 91, 280, 2283, 2232, 2731, 279, 1763, 1284, 1255, 398, 91, 429, 2159, 1886, 2501, 1534, 429, 225, 35, 293, 398, 91, 1987, 301, 9796, 284, 5430, 32, 2018, 14029, 9378, 111, 264, 415, 1886, 5961, 3353, 27, 301, 9796, 284, 5430, 32, 2018, 14029, 9378, 111, 351, 398, 3, 895, 397, 5430, 32, 2018, 14029, 9378, 111, 264, 415, 11931, 18766, 4555, 720, 1748, 429, 4752, 398, 1956, 27, 301, 9796, 397, 5430, 32, 2018, 14029, 9378, 111, 351, 398, 5961, 3353, 280, 398, 1508, 9796, 397, 5430, 32, 2018, 14029, 9378, 111, 351, 4036, 9796, 397, 5430, 32, 2018, 14029, 9378, 111, 264, 320, 9796, 397, 5430, 32, 2018, 14029, 9378, 111, 264, 415, 1886, 452, 479, 2], "prompt_token_count": 150, "reference_codepoints": 256, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [30, 225, 34, 27, 203, 306, 225, 202, 2946, 32, 885, 440, 625, 392, 2601], "continuation_token_count": 15, "decoded": ", 0)\n// \tsystem.Set(\"port\", port", "decoded_codepoints": 32, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/hub/config/config_test.go", "example_id": "0007e3177394c3ad1dfb8b180085d44e3f64baf1fde841a84aaba90884f0d54f", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 102, 802, 30, 2601, 1727, 35, 40, 30, 1256, 11519, 1605, 800, 27, 3256, 1262, 32, 3157, 30, 1048, 27, 301, 203, 306, 225, 202, 2946, 2256, 30, 1137, 1025, 1123, 32, 4868, 2256, 9813, 1527, 606, 440, 17579, 657, 203, 306, 225, 202, 325, 1137, 863, 1302, 301, 203, 306, 4222, 202, 601, 1302, 30, 1137, 203, 306, 225, 202, 111, 203, 203, 306, 225, 202, 2946, 1025, 5296, 32, 1812, 3157, 26, 2946, 2256, 27, 203, 306, 225, 202, 2946, 32, 885, 440, 426, 392, 636, 3, 33, 225, 202, 2946, 32, 885, 440, 625, 392, 2601, 27, 203, 306, 225, 202, 2946, 32, 885, 440, 3707, 392, 1256, 11519, 27, 203, 306, 225, 202, 2946, 32, 885, 440, 1517, 392, 313, 9671, 657, 203, 203, 306, 225, 202, 601, 2664, 30, 1123, 32, 5126, 26, 2946, 27, 203, 306, 320, 203, 203, 306, 6160, 667, 372, 1487, 312, 30304, 3627, 203, 1298, 1487, 1063, 1006, 40279, 26, 725, 5296, 32, 1290, 30, 2664, 779, 30, 2404, 30, 8058, 2], "prompt_token_count": 173, "reference_codepoints": 32, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [8058, 334, 8058, 334, 8058, 334, 8058, 334, 8058, 334, 8058, 334, 8058], "continuation_token_count": 13, "decoded": " fi\n fi\n fi\n fi\n fi\n fi\n fi", "decoded_codepoints": 33, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/install.sh", "example_id": "0007e574b93eff190f876f08c0f9e4cb39807d4fcd7c63cba2a94d71c6a9f2b5", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 12780, 1597, 26890, 30, 46363, 623, 11122, 13585, 397, 8058, 1687, 442, 225, 35, 446, 8058, 334, 8058, 719, 428, 429, 88, 3941, 3608, 20, 1481, 962, 1401, 750, 962, 442, 225, 34, 719, 428, 653, 429, 88, 3941, 9328, 20, 1481, 962, 442, 225, 35, 334, 428, 653, 429, 101, 3941, 9328, 20, 1481, 962, 442, 225, 35, 719, 588, 3456, 415, 322, 19687, 1597, 3425, 11451, 810, 2992, 3261, 334, 3, 47, 35, 2287, 47, 4108, 523, 554, 429, 86, 3228, 34, 34, 34, 683, 334, 17281, 19709, 2949, 6611, 101, 25, 3941, 15260, 20, 523, 13568, 429, 51, 310, 429, 102, 816, 35, 429, 104, 523, 554, 429, 86, 330, 766, 96, 27059, 334, 2196, 3432, 347, 35, 40, 20, 334, 5887, 3941, 10656, 4443, 20, 962, 3432, 347, 35, 41, 20, 719, 415, 3813, 3941, 15260, 20, 863, 3941, 2263, 20, 18154, 1615, 446, 3099, 313, 1318, 19687, 1098, 526, 11451, 4056, 3301, 322, 3488, 225, 2], "prompt_token_count": 162, "reference_codepoints": 32, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [202, 1131, 280, 1302, 357, 202, 111, 813, 301, 355, 202, 761, 30, 1137, 1025, 2322, 32, 2961, 2740, 47083, 27, 355, 202, 325, 1137, 6901, 1302, 301, 603, 202, 751, 32, 5497, 440, 7815, 372, 2156, 1509, 803, 44, 904, 104, 392, 1137], "continuation_token_count": 44, "decoded": "\tinput = nil\n\t\t} else {\n\t\t\tfile, err := os.Open(*inputFile)\n\t\t\tif err!= nil {\n\t\t\t\tlog.Errorf(\"failed to open input file: %v\", err", "decoded_codepoints": 129, "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:cmd/robots2policy/main.go", "example_id": "0007e6f8c73068452613dfb4411a3cec715facbba7d1ed74710157eb19cccb31", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 6901, 1302, 301, 355, 202, 751, 32, 14616, 440, 7815, 372, 5630, 13047, 101, 32, 2760, 645, 3834, 44, 904, 104, 392, 1137, 27, 357, 202, 111, 357, 202, 7353, 5127, 32, 3050, 32, 4173, 346, 434, 47467, 410, 44, 530, 1553, 357, 202, 1131, 280, 5127, 32, 3050, 203, 202, 111, 813, 301, 357, 202, 761, 30, 1137, 1025, 2322, 32, 2961, 2740, 47083, 27, 357, 202, 325, 1137, 863, 1302, 301, 355, 202, 751, 32, 14616, 440, 7815, 372, 2156, 1509, 803, 44, 904, 104, 392, 1137, 27, 355, 3, 202, 111, 357, 202, 20974, 357, 202, 1131, 280, 803, 203, 202, 111, 478, 202, 306, 8661, 13047, 101, 32, 2760, 203, 202, 7004, 30, 1137, 1025, 3185, 14843, 101, 17266, 26, 1131, 27, 203, 202, 325, 1137, 863, 1302, 301, 357, 202, 751, 32, 14616, 440, 7815, 372, 3185, 13047, 101, 32, 2760, 44, 904, 104, 392, 1137, 27, 203, 202, 111, 478, 202, 306, 8125, 372, 2244, 356, 297, 7019, 203, 202, 278, 356, 297, 9154, 1025, 42542, 1045, 356, 297, 9154, 26, 7004, 27, 478, 202, 306, 3456, 415, 1346, 7019, 341, 2], "prompt_token_count": 189, "reference_codepoints": 128, "repo": "TecharoHQ/anubis", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [958, 4759, 81, 84, 32, 2679, 346, 446, 665, 894, 81, 2853, 81, 1793, 81, 2951, 81, 2543, 26, 784, 711, 291, 4759, 280, 24864, 3566, 1598, 346, 291, 1596, 44, 324, 4759, 32, 2853, 26, 2521, 30, 313, 983, 31, 858, 657, 291, 2940, 3268, 619, 484, 44, 324, 1201, 313, 11394, 4131, 3502, 1994, 20, 328, 596, 26, 87, 27, 446], "continuation_token_count": 63, "decoded": " storage_b.close()\n\n def test_save_with_empty_element(self):\n storage = SQLiteStorageSystem()\n try:\n storage.save(None, \"path-test\")\n except Exception as e:\n assert \"Cannot save empty element\" in str(e)\n\n ", "decoded_codepoints": 259, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/core/test_storage_core.py", "example_id": "0007f24e80b9a7ad56c7c3c878040bad03a3c0186e8ce2362d6a1270283bf57e", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 300, 1598, 32, 2613, 81, 3815, 346, 324, 9823, 1598, 13976, 1114, 371, 81, 1439, 81, 965, 32, 2613, 81, 3815, 346, 1064, 4759, 81, 84, 280, 24864, 3566, 1598, 26, 4219, 81, 761, 47, 1199, 81, 983, 30, 1984, 347, 641, 555, 2851, 31, 84, 32, 508, 657, 324, 1201, 4759, 81, 84, 32, 19042, 440, 4190, 31, 314, 657, 438, 1665, 291, 8295, 44, 397, 3, 772, 1548, 772, 507, 772, 98, 48, 1031, 377, 98, 855, 507, 855, 1548, 855, 916, 19830, 291, 4759, 32, 2853, 26, 2543, 30, 313, 983, 31, 858, 657, 584, 1056, 280, 4759, 32, 19042, 440, 983, 31, 858, 657, 291, 1201, 1056, 438, 646, 1665, 291, 1201, 313, 983, 20, 328, 1056, 291, 588, 5380, 1395, 526, 312, 1149, 432, 2604, 4467, 645, 1118, 97, 2], "prompt_token_count": 136, "reference_codepoints": 256, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [5980, 32, 32263, 26, 371, 2780, 4097, 1215, 26, 2157, 4058, 471, 330, 3310, 31, 42, 683, 334, 320, 2368], "continuation_token_count": 20, "decoded": " fs.readFile(getStoreMetadataPath(storeRoot), 'utf-8')\n } catch", "decoded_codepoints": 64, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/store/foundation.ts", "example_id": "0007f3ccaa42da95163ec779ae1cb6d83e898223c3b428c62600ef2fbd806372", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 401, 1078, 48, 301, 334, 442, 3185, 2780, 4097, 1078, 26, 284, 2014, 5980, 32, 32263, 26, 371, 2780, 4097, 1215, 26, 2157, 4058, 471, 330, 3310, 31, 42, 683, 334, 1093, 203, 111, 203, 203, 1358, 2498, 667, 1491, 7556, 2780, 4097, 1078, 26, 334, 2968, 4058, 44, 802, 203, 711, 4664, 46, 2780, 4097, 1078, 523, 744, 48, 301, 334, 1596, 301, 284, 442, 2014, 3, 41778, 27981, 26, 731, 490, 301, 397, 442, 744, 45, 284, 320, 446, 1422, 1048, 45, 334, 320, 203, 111, 203, 203, 1358, 2498, 667, 2866, 2780, 4097, 1078, 26, 334, 2968, 4058, 44, 802, 30, 334, 1603, 44, 8809, 4097, 1078, 203, 711, 4664, 46, 1117, 48, 301, 334, 2014, 27234, 2755, 32, 39052, 26, 284, 622, 2780, 4097, 1215, 26, 101, 2], "prompt_token_count": 133, "reference_codepoints": 64, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [3389, 442, 2043, 1064, 415, 6937, 26, 2848, 30, 617, 1099, 1119, 3135, 12283, 711, 400, 442, 3523, 1114, 1580, 1064, 415, 6937, 26, 2848, 30, 617, 1099, 1119, 3135, 711, 400, 442, 3523, 1114, 1580, 1064, 415, 6937, 26, 2848, 30, 617, 1099, 1119], "continuation_token_count": 45, "decoded": " return client\n\n if isinstance(session, _ASyncSessionLogic):\n return session._client\n\n if isinstance(session, _ASyncSession):\n return session._client\n\n if isinstance(session, _ASync", "decoded_codepoints": 258, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/spiders/session.py", "example_id": "0007f5dea1a49ff70f26ab74ec8525a3f5a12376bea4016edba2621fca9676d6", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 4696, 415, 646, 3523, 1114, 297, 81, 19145, 44, 715, 2014, 3523, 3667, 83, 1403, 16369, 1064, 415, 6937, 26, 2848, 30, 15574, 265, 3135, 711, 400, 2043, 280, 3523, 1114, 1580, 2110, 415, 6937, 26, 1580, 30, 617, 1099, 1119, 3135, 12283, 711, 397, 3, 351, 1984, 47, 1357, 32, 965, 30, 715, 1115, 5321, 30, 528, 829, 400, 813, 44, 528, 588, 14353, 3523, 556, 1604, 3738, 429, 15501, 1330, 7292, 328, 2498, 1619, 528, 3636, 12678, 26, 88, 20, 3135, 827, 301, 681, 26, 1580, 4370, 310, 2], "prompt_token_count": 92, "reference_codepoints": 256, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [101, 884, 5816, 30, 844, 883, 793, 322, 529, 878, 82, 1600, 432, 322, 529, 5087, 82, 2125], "continuation_token_count": 18, "decoded": "s are missing, you can use the `text` field of the `done` action", "decoded_codepoints": 64, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/agent/system_prompts/system_prompt_no_thinking.md", "example_id": "00080d88538e9dd8fea59784fbc46982b666471a20b02220c732f597410a15cb", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1319, 18634, 1068, 33007, 6786, 41297, 15412, 372, 4036, 32, 203, 1318, 529, 5087, 82, 2125, 438, 1370, 30824, 372, 23086, 461, 8623, 1370, 44253, 623, 322, 1256, 32, 203, 31, 1756, 529, 3127, 82, 372, 529, 1508, 82, 1755, 415, 322, 3536, 14126, 27747, 1401, 2583, 9435, 623, 1289, 5816, 6339, 32, 203, 31, 1670, 1346, 1742, 432, 322, 1326, 3, 203, 31, 2448, 883, 793, 322, 529, 878, 82, 1600, 432, 322, 529, 5087, 82, 2125, 372, 25420, 1370, 44253, 461, 529, 2536, 81, 452, 81, 2751, 82, 372, 3240, 803, 29847, 372, 322, 1256, 30, 484, 32, 89, 32, 43294, 4295, 32, 954, 1446, 2541, 203, 31, 13938, 11865, 322, 10088, 2471, 844, 2431, 1259, 9019, 328, 322, 529, 878, 82, 1600, 1412, 844, 1476, 529, 11676, 2], "prompt_token_count": 132, "reference_codepoints": 64, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [12499, 81, 15302, 32, 3227, 26, 12499, 81, 15302, 30, 34612, 446, 665, 2164, 81, 4915, 81, 2665, 26, 784, 30, 37196, 711, 291, 1524, 291, 2164, 322, 5713, 5436, 291, 1524, 291, 281, 81, 2665, 280, 630, 32, 2416, 81, 4915, 81, 2665, 81, 2665, 26, 19692, 27, 291, 3420, 81, 426, 280, 281, 81, 2665, 32, 371, 440, 88, 558, 657, 291, 442, 3420, 81, 426, 32], "continuation_token_count": 69, "decoded": "FUNC_PLACE.replace(FUNC_PLACE, \"\"))\n\n def process_children_dict(self, elm):\n \"\"\"\n process the children dict\n \"\"\"\n c_dict = self.process_children_dict_dict(elm)\n func_name = c_dict.get(\"fName\")\n return func_name.", "decoded_codepoints": 256, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converter_utils/docx/math/omml.py", "example_id": "00080fe27cad0ff832d2ad5c871c5d92b4ced2db99a5634154a9c08f82f2f815", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 3557, 32, 371, 440, 5114, 2131, 446, 665, 745, 81, 1298, 26, 784, 30, 37196, 711, 291, 1524, 291, 322, 4540, 31, 9903, 1300, 308, 17533, 44, 7102, 10712, 27, 291, 1524, 291, 281, 81, 2665, 280, 630, 32, 2416, 81, 4915, 81, 2665, 26, 19692, 27, 291, 3420, 81, 426, 280, 281, 81, 2665, 32, 371, 440, 88, 558, 657, 291, 442, 3420, 81, 426, 32, 3227, 26, 12499, 81, 15302, 30, 225, 3, 7678, 327, 81, 13000, 32, 1689, 26, 12499, 77, 102, 1130, 400, 813, 44, 528, 3636, 22210, 440, 1337, 2193, 3420, 904, 101, 20, 904, 273, 27, 324, 813, 44, 400, 7678, 327, 81, 13000, 32, 1689, 26, 102, 27, 291, 273, 280, 15985, 19941, 32, 2524, 26, 24189, 81, 13000, 27, 291, 442, 273, 415, 31993, 81, 15302, 328, 273, 813, 2], "prompt_token_count": 139, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [370, 330, 9436, 370, 330, 9436, 81, 47910, 81, 1055, 370, 284, 330, 10513, 81, 14110, 370, 330, 4189, 370, 330, 9436, 81, 47910, 81, 1055, 370, 203, 997, 2524, 43365, 203, 203, 913, 10246], "continuation_token_count": 35, "decoded": "', 'abstract', 'abstract_inverted_index',\n 'related_works', 'language', 'abstract_inverted_index',\n].join(',');\n\nconst SELECT", "decoded_codepoints": 128, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/openalex/work.js", "example_id": "00081d2b4e65cb3be1adf8b220078d43171185409e2846cc64256a069501d324", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1070, 3770, 10583, 105, 749, 33, 13948, 374, 33, 8200, 920, 203, 465, 301, 284, 18571, 726, 1460, 81, 6177, 30, 284, 5489, 8602, 452, 30, 284, 27708, 2555, 91, 30, 284, 27708, 606, 30, 284, 2156, 1552, 7265, 2483, 30, 284, 44241, 5584, 30, 284, 1205, 2986, 2084, 30, 203, 111, 645, 3005, 2304, 32, 754, 920, 203, 203, 913, 10246, 81, 29054, 280, 428, 284, 330, 314, 370, 330, 13351, 370, 330, 1311, 370, 330, 24518, 81, 3, 370, 330, 10513, 81, 14110, 370, 330, 4189, 370, 330, 9436, 81, 47910, 81, 1055, 370, 203, 997, 2524, 43365, 203, 203, 4538, 1371, 284, 4755, 44, 330, 1676, 23848, 370, 284, 636, 44, 330, 1007, 370, 284, 2857, 44, 330, 850, 370, 284, 3048, 44, 330, 8675, 312, 3982, 3927, 27413, 6337, 308, 12407, 517, 1406, 1216, 517, 7618, 27, 12011, 5035, 474, 5547, 370, 284, 5880, 44, 330, 1237, 32, 41112, 2], "prompt_token_count": 155, "reference_codepoints": 128, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [2095, 1619, 32, 1222, 30, 4559, 3484], "continuation_token_count": 7, "decoded": "ctx context.Context, toolArgument", "decoded_codepoints": 33, "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:components/tool/interface.go", "example_id": "0008275d4a4231deaa63ee7be447f65becae319f74b7590ab8b2fc09473c896c", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 33, 203, 306, 5076, 312, 4559, 4575, 4335, 312, 6216, 461, 600, 41119, 2568, 30, 15635, 1212, 203, 306, 41585, 9408, 322, 41119, 2568, 32, 203, 681, 2556, 19975, 6343, 1253, 444, 3653, 2568, 301, 203, 202, 1761, 3653, 203, 202, 6343, 1253, 444, 2529, 26, 2095, 1619, 32, 1222, 30, 4559, 3484, 319, 3968, 32, 3653, 3484, 30, 6410, 2417, 2828, 27, 308, 3, 2556, 19975, 1862, 444, 3653, 438, 322, 20108, 7442, 432, 428, 45715, 6343, 1253, 444, 3653, 997, 203, 306, 203, 306, 2030, 18393, 428, 3968, 32, 3653, 1394, 79, 18605, 30, 29300, 33530, 10151, 449, 431, 279, 203, 306, 1688, 32, 886, 13097, 438, 18392, 436, 13734, 322, 4717, 428, 3968, 32, 33667, 997, 203, 681, 2556, 19975, 501, 268, 2], "prompt_token_count": 127, "reference_codepoints": 32, "repo": "cloudwego/eino", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [32, 203, 1997, 203, 1997, 886, 529, 21178, 5017, 82, 438, 312, 529, 8254, 82, 43266, 810, 312, 529, 8254], "continuation_token_count": 20, "decoded": ".\n///\n/// The `ConversationMemory` is a `HashMap` backed by a `HashMap", "decoded_codepoints": 70, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:crates/rig-core/src/memory.rs", "example_id": "00084369e998046b223415d17b31e19616c5c31acd76227b4453309e8d8634ec", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 26, 26017, 81, 314, 30, 7050, 3557, 318, 30, 18499, 81, 1498, 27, 284, 320, 203, 111, 203, 203, 1997, 399, 4281, 3664, 31, 4770, 328, 31, 5566, 6370, 21178, 5017, 27641, 43266, 810, 312, 529, 8254, 2541, 203, 1997, 203, 1997, 22641, 884, 7107, 328, 2164, 4117, 1755, 461, 15058, 544, 11686, 32, 36235, 436, 203, 1997, 3312, 30, 8272, 30, 461, 4504, 31, 374, 2236, 25136, 32, 3, 27641, 372, 4871, 312, 8142, 31, 615, 40971, 203, 1997, 17488, 544, 3638, 2454, 308, 28810, 367, 30, 23943, 1649, 30, 316, 31, 24576, 30, 5774, 37786, 203, 1997, 902, 19062, 8189, 20608, 10912, 328, 322, 529, 849, 31, 5566, 82, 29294, 8628, 32, 203, 6357, 11211, 26, 11532, 30, 4101, 2177, 203, 2862, 1671, 701, 5017, 21178, 5017, 301, 284, 8267, 2], "prompt_token_count": 134, "reference_codepoints": 64, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [202, 17435, 26, 18187, 32, 3006, 922, 878, 4251, 38712, 473, 1857, 202, 1824], "continuation_token_count": 14, "decoded": "\tassertThat(textContent.blob().text()).isNotNull();\n\t\t\t\t\t\t\t\t\telse", "decoded_codepoints": 65, "document_id": "modelcontextprotocol/java-sdk@fd004989b9484c9b81be6b03463396797b354804:mcp-test/src/main/java/io/modelcontextprotocol/client/AbstractMcpAsyncClientTests.java", "example_id": "00084561a4935ad967278919f82f85bd8af1370bac29c5cdf905b56907b5941a", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 9181, 202, 306, 31037, 6042, 6550, 4308, 1857, 202, 325, 308, 1286, 5113, 3319, 2291, 8041, 1344, 1777, 27, 301, 5369, 202, 17435, 26, 18187, 32, 878, 4251, 38712, 473, 1857, 202, 111, 1857, 202, 1824, 415, 308, 1286, 5113, 18140, 2291, 8041, 11589, 1777, 27, 301, 5369, 3, 111, 1488, 202, 111, 1379, 202, 111, 577, 202, 111, 603, 202, 1748, 603, 202, 32, 6967, 7371, 473, 357, 202, 1916, 203, 202, 111, 478, 202, 50, 1006, 203, 202, 1117, 894, 720, 2291, 15565, 11446, 20356, 346, 301, 357, 202, 6967, 1853, 12405, 6351, 8618, 24461, 20356, 26, 1580, 967, 2043, 32, 668, 2291, 15565, 26, 63, 2219, 3694, 32, 16838, 81, 12908, 471, 603, 202, 20, 14824, 736, 97, 2], "prompt_token_count": 123, "reference_codepoints": 64, "repo": "modelcontextprotocol/java-sdk", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [111, 284, 829, 334, 320, 203, 111, 203, 203, 1126, 16001, 3173, 1371, 334, 2615, 30, 334, 7442, 30, 334, 5576, 203, 10696, 3475, 32, 21167, 46, 20, 507, 413, 549, 28704, 3913, 46, 5139, 5953, 41729], "continuation_token_count": 37, "decoded": "}\n )\n }\n}\n\nfunction AlertTitle({\n className,\n variant,\n props\n}: React.DataMember<\"div\"> & VariantProps{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [81, 3369, 280, 225, 38, 45, 397, 632, 37, 36, 1169, 81, 7711, 81, 1719, 81, 11925, 280, 225, 38, 45, 397, 632, 37, 36, 3443, 81, 998, 81, 1294, 81, 3369, 280, 3443, 81, 998, 81, 1294, 45, 397, 632, 37, 36, 3443, 81, 998, 81, 1294], "continuation_token_count": 48, "decoded": "_inner = 4;\n U32 all_indices_off_outer = 4;\n U32 stream_count_raw_inner = stream_count_raw;\n U32 stream_count_raw", "decoded_codepoints": 128, "document_id": "EpicGames/raddebugger@78d12eb914378d8552b31c501c12e1c202356024:src/msf/msf_parse.c", "example_id": "00086931c8895e0d2ff418c416bf03cf1e15d386ca1ad9b13fa79a530ae58132", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 994, 261, 280, 1650, 81, 891, 610, 225, 36, 1018, 225, 42, 499, 225, 38, 45, 397, 632, 37, 36, 3443, 81, 998, 81, 1449, 958, 280, 308, 5660, 81, 891, 429, 225, 38, 27, 517, 1334, 81, 1028, 81, 2238, 81, 3038, 45, 397, 632, 37, 36, 3443, 81, 998, 505, 3369, 264, 280, 5958, 757, 3155, 26, 2238, 81, 998, 81, 1294, 30, 3443, 81, 998, 81, 1449, 293, 397, 632, 37, 36, 1169, 81, 2238, 81, 9150, 81, 1719, 280, 225, 38, 45, 397, 632, 37, 36, 1169, 81, 7711, 81, 1719, 3, 261, 3443, 81, 998, 280, 3443, 81, 998, 505, 3369, 45, 397, 18393, 647, 280, 5840, 81, 955, 81, 1347, 81, 6158, 26, 22731, 30, 488, 12036, 81, 6189, 1862, 30, 3443, 81, 998, 293, 8903, 434, 20139, 12998, 461, 10193, 328, 5440, 3111, 397, 632, 37, 36, 1468, 3414, 81, 7017, 280, 1169, 81, 2238, 81, 9150, 81, 1719, 45, 397, 632, 37, 36, 1468, 328, 286, 2], "prompt_token_count": 166, "reference_codepoints": 128, "repo": "EpicGames/raddebugger", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [5307, 368, 327, 81, 10953, 81, 10953, 81, 3274, 81, 507, 32, 83, 31, 1719, 4458, 370, 284, 5307, 368, 327, 81, 10953], "continuation_token_count": 23, "decoded": " '#apex_desktop_desktop_feature_div.a-offscreen',\n '#apex_desktop", "decoded_codepoints": 68, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/amazon/shared.js", "example_id": "00088403aa62b41a62fcac0387d496d210da329e7b9312b8ddfd3ed80dadc649", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 30255, 203, 1358, 660, 9314, 1757, 15052, 280, 330, 9534, 920, 203, 1358, 660, 11190, 81, 31853, 81, 4620, 6535, 280, 428, 284, 5307, 1262, 5606, 81, 3274, 81, 507, 638, 83, 31, 1719, 4458, 370, 284, 5307, 1262, 5606, 3933, 81, 10953, 81, 3274, 81, 507, 638, 83, 31, 1719, 4458, 370, 284, 5307, 1262, 5606, 81, 10953, 638, 83, 31, 1719, 4458, 370, 284, 5307, 368, 327, 81, 10953, 638, 83, 31, 1719, 4458, 370, 284, 3, 264, 5307, 4415, 1521, 81, 515, 4415, 370, 284, 5307, 4415, 1521, 81, 30736, 4415, 370, 284, 5307, 491, 81, 4415, 81, 1521, 81, 2999, 81, 4415, 81, 951, 370, 203, 970, 203, 913, 559, 4384, 1194, 81, 6016, 81, 66, 15835, 3020, 280, 428, 284, 330, 25796, 30, 996, 2258, 1849, 372, 1930, 3654, 844, 6945, 268, 646, 312, 13047, 370, 284, 330, 6545, 322, 7125, 844, 2318, 4794, 370, 284, 330, 620, 322, 7125, 533, 2], "prompt_token_count": 158, "reference_codepoints": 64, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [44, 301, 291, 2074, 9651, 44, 428, 2524, 5791, 300, 15920, 392, 313, 692, 6329, 13960, 2113, 7140, 5791, 4867, 392, 313, 692, 6329, 13960, 657, 614, 291, 3649, 9651, 44, 428, 2524, 26, 2833, 1515, 1026], "continuation_token_count": 37, "decoded": ": {\n projectPaths: [join(\".gemini\", \"antigravity\"), join(\".agent\", \"antigravity\")],\n globalPaths: [join(homedir(),", "decoded_codepoints": 128, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/setup/agents.ts", "example_id": "00088897e96a79a4879097c80fbdd0bc5ea54d30249fcd12f3fbcf6cd6f749bd", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 94, 44, 345, 2219, 2205, 26, 2393, 27, 801, 3796, 471, 284, 801, 284, 5750, 44, 301, 397, 6186, 44, 313, 1689, 392, 397, 803, 44, 308, 3473, 27, 532, 308, 3473, 1720, 313, 3264, 20, 1018, 7140, 26, 2833, 1515, 1026, 4939, 300, 15920, 392, 313, 3055, 4683, 59, 32, 954, 657, 499, 313, 3055, 4683, 59, 32, 954, 2113, 397, 4169, 11125, 44, 313, 2904, 1619, 41, 1101, 392, 284, 801, 284, 20838, 44, 301, 397, 636, 44, 313, 1819, 41, 31, 95, 2219, 20, 3, 14268, 44, 301, 397, 2074, 9651, 44, 428, 2296, 4867, 3439, 397, 3649, 9651, 44, 428, 2524, 26, 2833, 1515, 1026, 4939, 300, 15920, 392, 313, 692, 6329, 13960, 2113, 7140, 26, 2833, 1515, 1026, 4939, 4867, 657, 614, 284, 801, 334, 801, 719, 3226, 15920, 44, 301, 284, 636, 44, 313, 300, 15920, 392, 284, 23085, 44, 313, 26606, 5930, 10070, 392, 284, 345, 2219, 44, 301, 397, 2074, 9651, 44, 428, 2524, 5791, 300, 15920, 392, 2], "prompt_token_count": 168, "reference_codepoints": 128, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [601, 45, 334, 320, 719, 415, 308, 2184, 32, 1260, 27, 301, 284, 2549, 32, 751, 26, 3265, 32, 8136], "continuation_token_count": 20, "decoded": "return;\n }\n\n if (options.json) {\n console.log(JSON.stringify", "decoded_codepoints": 65, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/commands/docs.ts", "example_id": "00089139da129fbde9ad74daeec3504026fcd3ad3322d1cf1b7c843486a2c6b7", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2999, 1720, 225, 34, 27, 301, 284, 30703, 4972, 8447, 4199, 2023, 4333, 2431, 436, 44, 6313, 1217, 111, 3171, 293, 284, 415, 1429, 20759, 27, 1245, 32, 8447, 4199, 2023, 4333, 2431, 436, 44, 6313, 1217, 111, 3171, 293, 284, 442, 45, 334, 320, 719, 30703, 4972, 4048, 473, 719, 415, 308, 2184, 32, 1260, 27, 301, 284, 2549, 32, 751, 26, 3265, 32, 8136, 26, 2095, 30, 744, 30, 225, 36, 876, 275, 3, 913, 20085, 432, 3692, 32, 687, 32463, 27, 301, 397, 1245, 32, 7355, 26, 1970, 32, 8570, 26, 20511, 32, 687, 3173, 876, 397, 415, 308, 20511, 32, 687, 3234, 27, 1245, 32, 3534, 26, 20511, 32, 687, 3234, 293, 397, 1245, 32, 5006, 473, 397, 436, 308, 913, 1340, 432, 20085, 32, 687, 720, 27, 301, 291, 1245, 32, 7355, 440, 914, 20, 474, 1340, 32, 4189, 293, 2], "prompt_token_count": 147, "reference_codepoints": 64, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [2033, 829, 584, 415, 646, 630], "continuation_token_count": 6, "decoded": " )\n\n if not self", "decoded_codepoints": 32, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_xlsx_converter.py", "example_id": "000894fec7a2fa13f63ac130dea59813c35e3d5d9d6abf6713f75d088445c334", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 97, 438, 646, 1665, 44, 324, 3636, 20871, 9672, 984, 26, 400, 44739, 11312, 81, 33384, 25579, 81, 9572, 32, 1643, 26, 528, 17675, 47, 681, 26, 784, 14585, 426, 7642, 528, 5016, 26328, 17831, 392, 528, 2787, 347, 17831, 392, 400, 829, 664, 3, 81, 14806, 81, 1338, 77, 353, 35, 324, 13819, 1793, 81, 35382, 26, 225, 588, 827, 44, 5079, 77, 13304, 31, 2437, 79, 400, 617, 17831, 81, 9277, 81, 14806, 81, 1338, 77, 36, 79, 324, 829, 584, 45665, 280, 6121, 32, 850, 81, 15138, 26, 761, 81, 2238, 30, 13063, 81, 426, 47, 2521, 30, 6863, 347, 9445, 5334, 657, 291, 8735, 81, 1286, 280, 3330, 291, 16870, 2], "prompt_token_count": 116, "reference_codepoints": 32, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [647, 436, 595, 328, 2155, 26, 35, 34, 711, 324, 622, 81, 46466, 26, 91, 27, 584, 623, 48418, 7584, 26, 1449, 81, 17733, 47, 35, 34, 27, 619, 13916, 44, 324, 3276, 280, 13916, 32, 1110, 26, 371, 81, 46466, 30, 2155, 26, 35, 34, 490, 719], "continuation_token_count": 48, "decoded": " for i in range(10):\n get_proxies(i)\n\n with ThreadPoolExecutor(max_workers=10) as executor:\n results = executor.map(get_proxies, range(10))\n\n ", "decoded_codepoints": 176, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/fetchers/test_proxy_rotation.py", "example_id": "000899962eeddeefc6471a08ceb377d8eba0cff17b4522079f27d8c5aa51935c", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 267, 1330, 5749, 3878, 2993, 291, 44028, 280, 428, 88, 20, 525, 555, 98, 109, 91, 10696, 42, 34, 42, 34, 20, 436, 595, 328, 2155, 26, 35, 34, 2177, 291, 5028, 717, 280, 15637, 6726, 717, 26, 46466, 27, 291, 3276, 280, 1605, 584, 665, 622, 81, 46466, 26, 96, 711, 324, 436, 617, 328, 2155, 26, 96, 711, 400, 3276, 32, 1689, 26, 5346, 717, 32, 371, 81, 5866, 1157, 3017, 3, 958, 1201, 1169, 26, 98, 328, 44028, 436, 298, 328, 3276, 27, 446, 665, 894, 81, 3426, 81, 5178, 81, 8347, 81, 3560, 26, 784, 711, 291, 1524, 1006, 22493, 2857, 1471, 48418, 7584, 2993, 291, 44028, 280, 3037, 525, 555, 98, 35, 44, 42, 34, 42, 34, 392, 313, 525, 555, 98, 36, 44, 42, 34, 42, 34, 392, 313, 525, 555, 98, 37, 44, 42, 34, 42, 34, 1446, 291, 5028, 717, 280, 1312, 2], "prompt_token_count": 152, "reference_codepoints": 256, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [1392, 81, 8135, 73, 13157, 1449, 280, 225, 35, 40, 27, 2038, 1790, 2149, 324, 5042, 2730, 81, 6016, 26, 1583, 2730, 81, 5203, 440, 53, 991, 8600, 6895, 328, 4034, 18098, 18751, 12493, 1492, 31, 1621, 4588, 4559, 299, 26551, 5042, 2730, 81, 6016, 81, 6191, 1371, 638, 23180, 280, 225, 36, 42, 30, 638, 2186, 606, 280, 506, 4824, 81, 779, 81, 16938, 81, 37, 40, 30, 638, 43170, 280, 9351, 81, 7097, 30, 638, 43170, 5135, 280, 313, 8570, 392, 638, 43170, 5135], "continuation_token_count": 86, "decoded": "ING_GROW(.max = 16) }} }) {}\n CLAY_TEXT(CLAY_STRING(\"Clay includes built in \\\"Chrome Inspector\\\"-style debug tooling.\"), CLAY_TEXT_CONFIG({ .fontSize = 28, .fontId = FONT_ID_BODY_36, .textColor = COLOR_RED, .textColorSpace = \"bold\", .textColorSpace", "decoded_codepoints": 259, "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:examples/clay-official-website/main.c", "example_id": "0008a09b836ecfa481d6457e4f87134f69a2d51397f5b2db90fbe2a00c9f7689", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 34, 471, 5042, 2730, 81, 31367, 1392, 81, 48393, 13157, 887, 280, 3223, 3024, 429, 225, 39, 34, 27, 801, 638, 2661, 7751, 280, 301, 34, 30, 5042, 2730, 81, 12238, 81, 75, 81, 16582, 835, 638, 5281, 280, 301, 225, 42, 36, 30, 225, 42, 36, 30, 225, 37, 36, 30, 225, 37, 36, 801, 638, 2661, 15723, 280, 225, 40, 38, 801, 638, 21941, 280, 9351, 81, 7097, 1790, 301, 291, 5042, 2730, 26, 1583, 2730, 81, 779, 440, 11054, 3679, 1031, 2113, 301, 638, 3086, 280, 301, 638, 19134, 280, 301, 5042, 2730, 81, 31367, 1392, 81, 3, 11054, 41526, 2113, 301, 638, 3086, 280, 301, 638, 19134, 280, 301, 5042, 2730, 81, 31367, 1392, 81, 8135, 73, 13157, 1449, 280, 225, 35, 40, 27, 2038, 1790, 2149, 324, 5042, 2730, 81, 6016, 26, 1583, 2730, 81, 5203, 440, 53, 991, 8600, 6895, 328, 4034, 18098, 18751, 12493, 1492, 31, 1621, 4588, 4559, 299, 26551, 5042, 2730, 81, 6016, 81, 6191, 1371, 638, 23180, 280, 225, 36, 42, 30, 638, 2186, 606, 280, 506, 4824, 81, 779, 81, 16938, 81, 37, 40, 30, 638, 43170, 2], "prompt_token_count": 190, "reference_codepoints": 256, "repo": "nicbarker/clay", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [48, 24943, 20, 976, 1581, 347, 272, 20, 976, 347, 641, 555, 2763, 32, 508, 33, 272, 33, 1637, 3537, 284, 333, 17193, 44, 1204, 1875, 347, 24943, 20, 976, 1581, 347, 286, 20, 976, 347, 641, 555, 2763, 32, 508, 33, 286, 33, 1637, 3537, 284, 333, 17193, 44, 1204, 1875, 347, 24943, 20, 976, 1581, 347, 283, 20, 976, 347, 641, 555, 2763, 32, 508, 33, 283, 33, 1637, 3537, 284, 333, 17193, 44, 1204, 1875, 347, 24943], "continuation_token_count": 80, "decoded": ">alternate\" hreflang=\"en\" href=\"https://example.com/en/page\"/>\n \n \n {prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [25, 7128, 31, 539, 25, 517, 330, 9718, 13142, 32, 954, 370, 203, 202, 1215, 3949, 331, 44301, 683, 517, 330, 25071, 25, 517, 330, 7128, 31, 539, 25, 517, 330, 9718, 13142, 32, 954, 370, 203, 202, 1215, 3949, 331, 44301, 683, 517, 330, 25071, 25, 517, 330, 7128, 31, 539, 25, 517, 330, 9718, 13142, 32, 954, 370, 203, 202, 1215, 3949, 331, 44301, 683, 517, 330, 25071, 25, 517, 330, 7128, 31, 539, 25, 517, 330, 9718, 13142, 32, 954, 370, 203, 202, 1215, 3949, 331, 44301, 683, 517, 330, 25071, 25, 517, 330, 7128, 31, 539, 25, 517, 330, 9718, 13142], "continuation_token_count": 105, "decoded": "'browser-use' / 'SKILL.md',\n\tPath('.copilot') / 'skills' / 'browser-use' / 'SKILL.md',\n\tPath('.copilot') / 'skills' / 'browser-use' / 'SKILL.md',\n\tPath('.copilot') / 'skills' / 'browser-use' / 'SKILL.md',\n\tPath('.copilot') / 'skills' / 'browser-use' / 'SKILL", "decoded_codepoints": 258, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/test_browser_use_skill_install_docs.py", "example_id": "0008ed93af71ba56d87e4d00bebc537d32b36e048ade5d0f7c6421675a0465ad", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2473, 22705, 683, 517, 330, 25071, 25, 517, 330, 7128, 31, 539, 25, 517, 330, 9718, 13142, 32, 954, 370, 203, 202, 1215, 3949, 8475, 795, 683, 517, 330, 25071, 25, 517, 330, 7128, 31, 539, 25, 517, 330, 9718, 13142, 32, 954, 370, 203, 202, 1215, 3949, 331, 651, 683, 517, 330, 25071, 25, 517, 330, 7128, 31, 539, 25, 517, 330, 9718, 13142, 32, 954, 370, 203, 202, 1215, 3949, 331, 44301, 683, 517, 330, 25071, 25, 517, 330, 7128, 31, 539, 25, 517, 330, 9718, 13142, 32, 954, 370, 203, 202, 1215, 3949, 7017, 683, 517, 330, 25071, 25, 517, 225, 3, 330, 1771, 25, 203, 202, 1771, 81, 1515, 32, 10174, 346, 478, 202, 7971, 280, 7395, 81, 1515, 517, 330, 7971, 25, 203, 202, 7971, 32, 1821, 81, 878, 26, 357, 202, 25, 8756, 3381, 33, 1771, 33, 2121, 4262, 37, 78, 96, 25, 357, 202, 25, 465, 2322, 30, 29969, 30, 5237, 78, 96, 25, 357, 202, 25, 983, 1356, 32, 1215, 26, 500, 32, 12757, 1365, 12232, 81, 15976, 81, 14180, 81, 12896, 81, 3539, 41645, 1821, 81, 878, 440, 4939, 2524, 26, 3731, 32, 6118, 77, 35, 44, 5727, 7328, 347, 3310, 31, 42, 657, 78, 96, 370, 357, 202, 8644, 1057, 3310, 31, 42, 370, 357, 2], "prompt_token_count": 217, "reference_codepoints": 256, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [363, 6679, 25975, 32, 284, 7915, 5820, 31, 7128, 31, 1553, 392, 284, 7915, 5820, 31, 2848, 31, 2446, 22263, 31, 33131, 392, 284, 7915, 5820, 31, 1903, 31, 3483, 31, 11447, 31, 4458, 392, 203, 27, 203, 203, 13803, 81, 37952, 81, 12896, 280, 308, 284, 588, 1283, 12334, 44, 1678, 555, 348, 391, 32, 615, 33, 31716, 33, 27275, 31, 2501, 31, 928, 31, 1586, 21073, 33, 284, 588, 3189, 1247], "continuation_token_count": 73, "decoded": "and less responsive.\n \"--disable-browser-check\",\n \"--disable-session-crashed-bubble\",\n \"--disable-search-engine-choice-screen\",\n)\n\nWEB_BROWSER_ARGS = (\n # Explanation: https://peter.sh/experiments/chromium-command-line-switches/\n # Generally", "decoded_codepoints": 256, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:scrapling/engines/constants.py", "example_id": "0008f021f4c1870b987696249b420eecd9ba4c8cebd03b5f1af08b681a5201fe", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 740, 31, 7128, 31, 1553, 392, 284, 7915, 5820, 31, 2848, 31, 2446, 22263, 31, 33131, 392, 284, 7915, 5820, 31, 1903, 31, 3483, 31, 11447, 31, 4458, 392, 203, 27, 203, 203, 24064, 45541, 81, 12896, 280, 308, 284, 588, 1283, 12334, 44, 1678, 555, 348, 391, 32, 615, 33, 31716, 33, 27275, 31, 2501, 31, 928, 31, 1586, 21073, 33, 284, 588, 3189, 1247, 458, 1098, 1930, 322, 5427, 15162, 225, 3, 20, 287, 7494, 31, 1581, 47, 272, 31, 2045, 392, 284, 7915, 539, 31, 3613, 31, 678, 5074, 392, 284, 7915, 5820, 31, 7393, 392, 284, 7915, 5820, 31, 5894, 31, 1131, 392, 284, 7915, 3518, 31, 2705, 47, 34, 30, 34, 392, 284, 7915, 5820, 31, 27762, 31, 267, 31, 21952, 392, 284, 7915, 3617, 31, 9873, 31, 1521, 668, 392, 284, 7915, 4898, 31, 9374, 31, 6579, 31, 1676, 392, 284, 7915, 4898, 31, 1840, 31, 30184, 392, 334, 2], "prompt_token_count": 157, "reference_codepoints": 256, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [264, 1487, 81, 1003, 262, 38203, 19508, 4040, 21831, 81, 14880, 2370, 1181, 30, 769, 8202, 7808, 438, 322, 1133, 5839, 3733, 561, 461, 5035, 1487, 81, 1003, 203, 27, 203, 203, 6037, 1878, 37992, 17747, 10153, 81, 1648, 81, 1877, 81, 4642, 81, 12764, 26, 9874, 81, 314, 30, 1503, 81, 314, 30, 7715, 27, 203, 8548, 42283, 5223], "continuation_token_count": 60, "decoded": " create_time TIMESTAMPTZ DEFAULT CURRENT_TIMESTAMP NOT NULL, -- processing delay is the time diff between it and metadata create_time\n)\n\nCREATE OR REPLACE FUNCTION workflow_version_update_properties_changes(workflow_id, version_id, delta)\nRETURNS TR", "decoded_codepoints": 256, "document_id": "Netflix/maestro@abdbdadf8f075b8fa488c9efb386b468c709a63c:maestro-engine/src/main/resources/db/migration/postgres/V202008251000__add_workflow_tables.sql", "example_id": "0009010dfde894f97dd252a2f468b684f46a3e177ee896dda0ebfd1f55a38889", "language": "sql", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 3908, 1181, 6210, 308, 1648, 81, 314, 848, 225, 34, 471, 334, 5035, 647, 3398, 52, 2370, 1181, 30, 334, 5644, 264, 3398, 2370, 1181, 30, 334, 6595, 81, 6572, 101, 3398, 52, 30, 334, 1487, 81, 1421, 262, 38203, 19508, 4040, 21831, 81, 14880, 2370, 1181, 30, 769, 8202, 7808, 438, 322, 1133, 5839, 3733, 561, 461, 5035, 1487, 81, 1003, 203, 3, 30, 647, 769, 438, 23902, 619, 1503, 308, 1206, 33220, 23647, 471, 1015, 1503, 415, 5349, 334, 4081, 2071, 3398, 52, 2370, 1181, 30, 264, 769, 4081, 436, 322, 4308, 81, 12764, 334, 4308, 81, 12764, 264, 3398, 52, 2370, 1181, 30, 262, 769, 4308, 3404, 308, 6558, 27, 436, 322, 10153, 999, 587, 2], "prompt_token_count": 120, "reference_codepoints": 256, "repo": "Netflix/maestro", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [109, 397, 2615, 30, 397, 5576, 30, 397, 5576, 30, 397, 5576, 30, 397, 5576], "continuation_token_count": 15, "decoded": "{\n className,\n props,\n props,\n props,\n props", "decoded_codepoints": 69, "document_id": "OpenCut-app/OpenCut@4d8c49ed0706c4dc145361e01c6b1f1a87cbb863:apps/web/src/components/ui/command.tsx", "example_id": "000904ee5b7aade278ea3a25a58bc6311f012da9974220314fae282ecacbade8", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 98, 977, 101, 33, 1707, 33, 1131, 31, 1363, 32, 26897, 20, 203, 465, 301, 677, 9337, 5353, 2913, 320, 645, 6640, 46531, 5353, 33, 2391, 20, 203, 465, 301, 7422, 2913, 30, 34354, 34, 36, 2913, 320, 645, 6640, 46531, 5353, 33, 1262, 31, 3994, 31, 5353, 20, 203, 203, 1126, 5718, 1371, 334, 2615, 30, 334, 2417, 2962, 203, 10696, 3475, 32, 42258, 46, 5139, 5718, 12216, 5103, 301, 334, 442, 308, 275, 3, 291, 313, 5636, 1334, 31, 2620, 5463, 31, 748, 9973, 31, 3864, 13116, 31, 9445, 7481, 31, 15151, 298, 31, 35, 1344, 31, 15151, 31, 29242, 392, 291, 2615, 397, 14301, 397, 12399, 2962, 111, 284, 1681, 334, 829, 203, 111, 203, 203, 1126, 5718, 3728, 1371, 334, 1780, 280, 313, 2019, 46299, 392, 334, 3048, 280, 313, 3192, 436, 312, 2016, 372, 540, 2], "prompt_token_count": 142, "reference_codepoints": 64, "repo": "OpenCut-app/OpenCut", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [266, 13850, 9609, 1345, 81, 74, 4900, 81, 19814, 69, 44, 324, 442, 2933, 584, 415, 5016], "continuation_token_count": 17, "decoded": "in ACCEPTED_XLS_EXTENSIONS:\n return True\n\n if extension", "decoded_codepoints": 73, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_xlsx_converter.py", "example_id": "00090a26fe25e21c916713a68f575ef67312e89ec42f386b20ce35e5b2af92a5", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 95, 44, 13312, 2338, 30, 291, 3443, 81, 1338, 44, 7537, 1120, 30, 291, 1115, 5321, 44, 6204, 30, 225, 588, 11024, 372, 3097, 372, 322, 17675, 284, 829, 967, 1560, 44, 291, 18346, 681, 280, 308, 2238, 81, 1338, 32, 14639, 681, 556, 32375, 5729, 346, 291, 5016, 280, 308, 2238, 81, 1338, 32, 6728, 556, 32375, 5729, 346, 584, 415, 5016, 225, 3, 225, 436, 5202, 328, 13850, 9609, 1345, 81, 74, 4900, 81, 14038, 81, 2319, 81, 9857, 940, 44, 324, 415, 18346, 681, 32, 15990, 26, 4254, 711, 400, 442, 2933, 584, 442, 3177, 446, 665, 4483, 26, 291, 630, 30, 291, 803, 81, 2238, 44, 13312, 2338, 30, 291, 3443, 81, 1338, 44, 7537, 1120, 30, 291, 1115, 5321, 44, 2], "prompt_token_count": 127, "reference_codepoints": 64, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [], "continuation_token_count": 0, "decoded": "", "decoded_codepoints": 0, "document_id": "steipete/agent-scripts@bb3688355a4c1894dd53b4ed867d1600918fadf0:skills/clawsweeper-status/scripts/clawsweeper-status.test.sh", "example_id": "00091bca56889a5efbc0d75c7793d7a4ffa08fba0973a843b1180a9102b9c93d", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 3007, 460, 606, 563, 36, 38, 2360, 426, 2510, 34041, 4583, 17340, 629, 1062, 1461, 1517, 2510, 22115, 1461, 468, 13715, 563, 1693, 2360, 26296, 2510, 36, 34, 43, 43, 31, 34, 35, 31, 34, 35, 70, 34, 34, 44, 34, 34, 44, 34, 34, 76, 1461, 965, 2510, 641, 555, 933, 32, 858, 33, 19245, 33, 36, 38, 3612, 18262, 284, 10368, 334, 313, 1237, 25195, 33, 858, 33, 1586, 21603, 33, 3543, 33, 19245, 49, 1517, 47, 11879, 24, 462, 81, 1637, 47, 35, 36, 657, 284, 5242, 6611, 101, 78, 96, 25, 3, 284, 5242, 6611, 101, 78, 96, 25, 31167, 605, 10638, 37969, 10638, 5459, 28052, 1311, 2510, 13624, 5083, 1326, 1461, 965, 2510, 641, 555, 933, 32, 858, 33, 3978, 33, 43, 1461, 10687, 1076, 2510, 36, 34, 43, 43, 31, 34, 35, 31, 34, 35, 70, 34, 34, 44, 34, 34, 44, 34, 34, 76, 1461, 16471, 3637, 10638, 5459, 28052, 26296, 2510, 36, 34, 43, 43, 31, 34, 35, 31, 34, 35, 70, 34, 34, 44, 34, 34, 44, 34, 34, 76, 1461, 3260, 10638, 3615, 2510, 573, 812, 1586, 21603, 14944, 40255, 15755, 20, 4476, 563, 2], "prompt_token_count": 196, "reference_codepoints": 256, "repo": "steipete/agent-scripts", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [284, 319, 261, 1756, 322, 529, 3898, 3277, 81, 9871, 1392, 81, 17252, 81, 3307, 6083, 291, 319, 261, 7645, 372, 322, 24814, 2330, 44, 1678, 555, 1237, 32, 19246, 32, 508, 33, 1237, 33, 2393, 33, 1333, 31, 266, 284, 319, 261, 1756], "continuation_token_count": 44, "decoded": "\n * Set the `SLACK_SIGNING_SECRET_KEY`:\n * Go to the Slack API: https://api.slack.com/api/auth/sign-in\n * Set", "decoded_codepoints": 128, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:examples/integrations/slack/README.md", "example_id": "00091f82579aa369d676d347b6622057aadc27145f67d2da452be7a26fa6d1bc", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 28, 886, 3834, 3943, 810, 7388, 27835, 438, 11227, 34409, 461, 1098, 1539, 2504, 1133, 7388, 27835, 438, 7307, 32, 2448, 1098, 1849, 372, 1974, 322, 1326, 3834, 328, 322, 7361, 1182, 4070, 2504, 1133, 844, 11686, 7388, 27835, 32, 428, 7488, 2624, 372, 1974, 322, 1326, 3834, 4286, 34933, 31, 1382, 31, 1357, 31, 965, 31, 266, 31, 38281, 31, 3550, 547, 3, 33165, 392, 5021, 544, 313, 7203, 1995, 372, 33165, 2296, 284, 319, 261, 18756, 322, 29010, 1421, 372, 32917, 322, 1123, 461, 1015, 561, 372, 1370, 13571, 32, 203, 39, 32, 1756, 973, 4706, 4886, 44, 284, 319, 261, 49056, 322, 529, 3898, 3277, 81, 9871, 1392, 81, 17252, 6083, 291, 319, 261, 7645, 372, 322, 24814, 2330, 44, 1678, 555, 1237, 32, 19246, 32, 85, 2], "prompt_token_count": 132, "reference_codepoints": 128, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [225, 529], "continuation_token_count": 2, "decoded": " `", "decoded_codepoints": 3, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:openspec/work/simplify-context-and-workspace-model/slices/store-root-parity/plan.md", "example_id": "000920c9c014e28d479b9f9da14fccc3c2fb89c05404f1696361dea965e93782", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 543, 32, 203, 31, 19256, 107, 33032, 2876, 10625, 328, 3398, 33, 3780, 31, 17107, 2926, 7351, 12999, 7134, 82, 334, 438, 5403, 32, 203, 203, 5399, 993, 44, 203, 203, 31, 6468, 4905, 10625, 30, 1974, 2196, 10880, 1755, 1412, 5349, 32, 203, 31, 6468, 24954, 11741, 30, 1487, 10396, 11593, 897, 31, 2157, 33, 2157, 32, 6045, 82, 461, 1974, 322, 664, 3, 11593, 897, 15982, 26116, 2276, 5929, 3909, 32, 203, 203, 26063, 11741, 13012, 1395, 526, 3872, 44, 203, 203, 914, 878, 203, 13659, 458, 3927, 2710, 3051, 1991, 1619, 2968, 313, 5883, 31, 1819, 37827, 203, 914, 203, 203, 1482, 529, 1819, 31, 2157, 35726, 82, 203, 203, 34158, 438, 322, 2979, 31, 2278, 1741, 11806, 11213, 32, 203, 203, 1011, 9371, 44, 203, 203, 31, 7882, 297, 2], "prompt_token_count": 135, "reference_codepoints": 32, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [25, 2812, 672, 370, 225, 35, 42, 42, 30, 225, 38, 32, 42, 471, 334, 308, 40, 30, 13198, 40, 16249, 330, 19252, 5782, 370, 225, 35, 37, 38, 30, 225, 38, 32, 35, 471, 334, 308, 41, 30, 13198, 41, 16249, 330, 331, 1967, 107, 370, 225, 37, 42, 36, 30, 225, 36, 32, 40, 471, 334, 308, 42, 30, 13198, 42, 16249, 330, 545, 1037, 370, 225, 39, 37, 30, 225, 39, 32, 34, 471, 334, 308], "continuation_token_count": 79, "decoded": "'documentary', 188, 4.8),\n (6, '[6]', 'horror', 134, 4.1),\n (7, '[7]', 'comedy', 382, 2.6),\n (8, '[8]', 'scifi', 53, 5.0),\n (", "decoded_codepoints": 129, "document_id": "asg017/sqlite-vec@04d28bd21773981e2d266bbf6aa4efbd011eb4f6:test.sql", "example_id": "00092a611791e247b4e4dc354e1dcdcaf575d21cf754b9a8807c8ca51f16111c", "language": "sql", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 225, 38, 32, 42, 293, 203, 1958, 203, 203, 1109, 203, 203, 2631, 2641, 4712, 81, 22195, 26, 12895, 81, 314, 30, 10437, 23817, 81, 20711, 30, 34280, 30, 1929, 81, 17288, 30, 5651, 81, 11619, 27, 203, 20866, 334, 308, 35, 30, 13198, 35, 16249, 330, 19252, 5782, 370, 225, 35, 39, 37, 30, 225, 38, 32, 40, 471, 334, 308, 36, 30, 13198, 36, 16249, 330, 331, 1967, 107, 370, 225, 37, 42, 36, 30, 225, 36, 32, 40, 471, 334, 308, 37, 30, 13198, 37, 16249, 330, 545, 1037, 370, 225, 39, 37, 30, 225, 39, 32, 34, 471, 334, 308, 38, 30, 13198, 38, 16249, 330, 88, 41415, 370, 225, 36, 35, 34, 30, 225, 38, 32, 36, 471, 334, 308, 39, 30, 13198, 39, 16249, 225, 3, 26, 43, 30, 13198, 43, 16249, 330, 88, 41415, 370, 225, 35, 37, 38, 30, 225, 38, 32, 35, 471, 334, 308, 35, 34, 30, 13198, 35, 34, 16249, 330, 2812, 672, 370, 225, 40, 40, 30, 225, 37, 32, 36, 471, 334, 308, 35, 35, 30, 13198, 35, 35, 16249, 330, 19252, 5782, 370, 225, 42, 42, 30, 225, 38, 32, 43, 471, 334, 308, 35, 36, 30, 13198, 35, 36, 16249, 330, 331, 1967, 107, 370, 225, 39, 43, 30, 225, 36, 32, 42, 471, 334, 308, 35, 37, 30, 13198, 35, 37, 16249, 330, 545, 1037, 370, 225, 38, 36, 37, 30, 225, 38, 32, 39, 471, 334, 308, 35, 38, 30, 13198, 35, 38, 16249, 330, 88, 41415, 370, 225, 36, 41, 39, 30, 225, 37, 32, 40, 471, 334, 308, 35, 39, 30, 13198, 35, 39, 16249, 330, 2812, 672, 370, 225, 35, 43, 35, 30, 225, 38, 32, 38, 471, 203, 2], "prompt_token_count": 291, "reference_codepoints": 128, "repo": "asg017/sqlite-vec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [7188, 313, 681, 563, 313, 9822, 403, 15825, 403, 6772, 403, 890, 392, 1014, 313, 1131, 563, 301, 1378], "continuation_token_count": 19, "decoded": " \"type\": \"crate::completion::Usage::new\",\n \"input\": {\n ", "decoded_codepoints": 133, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:crates/rig-core/src/providers/openai/embedding.rs", "example_id": "00092bf1482784fe779d7d3a83adbadf7d42cf7daa614059a9f2a8ab6cf6ee8c", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 103, 40, 38, 471, 1014, 3320, 81, 16777, 81, 1131, 81, 8395, 44, 225, 34, 30, 1014, 4559, 81, 539, 81, 13232, 81, 8395, 44, 225, 34, 30, 1014, 5966, 299, 81, 8395, 44, 225, 34, 30, 715, 801, 715, 1665, 415, 8744, 403, 4858, 44785, 81, 25948, 532, 301, 664, 3, 30, 1014, 1122, 715, 320, 715, 1665, 532, 8628, 403, 15825, 403, 6772, 403, 890, 1026, 528, 1472, 3688, 1207, 41584, 280, 1789, 715, 638, 605, 715, 638, 8005, 81, 91, 2], "prompt_token_count": 85, "reference_codepoints": 128, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [202, 325, 1447, 81, 5729, 328, 5420, 81, 9081, 44, 355, 202, 601, 296, 20, 924, 44, 16806], "continuation_token_count": 18, "decoded": "\tif ext_lower in supported_extensions:\n\t\t\treturn f\"Error: Cannot", "decoded_codepoints": 64, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:browser_use/filesystem/file_system.py", "example_id": "00093ad5723b53506a91e6b9b664a5bfca67ad9dcfbbf842225d73335d92b907", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 27, 967, 596, 44, 203, 202, 2993, 3313, 312, 2818, 1048, 1474, 44000, 6916, 322, 4870, 1597, 21347, 461, 2624, 372, 2421, 561, 7103, 203, 202, 1439, 280, 2322, 32, 983, 32, 15705, 26, 761, 81, 426, 27, 478, 202, 21, 3456, 436, 5298, 33, 893, 5016, 203, 202, 325, 18491, 328, 1695, 44, 357, 202, 3739, 1447, 280, 1695, 32, 100, 2998, 39054, 225, 35, 27, 357, 202, 407, 81, 5729, 280, 1447, 32, 5729, 346, 357, 3, 88, 20, 924, 44, 16806, 2866, 5298, 33, 893, 803, 8930, 1439, 16805, 313, 603, 202, 88, 25, 1318, 2866, 81, 761, 4559, 1755, 9567, 1344, 31, 7873, 2276, 32, 330, 603, 202, 88, 25, 10323, 11581, 44, 301, 392, 4939, 2524, 440, 3107, 474, 484, 436, 484, 328, 5420, 81, 9081, 31842, 330, 603, 202, 88, 25, 1562, 26516, 30, 322, 5427, 6924, 40341, 3026, 2], "prompt_token_count": 147, "reference_codepoints": 64, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [647, 428, 429, 96, 3941, 426, 20, 1481, 962, 17161, 313, 5842, 636, 44, 8493, 426, 7362, 284, 8058, 446, 415, 428, 429, 96, 3941, 426, 20, 1481, 962, 397, 3813, 6313, 16142, 81, 314, 4781, 3845, 610, 319, 24168, 6569, 20, 18154], "continuation_token_count": 43, "decoded": " [ -n \"$name\" ] && warn \"Unknown name: '$name'\"\n fi\n\n if [ -n \"$name\" ] &&\n [[ \"${candidate_id,,}\" == *\"-eval\" ]];", "decoded_codepoints": 130, "document_id": "dockur/windows@36d127d8cfdccb007e03a0c2ee579f75685605fc:src/image.sh", "example_id": "00093ebd213853a9603cc65b03e86baf5807c80c71f3c62d550170cc2deb86bb", "language": "shell", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 3925, 657, 1687, 428, 429, 96, 3941, 16142, 81, 1439, 20, 1481, 962, 428, 429, 96, 3941, 16142, 81, 314, 20, 1481, 962, 1626, 284, 3390, 446, 415, 428, 429, 108, 3941, 16142, 81, 1439, 20, 1481, 1276, 428, 429, 108, 3941, 16142, 81, 314, 20, 4028, 1615, 397, 2196, 636, 9483, 2751, 5979, 1667, 893, 5979, 22, 2445, 11590, 397, 428, 429, 96, 3941, 426, 20, 1481, 962, 17161, 313, 5842, 1778, 636, 44, 8493, 426, 7362, 334, 3, 28, 1276, 397, 6313, 2445, 4781, 3845, 610, 46760, 22574, 41731, 1276, 397, 6313, 31728, 81, 314, 4781, 3845, 610, 46760, 6569, 41731, 1276, 397, 6313, 4545, 4781, 3845, 610, 46760, 6569, 41731, 18154, 1615, 397, 11903, 11150, 6569, 20, 284, 8058, 446, 415, 428, 429, 96, 3941, 22574, 20, 1481, 962, 397, 3813, 6313, 16142, 81, 314, 4781, 3845, 863, 319, 24168, 6569, 20, 18154, 1615, 397, 15133, 81, 2], "prompt_token_count": 152, "reference_codepoints": 128, "repo": "dockur/windows", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [647, 801, 400, 313, 1132, 563, 301, 313, 681, 563, 313, 1473, 392, 313, 4642, 563, 301, 313, 681, 563, 313, 1473, 392, 313, 4642, 563, 301, 313, 681, 563, 313, 800, 20, 320, 320, 801, 400, 313, 5919, 563, 301, 313, 681, 563, 313, 955, 392, 313, 3028, 563, 301, 313, 681, 563, 313, 800, 20, 320, 801, 400, 313, 12637, 563, 301, 313, 681, 563, 313, 800, 20, 320, 324], "continuation_token_count": 72, "decoded": " },\n \"args\": { \"type\": \"object\", \"properties\": { \"type\": \"object\", \"properties\": { \"type\": \"string\" } } },\n \"labels\": { \"type\": \"array\", \"items\": { \"type\": \"string\" } },\n \"separator\": { \"type\": \"string\" }\n ", "decoded_codepoints": 266, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:tests/providers/openrouter/cassette/agent_tool_sessions.rs", "example_id": "00094007dbec636375d3a436f6a414b2b4315d83b37d889bac335b1f733c2f90", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1260, 19, 1371, 324, 313, 681, 563, 313, 1473, 392, 324, 313, 4642, 563, 301, 400, 313, 5919, 563, 301, 528, 313, 681, 563, 313, 955, 392, 528, 313, 3028, 563, 301, 313, 681, 563, 313, 800, 20, 320, 400, 801, 400, 313, 12637, 563, 301, 313, 681, 563, 313, 800, 20, 320, 1568, 3, 32, 751, 30, 6609, 403, 2474, 30, 549, 1132, 293, 291, 6311, 26, 1643, 9170, 11379, 69, 31, 2950, 12263, 2181, 32, 5919, 32, 2524, 1652, 1132, 32, 12637, 2610, 284, 320, 203, 111, 203, 203, 3106, 10018, 436, 516, 10946, 23872, 301, 284, 660, 8912, 44, 15068, 1574, 596, 280, 313, 11731, 81, 3474, 866, 284, 827, 3081, 280, 6548, 3653, 924, 45, 284, 827, 10460, 280, 41518, 3080, 45, 284, 827, 5582, 225, 2], "prompt_token_count": 132, "reference_codepoints": 256, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [2538, 1104, 109, 357, 202, 9140, 44, 2430, 858, 32, 978, 392, 357, 202, 1777, 44, 225, 313, 589, 17964, 2262, 78, 96, 264, 1459, 463, 731, 683, 78, 96, 264, 1459, 463, 5860, 683, 392, 203, 202, 1748, 203, 202, 7878, 32, 2538, 26, 2095, 30, 225, 2538, 1104, 109, 357, 202, 9140, 44, 2430, 858, 32, 978, 392, 357, 202, 1777, 44, 225, 313, 589, 17964, 2262, 78, 96, 264, 1459, 463, 731, 683, 78, 96, 264, 1459, 463, 5860, 683, 392, 203, 202, 1748, 203, 202, 7878, 32, 2538, 26, 2095], "continuation_token_count": 94, "decoded": "WriteRequest{\n\t\tFilePath: \"/test.py\",\n\t\tContent: \"def hello():\\n print('error')\\n print('world')\",\n\t})\n\tbackend.Write(ctx, WriteRequest{\n\t\tFilePath: \"/test.py\",\n\t\tContent: \"def hello():\\n print('error')\\n print('world')\",\n\t})\n\tbackend.Write(ctx", "decoded_codepoints": 258, "document_id": "cloudwego/eino@ca0441ac0bceed8945dcf7d5a18c237c924c6aa8:adk/filesystem/backend_inmemory_test.go", "example_id": "000945398fa2d18f073642a3e733f762c6573828f1ccc43afc1dbbf601f658f8", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1704, 392, 357, 202, 1777, 44, 225, 313, 1320, 2575, 78, 96, 1298, 2575, 346, 6913, 96, 78, 102, 751, 32, 924, 26326, 731, 33865, 78, 96, 78, 102, 3972, 32, 10307, 26326, 7656, 33865, 78, 96, 6553, 203, 202, 1748, 203, 202, 7878, 32, 2538, 26, 2095, 30, 549, 2538, 1104, 109, 357, 202, 9140, 44, 2430, 858, 32, 978, 392, 357, 202, 1777, 44, 225, 313, 589, 17964, 2262, 78, 96, 264, 1459, 463, 731, 683, 78, 96, 264, 1459, 463, 5860, 683, 392, 203, 202, 1748, 203, 202, 7878, 32, 2538, 26, 2095, 30, 225, 3, 1748, 357, 202, 325, 1137, 863, 1302, 301, 355, 202, 102, 32, 14616, 440, 57, 4315, 6189, 3803, 44, 904, 104, 392, 1137, 27, 357, 202, 111, 357, 202, 325, 2069, 26, 8933, 27, 863, 225, 37, 301, 355, 202, 102, 32, 5497, 440, 7700, 225, 36, 8001, 30, 5424, 904, 86, 392, 2069, 26, 8933, 490, 357, 202, 111, 203, 202, 1748, 478, 202, 102, 32, 2529, 440, 2951, 5257, 1048, 392, 3420, 26, 102, 319, 4266, 32, 70, 27, 301, 357, 202, 3739, 1137, 1025, 9161, 32, 57, 4315, 6189, 26, 2095, 30, 549, 57, 4315, 1104, 109, 355, 202, 66, 2], "prompt_token_count": 204, "reference_codepoints": 256, "repo": "cloudwego/eino", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [101, 432, 322, 1256, 30, 461, 1615, 18613, 322, 1056, 1751, 372, 322, 2043, 32, 895, 284], "continuation_token_count": 17, "decoded": "s of the user, and then sends the result back to the client.');\n ", "decoded_codepoints": 67, "document_id": "jackwener/OpenCLI@5256711a25458e537c5a63d2a6f9c7fd36d0d1eb:clis/lichess/lichess.test.js", "example_id": "0009455a87836a3d975355b1b827c1c1483e60d06bc81808c67da80f037f3047", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1960, 32, 8136, 1371, 324, 804, 44, 330, 10687, 31, 496, 370, 952, 44, 330, 13624, 1240, 370, 6869, 44, 861, 30, 291, 7305, 301, 2287, 44, 225, 36, 34, 34, 320, 4236, 291, 2014, 1424, 26, 3515, 32, 1298, 1371, 952, 44, 330, 13624, 1240, 25, 42709, 11592, 101, 32, 32000, 26, 2766, 1394, 924, 293, 284, 1122, 446, 561, 463, 98, 6758, 322, 4630, 31, 1066, 318, 24605, 3, 922, 3613, 17923, 882, 26, 890, 5170, 26, 3265, 32, 8136, 1371, 324, 804, 44, 330, 6060, 3840, 370, 324, 952, 44, 330, 7303, 3505, 370, 324, 25463, 44, 225, 35, 39, 38, 37, 34, 34, 34, 34, 34, 34, 34, 34, 34, 30, 324, 10925, 1076, 44, 225, 35, 41, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 30, 324, 2385, 44, 301, 1169, 44, 225, 35, 34, 34, 30, 8888, 44, 225, 39, 34, 30, 7699, 44, 225, 37, 34, 30, 5171, 44, 225, 36, 34, 801, 275, 2], "prompt_token_count": 166, "reference_codepoints": 64, "repo": "jackwener/OpenCLI", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [284, 1135, 25117, 26, 100, 47, 35, 30, 1695, 47, 84, 30, 2384, 47, 90, 711, 291, 442, 225, 34, 32, 39, 319, 323, 319, 420, 284, 1135, 31526, 26, 100, 47, 35, 30, 1695, 47, 84, 30, 2384, 47, 90, 711, 291, 442, 225, 34, 32, 39, 319, 323, 319, 420, 284, 1135, 10379, 6522, 26, 100, 47, 35, 30, 1695, 47, 84, 30, 2384, 47, 90, 711, 291, 442, 225, 34, 32, 39, 319, 323, 319, 420, 284, 1135, 10379, 6522, 26, 100, 47, 35, 30, 1695, 47, 84, 30, 2384, 47, 90, 711, 291, 442], "continuation_token_count": 98, "decoded": "\n case Circle(r=1, base=b, height=h):\n return 0.5 * b * h\n case Square(r=1, base=b, height=h):\n return 0.5 * b * h\n case Ellipse(r=1, base=b, height=h):\n return 0.5 * b * h\n case Ellipse(r=1, base=b, height=h):\n return", "decoded_codepoints": 258, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:python-book/src/ch06-enums-and-pattern-matching.md", "example_id": "00094d0d8cd9030d32f3a9af6d21505767d7718add9c02389fe7a74e9d42dff4", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 44, 324, 442, 225, 37, 32, 35, 38, 35, 39, 43, 319, 540, 319, 540, 291, 1135, 18109, 26, 1644, 47, 105, 30, 2384, 47, 90, 711, 324, 442, 341, 319, 420, 291, 1135, 39477, 26, 1439, 47, 84, 30, 2384, 47, 90, 711, 324, 442, 225, 34, 32, 39, 319, 323, 319, 420, 291, 588, 3139, 8980, 5967, 415, 844, 25184, 312, 1135, 19, 291, 588, 18913, 312, 537, 6024, 49, 3, 12955, 26, 88, 40, 38, 30, 296, 40, 38, 471, 351, 434, 18109, 6346, 3064, 1861, 30, 2384, 284, 39477, 301, 1695, 44, 296, 40, 38, 30, 2384, 44, 296, 40, 38, 801, 434, 19584, 3829, 2329, 1389, 203, 111, 203, 203, 3359, 5951, 26, 3229, 44, 549, 4735, 27, 967, 296, 40, 38, 301, 284, 2530, 6024, 301, 291, 17249, 403, 12127, 26, 100, 27, 532, 1230, 403, 88, 40, 38, 403, 40403, 403, 1164, 319, 540, 319, 540, 30, 291, 17249, 403, 2], "prompt_token_count": 159, "reference_codepoints": 256, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [5877, 7234, 203, 203, 823, 2108, 6720, 26, 18986, 32, 7233, 711, 284, 665, 894, 81, 5954, 26, 784, 711, 291, 11492, 280, 31672, 346, 584, 4395, 81, 1267, 280, 25864, 3660, 346, 291, 4395, 81, 1267, 32, 8078, 280, 1605, 291, 4395, 81, 3415, 1180, 280, 25864, 3660, 346, 291], "continuation_token_count": 51, "decoded": "-------------------------------------------------------\n\nclass TestConvert(unittest.TestCase):\n def test_convert(self):\n conv = Converter()\n\n mock_result = MagicMock()\n mock_result.contents = []\n mock_poller = MagicMock()\n ", "decoded_codepoints": 260, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/tests/test_cu_converter.py", "example_id": "000951aebb5b28f897e3bfceafa077d4f27edfb56ce34d43bebf3ae47a12918b", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 102, 617, 371, 81, 3867, 543, 26, 1777, 12915, 17443, 18811, 32, 73, 4570, 27, 610, 313, 7365, 20, 291, 1201, 617, 371, 81, 3867, 543, 26, 1777, 12915, 17443, 18811, 32, 1456, 37, 27, 610, 313, 7365, 20, 478, 203, 21, 40595, 203, 21, 4483, 346, 4395, 3312, 203, 21, 8583, 3, 1114, 1580, 280, 25864, 3660, 346, 584, 4395, 81, 1267, 280, 25864, 3660, 346, 291, 4395, 81, 1267, 32, 8078, 280, 1605, 291, 4395, 81, 3415, 1180, 280, 25864, 3660, 346, 291, 4395, 81, 3415, 1180, 32, 1267, 32, 601, 81, 853, 280, 4395, 81, 1267, 291, 11492, 1114, 1580, 32, 2409, 81, 25132, 81, 7003, 32, 601, 81, 853, 280, 4395, 81, 3415, 1180, 14676, 2], "prompt_token_count": 121, "reference_codepoints": 256, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [800, 30, 355, 202, 11884, 1943, 44, 802, 30, 355, 202, 11884, 1943, 1250, 44, 802, 30, 355, 202, 11884, 1943, 620, 44, 802, 30, 355, 202, 11884, 1943, 1078, 44, 802, 30, 355, 202, 11884, 1943, 1078, 1250, 44, 802, 30, 355, 202, 11884, 1943, 1078, 620, 44, 802, 30, 355, 202, 11884, 1943, 1078, 1078, 44, 802, 30, 355, 202, 11884, 1943, 1078, 1250, 44, 802, 30, 355, 202, 11884, 1943, 1078], "continuation_token_count": 74, "decoded": "string,\n\t\t\tMountPoint: string,\n\t\t\tMountPointSize: string,\n\t\t\tMountPointType: string,\n\t\t\tMountPointState: string,\n\t\t\tMountPointStateSize: string,\n\t\t\tMountPointStateType: string,\n\t\t\tMountPointStateState: string,\n\t\t\tMountPointStateSize: string,\n\t\t\tMountPointState", "decoded_codepoints": 260, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/disk_test.go", "example_id": "000961887eabf669afc7918fb7ced64b3f06f895deaa72b85347e6d500e293db", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 87, 44, 313, 9692, 289, 35, 96, 35, 3918, 603, 202, 835, 355, 202, 835, 357, 202, 111, 203, 202, 111, 478, 202, 102, 32, 2529, 440, 30788, 3872, 2838, 432, 6717, 31, 18290, 101, 392, 3420, 26, 102, 319, 4266, 32, 70, 27, 301, 357, 202, 4867, 1025, 549, 6143, 109, 2548, 5773, 44, 1930, 26, 1110, 77, 800, 6603, 2946, 32, 15516, 5773, 4370, 357, 202, 86, 1025, 1930, 17323, 26, 4867, 27, 1314, 202, 86, 32, 669, 10728, 9113, 15516, 26, 10300, 32, 10728, 5944, 109, 355, 202, 3033, 44, 225, 3, 30, 313, 85, 28491, 35, 31, 2388, 392, 8616, 32, 558, 27, 203, 202, 1748, 478, 202, 102, 32, 2529, 440, 5961, 101, 11815, 10874, 1531, 6717, 31, 18290, 5111, 10874, 392, 3420, 26, 102, 319, 4266, 32, 70, 27, 301, 357, 202, 4867, 1025, 549, 6143, 109, 2548, 5773, 44, 1930, 26, 1110, 77, 800, 6603, 2946, 32, 15516, 5773, 4370, 357, 202, 86, 1025, 1930, 17323, 26, 4867, 27, 1314, 202, 306, 8204, 26584, 322, 3501, 10874, 101, 688, 11092, 2], "prompt_token_count": 179, "reference_codepoints": 256, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [2264, 442, 901, 45, 291], "continuation_token_count": 5, "decoded": " return false;\n ", "decoded_codepoints": 32, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/commands/store.ts", "example_id": "000968ec723594949c75be55c0be2a12ce58d0820966f77e842060b18c25cd0b", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 283, 3909, 18119, 2780, 1371, 616, 1519, 44, 1509, 1215, 30, 616, 804, 44, 2075, 32, 314, 30, 616, 2608, 1922, 6729, 44, 2075, 32, 7134, 30, 291, 1122, 397, 320, 2368, 308, 731, 27, 301, 291, 415, 1429, 297, 4329, 6729, 23302, 924, 26, 731, 27, 1276, 2075, 32, 1260, 1276, 653, 297, 26063, 1157, 301, 334, 3, 291, 2014, 8655, 4329, 14350, 26, 731, 293, 291, 1056, 280, 2014, 3909, 18119, 2780, 1371, 616, 1519, 44, 1509, 1215, 30, 616, 804, 44, 2075, 32, 314, 30, 616, 2608, 1922, 6729, 44, 861, 30, 291, 1122, 397, 320, 1687, 660, 5797, 280, 372, 15368, 2301, 26, 1267, 293, 478, 2], "prompt_token_count": 112, "reference_codepoints": 32, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [264, 432, 322, 529, 2157, 82, 1359, 32, 203, 31, 1115, 15661, 4914, 312, 313, 8804, 16068, 15321, 645, 312, 2074, 20, 1361, 1906, 328, 334, 529, 2180, 33, 4538, 32, 954, 30052, 101, 40579, 4169], "continuation_token_count": 36, "decoded": " of the `store` config.\n- **References**: a \"Referencing stores from a project\" subsection in\n `docs/cli.md`'s Stores section", "decoded_codepoints": 129, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:openspec/work/simplify-context-and-workspace-model/slices/store-references/spec.md", "example_id": "00097129b57b29405c675521a5549b726a0650ca2487785e2909d179bf1988de", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1374, 30, 529, 20153, 82, 1688, 334, 6346, 3064, 322, 1650, 30, 461, 322, 21440, 5630, 2016, 9792, 2643, 25862, 334, 8187, 322, 6895, 5298, 32, 203, 31, 1115, 10113, 4914, 312, 313, 8804, 16068, 15321, 645, 312, 2074, 20, 1361, 1906, 328, 334, 529, 2180, 33, 4538, 32, 954, 30052, 101, 40579, 4169, 1825, 299, 322, 529, 6365, 5781, 1359, 203, 3, 2157, 5781, 4956, 436, 3051, 2274, 25195, 308, 37, 32, 36, 547, 203, 31, 5477, 10942, 5387, 8338, 328, 2968, 10625, 461, 7892, 31, 1855, 27826, 308, 37, 32, 37, 547, 203, 31, 498, 1651, 12112, 11806, 328, 35726, 308, 37, 32, 40, 27, 12011, 9400, 31, 3221, 28814, 334, 884, 458, 11494, 1182, 1755, 11806, 11213, 32, 203, 31, 6204, 1539, 372, 3051, 18776, 303, 2], "prompt_token_count": 131, "reference_codepoints": 128, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [264, 461, 313, 1490, 1643, 81, 681, 20, 328, 16807, 81, 1286, 528, 461], "continuation_token_count": 14, "decoded": " and \"nbformat_type\" in notebook_content\n and", "decoded_codepoints": 67, "document_id": "microsoft/markitdown@2e42a01c404629b06892a1bdb5e7bf5261770c40:packages/markitdown/src/markitdown/converters/_ipynb_converter.py", "example_id": "0009a073b3cca4e0785d1c2b59a9922607467ff6b18e6cdd8231964c1a895359", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 556, 313, 3310, 31, 42, 20, 528, 16807, 81, 1286, 280, 803, 81, 2238, 32, 850, 922, 5460, 26, 8644, 27, 528, 442, 308, 715, 313, 1490, 1643, 20, 328, 16807, 81, 1286, 715, 461, 313, 1490, 1643, 81, 17765, 20, 328, 16807, 81, 1286, 3486, 3, 1537, 81, 966, 27, 584, 442, 3177, 446, 665, 4483, 26, 291, 630, 30, 291, 803, 81, 2238, 44, 13312, 2338, 30, 291, 3443, 81, 1338, 44, 7537, 1120, 30, 291, 1115, 5321, 44, 6204, 30, 225, 588, 11024, 372, 3097, 372, 322, 17675, 284, 829, 967, 6211, 6519, 1394, 44, 291, 588, 8661, 461, 4483, 322, 5997, 2], "prompt_token_count": 107, "reference_codepoints": 64, "repo": "microsoft/markitdown", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [396, 5980, 32, 27192, 26, 27588, 2976, 30, 330, 3310, 42, 895, 334, 2368, 308, 87, 27, 301, 284, 660, 484, 280, 484, 32, 3227, 463, 306, 370, 37902, 78, 96, 895, 284, 660, 484, 280, 484, 32, 3227, 463, 306, 370, 37902, 78, 96, 895, 284, 660, 484, 280, 484, 32, 3227, 463, 306, 370, 37902, 78, 96, 895, 284, 660, 484, 280, 484, 32, 3227, 463, 306, 370, 37902, 78, 96, 895, 284, 660, 484, 280, 484, 32, 3227, 463, 306, 370, 37902, 78, 96, 895, 284, 660, 484], "continuation_token_count": 91, "decoded": "-> fs.readFileSync(shimDir, 'utf8');\n catch (e) {\n const e = e.replace('//', '//\\n');\n const e = e.replace('//', '//\\n');\n const e = e.replace('//', '//\\n');\n const e = e.replace('//', '//\\n');\n const e = e.replace('//', '//\\n');\n const e", "decoded_codepoints": 257, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:tests/installer/opencode.test.mjs", "example_id": "0009a3bc88780153a3ad1aca694e8115aa6beb392b208ae3941400843caf68f2", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 334, 320, 203, 1916, 203, 203, 306, 225, 3125, 225, 36, 85, 32, 26661, 33750, 32, 954, 296, 942, 1406, 33123, 1256, 1795, 3684, 461, 4794, 225, 12115, 3125, 2606, 203, 858, 463, 1676, 687, 28870, 14881, 1069, 296, 8984, 26661, 33750, 32, 954, 2163, 30, 1406, 21408, 1256, 5202, 461, 12809, 370, 1404, 532, 301, 334, 660, 816, 12579, 280, 21191, 15770, 2976, 473, 334, 660, 38917, 2976, 280, 38917, 2961, 687, 473, 334, 1596, 225, 3, 264, 660, 6713, 280, 5980, 32, 27192, 26, 22705, 20768, 30, 330, 3310, 42, 895, 284, 434, 42201, 42946, 322, 281, 453, 37076, 2163, 3733, 1256, 5202, 461, 12809, 32, 284, 660, 1256, 5419, 280, 5307, 1672, 2074, 78, 96, 78, 96, 539, 225, 36, 31, 1166, 10525, 5327, 96, 78, 96, 920, 284, 660, 1256, 14059, 280, 3228, 96, 433, 6717, 78, 96, 78, 96, 10504, 20433, 5532, 5327, 96, 920, 284, 5980, 32, 7015, 2], "prompt_token_count": 156, "reference_codepoints": 256, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [225, 660, 1628, 280, 4845, 32, 6099, 26, 34, 30, 19733, 293, 284, 660, 1628, 280, 4845, 32, 6099, 26, 8378, 474, 225, 35, 293, 284, 415, 308, 928, 32, 5464, 1157, 544, 1811, 26, 928, 293, 334, 320, 334, 660, 1628, 280, 4845, 32, 6099], "continuation_token_count": 46, "decoded": " const line = buf.slice(0, nl);\n const line = buf.slice(nl + 1);\n if (line.trim()) onLine(line);\n }\n const line = buf.slice", "decoded_codepoints": 132, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:src/mcp-servers/caveman-shrink/index.js", "example_id": "0009bbbab213965b3a121e240c73871d8aaa7a0dea1e7aa2adc2f36ca27ac0b2", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 53, 43923, 299, 2288, 1230, 716, 44, 5218, 884, 18604, 810, 537, 4446, 308, 1382, 203, 306, 488, 2955, 1230, 716, 11337, 5251, 498, 2231, 31, 6228, 1795, 1273, 4630, 13602, 9533, 1591, 3398, 203, 306, 1300, 1292, 1628, 547, 2688, 1628, 31, 2668, 328, 4335, 29038, 461, 3185, 23885, 311, 5401, 1247, 32, 203, 1126, 1930, 1811, 2013, 26, 267, 1811, 27, 301, 203, 3, 397, 660, 1628, 280, 4845, 32, 6099, 26, 34, 30, 19733, 293, 397, 4845, 280, 4845, 32, 6099, 26, 8378, 474, 225, 35, 293, 397, 415, 308, 928, 32, 5464, 1157, 544, 1811, 26, 928, 293, 284, 320, 334, 1472, 203, 111, 203, 203, 1126, 4522, 1397, 26, 2076, 27, 301, 334, 434, 46630, 3048, 3829, 544, 1149, 31, 1621, 14812, 32, 12253, 810, 1411, 334, 434, 6024, 12011, 996, 2800, 1330, 5182, 2], "prompt_token_count": 141, "reference_codepoints": 128, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [78, 96, 31, 428, 1481, 225, 36, 32, 38, 343, 78, 96, 31, 428, 1481, 225, 36, 32, 39, 484, 78, 96, 31, 428, 1481], "continuation_token_count": 25, "decoded": "\\n- [ ] 2.4 d\\n- [ ] 2.5 e\\n- [ ]", "decoded_codepoints": 33, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:test/utils/task-progress.test.ts", "example_id": "0009c7e44b1d52a594e290bbcc22d9b883f7288cc32ef9429366eab52914a6d6", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 101, 10160, 11815, 8253, 32, 954, 2276, 14995, 810, 322, 12460, 370, 2498, 1404, 532, 301, 284, 2014, 2866, 34550, 3694, 473, 284, 2014, 2866, 1791, 463, 13285, 2342, 370, 301, 397, 330, 7878, 33, 8246, 32, 954, 950, 6470, 428, 106, 79, 225, 35, 32, 35, 312, 78, 96, 31, 428, 106, 79, 225, 35, 32, 36, 323, 78, 96, 370, 397, 330, 12711, 33, 8246, 32, 954, 950, 6470, 428, 106, 79, 225, 36, 32, 35, 312, 78, 96, 31, 428, 1481, 225, 36, 32, 36, 323, 78, 96, 31, 428, 1481, 225, 36, 32, 37, 281, 78, 3, 47, 2014, 622, 2247, 5280, 1562, 1791, 26, 12764, 2976, 30, 330, 13285, 2342, 370, 2074, 4058, 293, 284, 1424, 26, 6654, 547, 7285, 1371, 3380, 44, 225, 39, 30, 9435, 44, 225, 37, 1122, 334, 1122, 719, 561, 463, 49115, 322, 2432, 739, 432, 2276, 2287, 30290, 308, 15592, 31, 289, 32818, 43264, 7243, 2498, 1404, 532, 301, 284, 2014, 2866, 34550, 2], "prompt_token_count": 166, "reference_codepoints": 32, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [81, 23968, 81, 13232, 26, 1637, 81, 605, 32, 371, 463], "continuation_token_count": 11, "decoded": "_instagram_prompt(page_data.get('", "decoded_codepoints": 33, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:examples/apps/ad-use/ad_generator.py", "example_id": "0009d784c8fbba6ba0bcd777f0156d33f6bc0b5eec98dbd674c27f2dd3859694", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 300, 81, 605, 1365, 19765, 81, 983, 1446, 15837, 478, 203, 4396, 665, 4450, 81, 6270, 81, 339, 26, 1637, 81, 605, 44, 5436, 30, 2926, 44, 596, 30, 1544, 81, 314, 44, 629, 711, 203, 202, 2993, 10505, 312, 3982, 1544, 1471, 1406, 31, 25519, 14018, 1938, 706, 2993, 203, 202, 7101, 280, 3586, 4815, 26, 2816, 47, 2816, 27, 478, 202, 1270, 44, 357, 202, 325, 2926, 610, 330, 23968, 950, 355, 202, 13232, 280, 9750, 32, 1297, 3, 27, 355, 202, 339, 81, 1286, 280, 2014, 9750, 32, 5536, 81, 339, 81, 893, 26, 13232, 30, 1938, 81, 605, 32, 371, 463, 19765, 81, 983, 2847, 355, 202, 325, 1544, 81, 1286, 438, 1665, 44, 603, 202, 13225, 26405, 26, 88, 25, 1768, 1778, 11745, 3803, 436, 1544, 8578, 339, 81, 314, 15837, 357, 202, 1824, 44, 225, 588, 273, 1546, 13586, 355, 202, 5000, 81, 12521, 280, 2014, 9750, 32, 1297, 81, 5000, 81, 2], "prompt_token_count": 160, "reference_codepoints": 32, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [82, 3359, 24827, 26, 17659, 44, 12536, 103, 42, 45, 225, 35, 36, 1130, 82, 523, 489, 8232, 883, 526, 44865, 308, 24564, 27, 523, 529, 3359, 24827, 26, 17659, 44, 489, 8232, 7601, 308, 1500, 27, 523, 203, 110, 225, 529, 3359, 5543, 26, 2649, 44, 549, 466, 7601, 623, 17163, 523, 20775, 966, 45889, 1244, 523, 225, 529, 3359, 5543, 26, 2649, 44, 596, 7601, 523, 203, 110, 225, 529, 3359, 5543, 26, 2649, 44, 549, 466, 7601, 623, 17163, 523, 20775, 966, 45889, 1244], "continuation_token_count": 87, "decoded": "`fn decrypt(nonce: &[u8; 12])` | Nonce can be reused (borrow) | `fn decrypt(nonce: Nonce)` (move) |\n| `fn route(level: &str)` with fallback | Typos silently default | `fn route(level: str)` |\n| `fn route(level: &str)` with fallback | Typos silently default", "decoded_codepoints": 259, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:type-driven-correctness-book/src/ch13-reference-card.md", "example_id": "0009dc077726b5c170741c0f84d7c8a78d481b7d364ed009d265a7897a76a133", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 203, 110, 39351, 3129, 10754, 608, 10754, 203, 110, 529, 3359, 1491, 81, 12601, 346, 967, 296, 40, 38, 82, 523, 1683, 778, 422, 12011, 3065, 526, 6629, 127, 53, 30, 6629, 127, 56, 30, 556, 48483, 523, 529, 3359, 1491, 81, 12601, 346, 967, 390, 9859, 3263, 82, 523, 203, 110, 529, 3359, 18884, 26, 17659, 44, 12536, 103, 42, 45, 225, 35, 36, 1130, 82, 523, 489, 8232, 883, 526, 44865, 308, 24564, 27, 523, 529, 3359, 18884, 26, 17659, 44, 489, 8232, 7601, 308, 1500, 27, 523, 203, 110, 225, 3, 7601, 523, 203, 110, 529, 11532, 82, 544, 11227, 34409, 5036, 523, 1513, 32069, 3982, 31, 539, 28764, 523, 12029, 1330, 30310, 14429, 523, 203, 110, 529, 730, 16403, 81, 314, 44, 1044, 35, 40, 280, 225, 34, 24988, 82, 523, 44345, 40435, 22678, 523, 529, 730, 16403, 81, 314, 44, 3659, 46, 103, 35, 40, 48, 280, 1665, 82, 523, 203, 110, 529, 3359, 5543, 26, 2649, 44, 549, 466, 7601, 623, 17163, 523, 20775, 966, 45889, 1244, 523, 225, 2], "prompt_token_count": 177, "reference_codepoints": 256, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [351, 2350, 81, 2024, 81, 4254, 32, 302, 81, 466], "continuation_token_count": 10, "decoded": " group_output_prefix.as_str", "decoded_codepoints": 34, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/run/run.rs", "example_id": "0009dcef4898093ac4a68d706969f8be8f1ff567412816a01446d9bc05f302ca", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 45, 291, 1207, 9355, 81, 4254, 280, 415, 2519, 81, 1363, 81, 1707, 301, 324, 2350, 81, 2024, 81, 4254, 32, 302, 81, 466, 346, 291, 320, 813, 301, 324, 11962, 81, 4254, 291, 1472, 291, 1207, 2350, 81, 12637, 280, 2179, 9170, 109, 7133, 81, 4254, 111, 28734, 313, 225, 5283, 2296, 3534, 1967, 1035, 584, 415, 2519, 81, 1363, 81, 1707, 301, 1802, 3, 2264, 313, 3839, 4528, 8844, 810, 2412, 21042, 392, 400, 11962, 81, 4254, 30, 400, 4489, 1533, 403, 5288, 30, 324, 829, 12370, 291, 320, 584, 436, 308, 91, 30, 1056, 27, 328, 2350, 81, 4295, 32, 1731, 922, 23053, 346, 301, 324, 1207, 5202, 280, 415, 2519, 81, 1363, 81, 1707, 301, 1568, 2], "prompt_token_count": 122, "reference_codepoints": 32, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [326, 1103, 326, 529, 1297, 1791, 6620, 667], "continuation_token_count": 8, "decoded": "**Add** `createChange()` function", "decoded_codepoints": 33, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:openspec/changes/archive/2025-12-25-add-change-manager/design.md", "example_id": "0009dd80f05f73b415da80b1bd109f70c7449866e0a8259a9b1d42164b75f2d2", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 285, 32, 203, 203, 433, 7645, 3528, 517, 12495, 31, 6098, 3528, 203, 203, 1482, 7645, 3528, 203, 31, 1115, 1103, 326, 529, 1297, 1791, 6620, 667, 372, 1487, 1539, 14904, 203, 31, 1115, 1103, 326, 529, 4635, 1791, 558, 6620, 667, 436, 3947, 20018, 31, 1732, 6850, 203, 31, 1115, 6601, 326, 32223, 308, 2165, 83, 795, 6350, 30, 10105, 27, 372, 1487, 3404, 203, 203, 1482, 12495, 31, 6098, 3528, 203, 31, 3, 26, 31181, 1389, 8394, 27, 203, 31, 2648, 35524, 11583, 556, 7884, 6015, 203, 31, 5614, 2624, 529, 720, 2019, 82, 556, 529, 1791, 2019, 82, 1389, 203, 203, 433, 9125, 14684, 203, 203, 1482, 35732, 225, 35, 44, 7155, 23193, 14749, 203, 203, 326, 13860, 4914, 2222, 4442, 372, 529, 1617, 33, 2304, 33, 2342, 31, 2304, 32, 1421, 82, 429, 1289, 443, 32, 203, 203, 914, 11979, 203, 2], "prompt_token_count": 147, "reference_codepoints": 32, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [647, 323, 81, 875, 101, 1101, 312, 81, 875, 101, 36, 44, 1207, 312, 280, 323, 308, 13527, 27, 291, 312, 81, 875, 101, 36, 1101, 323], "continuation_token_count": 27, "decoded": " b_owns --> a_owns2: let a = b (MOVE)\n a_owns2 --> b", "decoded_codepoints": 64, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:python-book/src/ch07-ownership-and-borrowing.md", "example_id": "0009e5fd18311f537883a5dfa848e875fd545299eb4d939e79a33663dd0159cd", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 262, 323, 81, 2585, 1101, 27572, 44, 3555, 323, 308, 612, 998, 225, 35, 40885, 34, 27, 291, 5997, 2091, 432, 7176, 44, 23730, 312, 461, 323, 2260, 46, 839, 2039, 452, 322, 358, 3848, 1300, 284, 320, 284, 1603, 313, 41109, 308, 39585, 11530, 4731, 619, 28804, 301, 291, 33836, 79, 1101, 312, 81, 875, 101, 36, 44, 1207, 312, 280, 4712, 2513, 35, 30, 36, 30, 37, 79, 291, 312, 81, 875, 101, 36, 1101, 323, 81, 875, 101, 44, 1207, 323, 280, 312, 308, 13527, 27, 664, 3, 1028, 323, 81, 875, 101, 44, 312, 438, 22855, 2685, 5169, 46, 839, 2039, 13788, 1048, 415, 1654, 284, 320, 203, 914, 203, 203, 8133, 203, 203, 433, 11530, 12971, 16803, 8480, 9494, 9618, 299, 203, 203, 1482, 2389, 8480, 11530, 203, 914, 7421, 203, 306, 7155, 3738, 308, 4032, 7983, 30, 36465, 30, 1560, 101, 30, 16656, 27, 884, 3366, 1164, 1345, 30, 646, 13639, 203, 730, 816, 280, 225, 38, 36, 45, 203, 730, 533, 280, 816, 45, 264, 434, 816, 438, 3366, 1164, 1345, 273, 2], "prompt_token_count": 181, "reference_codepoints": 64, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [26, 426, 293, 203, 111, 203, 203, 1332, 886, 21982, 20066], "continuation_token_count": 11, "decoded": "(name);\n}\n\n/** The canonical requirement", "decoded_codepoints": 40, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/parsers/requirement-blocks.ts", "example_id": "0009eed875965693c50af44932e0c7316c407f008424f47bb0cd03a09aa6b7d0", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1382, 203, 319, 559, 14450, 54, 29, 613, 45038, 8184, 31, 1906, 11730, 429, 2154, 3134, 15037, 2052, 688, 3178, 203, 319, 1755, 328, 1135, 556, 46084, 19782, 5651, 312, 32429, 30, 7152, 3134, 10130, 32, 203, 569, 203, 1358, 667, 11426, 18079, 558, 26, 426, 44, 802, 711, 802, 301, 334, 442, 13316, 18079, 558, 3, 20737, 89, 30, 330, 17858, 203, 111, 203, 203, 1332, 886, 21982, 20066, 3338, 322, 7715, 6187, 37768, 5052, 32, 569, 203, 913, 15715, 3480, 81, 10870, 81, 29396, 280, 17602, 1482, 78, 101, 28, 18079, 3491, 101, 8088, 33581, 5421, 101, 28, 12639, 91, 45, 203, 203, 1332, 203, 319, 15218, 101, 322, 23496, 4169, 645, 312, 1374, 803, 461, 35228, 20066, 9058, 32, 203, 569, 203, 1358, 3420, 2], "prompt_token_count": 129, "reference_codepoints": 32, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [101, 280, 301, 334, 313, 1877, 563, 301, 284, 313, 2184, 563, 301, 397, 313, 3732, 563, 301, 291, 313, 2184, 563, 301, 616, 313, 3732, 563, 301, 324, 313, 2184, 563, 301, 1090], "continuation_token_count": 34, "decoded": "s = {\n \"update\": {\n \"options\": {\n \"tool\": {\n \"options\": {\n \"tool\": {\n \"options\": {\n ", "decoded_codepoints": 132, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/update.ts", "example_id": "0009f35079853afc59dd6415bd9415cdc4d704eac4edaee78124900c45f1449b", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 225, 16381, 30096, 7923, 44, 802, 10863, 334, 10153, 25936, 44, 14584, 46, 3157, 46, 800, 30, 4283, 308, 5139, 11865, 81, 8703, 40881, 3951, 5594, 2171, 18311, 29380, 334, 18329, 4455, 20253, 2805, 34165, 16056, 1394, 45, 203, 1255, 203, 203, 1332, 203, 319, 11024, 436, 322, 1974, 2016, 32, 203, 569, 203, 1358, 2568, 4000, 2019, 2031, 3, 363, 12852, 6350, 27, 10160, 1169, 9577, 8684, 32, 203, 319, 3759, 322, 15234, 432, 14098, 10153, 15342, 688, 2530, 11865, 81, 8703, 40881, 3951, 32, 203, 319, 203, 319, 21746, 6835, 322, 7176, 12742, 2297, 1182, 8971, 23329, 11199, 101, 688, 19201, 4559, 15342, 32, 203, 569, 203, 1358, 667, 8971, 23329, 73, 271, 2], "prompt_token_count": 117, "reference_codepoints": 128, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [3317, 372, 3523, 203, 202, 2848, 1114, 2087, 98, 81, 1580, 81, 2388, 32, 3317, 280, 617, 4329], "continuation_token_count": 18, "decoded": "register to session\n\tsession._cdp_client_root.register = _Register", "decoded_codepoints": 66, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/browser/test_proxy.py", "example_id": "0009f3ef00e6b9b172f1a46841994b323273581c8d02a4b7b53e0348a6031a3a", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 4766, 66, 683, 967, 1665, 44, 577, 202, 784, 32, 8675, 280, 617, 8675, 4329, 26, 11925, 27, 2540, 202, 784, 32, 2714, 280, 617, 4863, 26, 784, 27, 355, 202, 784, 32, 3317, 280, 617, 4329, 26, 784, 27, 478, 202, 2388, 280, 32522, 4766, 66, 346, 478, 202, 21, 29933, 11680, 101, 372, 3523, 203, 202, 2848, 1114, 2087, 98, 81, 1580, 81, 2388, 280, 3051, 225, 588, 827, 44, 5079, 77, 2437, 31, 2187, 79, 203, 202, 21, 3139, 1849, 372, 12386, 312, 4011, 225, 3, 3317, 15574, 4899, 461, 5352, 3796, 9933, 2876, 49039, 203, 202, 6240, 3523, 1114, 5522, 81, 5866, 81, 2393, 346, 478, 202, 862, 3051, 32, 6565, 438, 2933, 203, 202, 862, 20695, 26, 2388, 32, 2393, 81, 4383, 27, 478, 202, 21, 9296, 6197, 7664, 3796, 2129, 1692, 203, 202, 5092, 280, 5053, 34584, 950, 330, 100, 35, 370, 330, 2393, 22911, 950, 5053, 1855, 2], "prompt_token_count": 156, "reference_codepoints": 64, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [614, 324, 549, 24171, 73, 30, 324, 549, 24171, 58, 30, 324, 549, 24171, 73, 30, 324, 549, 24171, 58, 30, 324, 549, 24171, 73, 30, 324, 549, 24171, 58, 30], "continuation_token_count": 31, "decoded": "],\n &atlasW,\n &atlasH,\n &atlasW,\n &atlasH,\n &atlasW,\n &atlasH,", "decoded_codepoints": 128, "document_id": "nicbarker/clay@e6cc36941ab2af5d81107617039d6f527a1c660b:examples/GLES3-SDL2-video-demo/main.c", "example_id": "0009f8b74c9af25e14ca575d37da1d563bf39d4638e3f05a81cfb8c78ce4f85f", "language": "c", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 81, 270, 84, 32778, 293, 284, 570, 1882, 37, 81, 885, 3121, 1031, 2447, 1652, 89, 81, 31720, 37, 30, 1258, 84, 81, 3121, 1031, 30, 549, 89, 81, 270, 84, 32778, 293, 446, 570, 1882, 37, 81, 9962, 1652, 89, 81, 31720, 37, 30, 225, 38, 34, 43, 40, 293, 446, 629, 34962, 73, 280, 225, 35, 34, 36, 38, 45, 284, 629, 34962, 58, 280, 225, 35, 34, 36, 38, 45, 284, 415, 1429, 501, 84, 81, 3013, 3713, 26, 324, 549, 89, 81, 31720, 37, 32, 2186, 24333, 77, 34, 614, 324, 549, 89, 81, 270, 84, 32778, 77, 34, 3, 351, 13313, 473, 446, 390, 991, 81, 885, 3529, 2101, 3990, 26, 1508, 293, 203, 111, 203, 203, 1117, 5258, 346, 203, 109, 446, 3962, 6790, 1514, 26, 34, 32, 35, 88, 30, 225, 34, 32, 36, 88, 30, 225, 34, 32, 35, 88, 30, 225, 35, 32, 34, 88, 293, 446, 390, 991, 81, 2863, 36, 7499, 9189, 280, 5330, 284, 12675, 81, 1151, 1692, 45, 284, 2218, 308, 12352, 81, 20041, 1151, 1652, 1567, 490, 284, 301, 291, 3578, 308, 1567, 32, 681, 27, 291, 301, 291, 2], "prompt_token_count": 195, "reference_codepoints": 128, "repo": "nicbarker/clay", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [32, 203, 306, 203, 306, 1348, 894, 9371, 688, 322, 11607, 101, 14942, 623, 2504, 1604, 30, 461, 688, 203, 306, 322, 11607, 101, 884, 646, 3502, 32, 203, 306, 203, 306, 1348, 894, 9371, 688, 322, 11607, 101, 884, 646, 3502, 32, 203, 306, 203, 306, 1348, 894, 9371, 688, 322, 11607, 101, 884, 646, 3502, 32, 203, 306, 203, 306, 1348, 894, 9371, 688, 322, 11607], "continuation_token_count": 68, "decoded": ".\n//\n// This test checks that the manifests agree with each other, and that\n// the manifests are not empty.\n//\n// This test checks that the manifests are not empty.\n//\n// This test checks that the manifests are not empty.\n//\n// This test checks that the manifest", "decoded_codepoints": 262, "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:scripts/check-versions.js", "example_id": "000a0016e6580f8ac882e706e36106b2f406fef010763ccdccaf1bcbaa4c084e", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 661, 3408, 30487, 17579, 30, 461, 3638, 3621, 17413, 101, 1169, 432, 3026, 810, 4091, 32, 203, 306, 203, 306, 3312, 33, 300, 15920, 31, 6728, 32, 858, 32, 754, 3425, 9371, 322, 12074, 3973, 11607, 101, 14942, 203, 306, 623, 2504, 1604, 30, 1273, 688, 883, 1330, 2368, 322, 7829, 2926, 688, 787, 9974, 328, 354, 38, 32, 42, 32, 34, 44, 203, 306, 3638, 11607, 20005, 318, 3, 461, 203, 306, 264, 36, 32, 544, 312, 3621, 31, 2142, 9683, 1420, 30, 688, 7176, 1503, 2298, 5040, 322, 2604, 32, 203, 203, 913, 5980, 280, 1205, 463, 2548, 895, 203, 913, 1519, 280, 1205, 463, 983, 895, 203, 203, 913, 3051, 280, 1519, 32, 2524, 4064, 7781, 30, 31001, 895, 203, 913, 16830, 64, 1345, 81, 48976, 1971, 280, 517, 14747, 86, 19650, 5327, 86, 19650, 5327, 86, 29, 12639, 45, 203, 203, 306, 17640, 803, 688, 4497, 10999, 322, 534, 2709, 2], "prompt_token_count": 156, "reference_codepoints": 256, "repo": "DietrichGebert/ponytail", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [9663, 8224, 29594, 291, 1201, 538, 32, 8933, 440, 641, 555, 2763, 32, 508, 33, 8224, 33], "continuation_token_count": 17, "decoded": "\"/posts/\")\n assert ex.matches(\"https://example.com/posts/", "decoded_codepoints": 64, "document_id": "D4Vinci/Scrapling@07a548362ff904a2837f503ed9d9f6b9dcef0195:tests/spiders/test_links.py", "example_id": "000a2485747f318bc9769144b9f865327770b71a735225b0a4c49f5bab8b3e4f", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 105, 26, 784, 711, 291, 538, 280, 6116, 16653, 26, 4568, 47, 100, 9663, 8224, 29594, 291, 1201, 538, 32, 8933, 440, 641, 555, 2763, 32, 508, 33, 8224, 33, 35, 657, 438, 2933, 291, 1201, 538, 32, 8933, 440, 641, 555, 2763, 32, 508, 33, 7468, 657, 438, 3177, 446, 665, 894, 81, 8933, 81, 26362, 1734, 81, 34282, 26, 784, 711, 291, 538, 280, 6116, 16653, 26, 34282, 47, 3, 106, 657, 438, 3177, 291, 1201, 538, 32, 8933, 440, 641, 555, 2763, 32, 508, 33, 8224, 33, 35, 657, 438, 2933, 446, 665, 894, 81, 8933, 81, 26362, 1734, 81, 4568, 81, 20798, 26, 784, 711, 291, 538, 280, 6116, 16653, 26, 4568, 81, 20798, 347, 2763, 32, 508, 657, 291, 1201, 538, 32, 8933, 440, 641, 555, 1237, 32, 2763, 32, 508, 33, 106, 657, 438, 2933, 291, 312, 2], "prompt_token_count": 145, "reference_codepoints": 64, "repo": "D4Vinci/Scrapling", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [958, 313, 371, 3457, 392, 324, 537, 32246, 620, 1178, 301, 1090, 32246, 60, 17548, 4852, 32, 1028, 26, 890, 6666, 26, 34, 30, 6666, 6767, 32, 979, 779, 440, 29521, 33, 30236], "continuation_token_count": 33, "decoded": " \"getOffset\",\n new SelType[] {\n SelJodaDateTime.of(new DateTime(0, DateTimeZone.forID(\"America/Los", "decoded_codepoints": 128, "document_id": "Netflix/maestro@abdbdadf8f075b8fa488c9efb386b468c709a63c:netflix-sel/src/test/java/com/netflix/sel/type/SelJodaDateTimeZoneTest.java", "example_id": "000a2e878d4c3f6d4c03587888584033de254308dffdc218159db70f9638e8e9", "language": "java", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1069, 26, 15481, 3397, 32, 5363, 81, 25620, 30, 32246, 652, 32, 1028, 440, 3986, 2974, 334, 320, 719, 477, 1006, 334, 562, 763, 894, 17838, 346, 301, 284, 32246, 620, 736, 280, 1591, 32, 1851, 440, 979, 779, 392, 537, 32246, 620, 1178, 301, 15481, 652, 32, 1028, 440, 15689, 657, 1916, 284, 3788, 440, 31141, 81, 27368, 44, 17197, 392, 736, 32, 681, 346, 474, 10685, 313, 474, 736, 293, 284, 736, 280, 291, 1591, 32, 1851, 26, 397, 3, 81, 1045, 300, 1882, 14036, 324, 1122, 284, 3788, 440, 10129, 44, 225, 34, 392, 736, 32, 681, 346, 474, 10685, 313, 474, 736, 293, 284, 736, 280, 291, 4674, 32, 1851, 26, 324, 313, 371, 3457, 392, 324, 537, 32246, 620, 1178, 301, 1090, 32246, 60, 17548, 4852, 32, 1028, 26, 890, 6666, 26, 34, 30, 6666, 6767, 32, 979, 779, 440, 29521, 33, 30236, 81, 1045, 300, 1882, 2], "prompt_token_count": 154, "reference_codepoints": 128, "repo": "Netflix/maestro", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [27, 920, 616, 320, 291, 320, 291, 415, 308, 626, 1720, 330, 1719, 683, 2926, 280, 330, 1719], "continuation_token_count": 18, "decoded": ")';\n }\n }\n if (arg === 'off') mode = 'off", "decoded_codepoints": 64, "document_id": "DietrichGebert/ponytail@16f29800fd2681bdf24f3eb4ccffe38be3baec6b:hooks/ponytail-mode-tracker.js", "example_id": "000a3807b437f7ba39c64df5206c46c97992ca93afb39849abab837095aff242", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1720, 330, 1536, 683, 301, 616, 660, 343, 2816, 280, 8710, 77, 36, 970, 616, 415, 308, 86, 2816, 1720, 330, 1719, 25, 1276, 343, 2816, 1720, 330, 16432, 25, 1276, 343, 2816, 1720, 330, 2620, 25, 1276, 343, 2816, 1720, 330, 338, 2692, 683, 301, 324, 2866, 2044, 2101, 26, 86, 2816, 293, 324, 2866, 9824, 2301, 463, 1240, 18249, 7464, 370, 343, 2816, 30, 330, 66, 13148, 19406, 4040, 225, 3, 264, 442, 45, 434, 2800, 1330, 16843, 3919, 372, 322, 3523, 31, 2816, 3578, 291, 320, 291, 415, 308, 626, 1720, 330, 16432, 683, 2926, 280, 330, 16432, 920, 291, 813, 415, 308, 626, 1720, 330, 2620, 683, 2926, 280, 330, 2620, 920, 291, 813, 415, 308, 626, 1720, 330, 338, 2692, 683, 2926, 280, 330, 338, 2692, 920, 291, 813, 415, 308, 626, 1720, 330, 1719, 683, 2926, 280, 330, 1719, 25, 2], "prompt_token_count": 148, "reference_codepoints": 64, "repo": "DietrichGebert/ponytail", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [2501, 44, 2016, 30, 664, 2181, 44, 2181, 30], "continuation_token_count": 9, "decoded": "command: command,\n args: args,", "decoded_codepoints": 32, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/upgrade-command.test.ts", "example_id": "000a52f9c7f820964d01af7cac3510bc128fd99efe4fd23eacce222cd82e5383", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 64, 2123, 81, 21589, 30, 10779, 203, 111, 203, 203, 4396, 667, 1420, 2019, 14705, 1132, 44, 802, 28237, 4664, 46, 1117, 48, 301, 334, 660, 3460, 280, 537, 5718, 473, 334, 3460, 32, 4775, 1788, 473, 334, 3909, 15492, 2019, 26, 5784, 293, 334, 2014, 3460, 32, 2208, 2981, 14141, 1251, 392, 313, 858, 392, 2417, 1132, 1989, 203, 111, 203, 203, 5553, 3863, 4114, 532, 301, 664, 3, 47, 4312, 334, 1395, 4311, 2333, 6253, 32, 3613, 17923, 882, 26, 1508, 293, 334, 1395, 11393, 2333, 26003, 32, 3613, 18302, 26, 1870, 293, 334, 8943, 32, 47901, 26, 4466, 30, 313, 751, 1895, 3613, 14634, 1162, 1179, 1132, 44, 8665, 9795, 532, 301, 284, 1245, 2301, 32, 2018, 26, 1132, 32, 2524, 440, 41320, 334, 1122, 334, 16611, 32, 3613, 18302, 1371, 284, 2], "prompt_token_count": 137, "reference_codepoints": 32, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [2965, 392, 355, 202, 1131, 44, 264, 313, 36, 34, 34, 35, 44, 34, 1199, 42, 44, 34, 34, 34, 34, 44, 34, 34, 34, 34, 44, 34, 34, 34, 34, 44, 34, 34, 34, 34, 44, 34, 34, 34, 35, 392, 355], "continuation_token_count": 43, "decoded": " address\",\n\t\t\tinput: \"2001:0db8:0000:0000:0000:0000:0001\",\n\t\t", "decoded_codepoints": 64, "document_id": "TecharoHQ/anubis@34badc646c39af3d9f1f70757474b141316f23ad:internal/clampip_test.go", "example_id": "000a566e597cb0366b5024fbdc9646a0c80c3b063c9803deaf9fb83788fa3b0c", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 30, 357, 202, 109, 355, 202, 426, 44, 262, 313, 21710, 38, 2552, 31, 1696, 392, 355, 202, 1131, 44, 264, 313, 35, 40, 43, 32, 36, 39, 38, 32, 34, 32, 35, 392, 355, 202, 3140, 44, 313, 35, 40, 43, 32, 36, 39, 38, 32, 34, 32, 34, 33, 36, 38, 392, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 262, 313, 21710, 38, 562, 2965, 392, 355, 202, 1131, 44, 264, 313, 36, 34, 37, 32, 34, 32, 35, 35, 37, 32, 35, 392, 355, 202, 3140, 44, 313, 36, 34, 37, 32, 34, 32, 35, 35, 37, 32, 34, 33, 36, 38, 392, 357, 202, 835, 1314, 202, 306, 17409, 40, 11019, 357, 202, 109, 355, 202, 426, 44, 262, 313, 21710, 40, 4302, 3, 38, 42, 392, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 262, 313, 21710, 40, 623, 3536, 27213, 392, 355, 202, 1131, 44, 264, 313, 36, 34, 34, 35, 44, 34, 1199, 42, 44, 34, 34, 34, 34, 44, 34, 34, 34, 34, 44, 34, 34, 34, 34, 44, 34, 34, 34, 34, 44, 34, 34, 34, 34, 44, 34, 34, 34, 35, 392, 355, 202, 3140, 44, 313, 36, 34, 34, 35, 44, 1199, 42, 403, 33, 38, 42, 392, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 262, 313, 21710, 40, 5258, 975, 392, 355, 202, 1131, 44, 264, 32882, 35, 392, 355, 202, 3140, 44, 32882, 33, 38, 42, 392, 357, 202, 835, 357, 202, 109, 355, 202, 426, 44, 262, 313, 21710, 40, 707, 2285, 2], "prompt_token_count": 266, "reference_codepoints": 64, "repo": "TecharoHQ/anubis", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [87], "continuation_token_count": 1, "decoded": "e", "decoded_codepoints": 1, "document_id": "DataWithBaraa/sql-data-warehouse-project@92406686380cde6eca208c8b43e6fa40ecd26344:scripts/gold/ddl_gold.sql", "example_id": "000a593cae413919cac48c7afc0b7faf8274e47b0165cffdde9dfbff2b7586f4", "language": "sql", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 2533, 379, 203, 2952, 19350, 81, 779, 463, 16782, 32, 3534, 81, 8416, 370, 330, 72, 683, 2756, 2370, 1181, 284, 31636, 32757, 21486, 32, 3534, 81, 8416, 45, 203, 6990, 203, 203, 6037, 32757, 21486, 32, 3534, 81, 8416, 2469, 203, 4620, 284, 31879, 81, 10463, 346, 27879, 308, 9349, 6936, 20264, 32, 777, 86, 81, 1366, 81, 2632, 30, 20264, 32, 777, 86, 81, 678, 27, 2469, 4054, 81, 678, 30, 769, 18379, 32062, 1202, 3, 314, 30, 284, 20264, 32, 777, 86, 81, 678, 647, 2469, 4054, 81, 2171, 30, 284, 20264, 32, 777, 86, 81, 14276, 958, 2469, 4054, 81, 426, 30, 284, 20264, 32, 2579, 81, 314, 958, 2469, 6215, 81, 314, 30, 284, 11487, 32, 2579, 2033, 2469, 6215, 30, 284, 11487, 32, 1113, 2579, 958, 2469, 1361, 3153, 30, 284, 11487, 32, 31277, 225, 2469, 24514, 30, 284, 20264, 32, 777, 86, 81, 8030, 262, 2469, 7847, 30, 284, 20264, 2], "prompt_token_count": 159, "reference_codepoints": 32, "repo": "DataWithBaraa/sql-data-warehouse-project", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [264, 429, 42132, 410, 82, 12011, 33187, 318, 30, 42700, 4121, 308, 6228, 390, 1182, 529, 913, 629], "continuation_token_count": 18, "decoded": " - `&int` — borrowed, lightweight reference (like C's `const int", "decoded_codepoints": 67, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:c-cpp-book/src/ch05-data-structures.md", "example_id": "000a6309ecd24acba192654a71454e4d424d3ef27e4830afd52d95818090b586", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 30, 15121, 31, 21511, 30, 15230, 444, 308, 6228, 390, 1182, 529, 13770, 30052, 86, 3112, 30, 556, 390, 1046, 25, 101, 529, 1530, 403, 800, 4529, 284, 429, 42132, 466, 82, 12011, 33187, 318, 30, 42700, 4121, 308, 6228, 390, 1182, 529, 913, 1351, 40784, 623, 3104, 30, 556, 390, 1046, 25, 101, 529, 1530, 403, 800, 81, 1071, 82, 12011, 1273, 42132, 466, 82, 438, 1115, 30179, 31, 7149, 326, 1259, 561, 883, 7152, 343, 3695, 27, 284, 3, 1322, 461, 884, 28809, 2080, 9354, 31, 42, 203, 203, 48, 1115, 1562, 390, 1046, 15462, 4777, 529, 652, 82, 21426, 235, 529, 1530, 403, 800, 1801, 42132, 466, 82, 21426, 235, 529, 1530, 403, 800, 81, 1071, 2541, 1683, 6228, 529, 1530, 403, 800, 81, 1071, 1801, 312, 42132, 466, 82, 438, 28809, 2080, 436, 2819, 9449, 26592, 810, 322, 33187, 26664, 32, 203, 203, 433, 892, 8480, 549, 466, 44, 29912, 318, 8480, 48832, 100, 2], "prompt_token_count": 160, "reference_codepoints": 64, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [351, 313, 1240, 3099, 563, 301, 616], "continuation_token_count": 7, "decoded": " \"User info\": {\n ", "decoded_codepoints": 32, "document_id": "upstash/context7@b250c2515694eee4b6df4db82fa056df9ed3e306:packages/cli/src/__tests__/auth-commands.test.ts", "example_id": "000a656b6048a1c4c3c46d91c3d6e08bc40493db109eaf483f78d49fccb5f67d", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 97, 1467, 26, 1508, 293, 334, 1122, 719, 894, 440, 88, 27277, 461, 20179, 1256, 3099, 1412, 12946, 328, 392, 2498, 1404, 532, 301, 284, 4395, 936, 2303, 16439, 32, 3613, 17923, 882, 440, 1327, 31, 1956, 724, 284, 8943, 32, 10520, 4455, 26, 397, 313, 5140, 392, 397, 8943, 32, 3359, 922, 3613, 17923, 882, 1371, 291, 3835, 44, 861, 30, 291, 2361, 44, 1404, 532, 203, 3, 351, 3117, 44, 861, 30, 324, 636, 44, 313, 1006, 2680, 392, 324, 4096, 44, 313, 858, 50, 2763, 32, 508, 392, 324, 6498, 1166, 44, 744, 30, 616, 7305, 397, 1790, 284, 1093, 446, 2014, 1420, 2019, 440, 19483, 12401, 724, 284, 1424, 26, 751, 2301, 32, 6060, 1162, 94, 27, 532, 456, 32, 6411, 440, 18463, 328, 2131, 547, 5492, 26, 1508, 293, 203, 2], "prompt_token_count": 137, "reference_codepoints": 32, "repo": "upstash/context7", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [225, 2771, 10194, 81, 4918, 81, 10410, 81, 363, 81, 268, 21332, 81, 3242, 346, 967, 1346, 6893, 403, 1394, 31012, 301, 291], "continuation_token_count": 23, "decoded": " fn rm_rf_counts_and_removes_tree() -> anyhow::Result<()> {\n ", "decoded_codepoints": 68, "document_id": "j178/prek@438f9c5a6a594b609413da4ad8643423601a771f:crates/prek/src/cli/cache_clean.rs", "example_id": "000a663d3e590d6a07aa5d568f7978fe8500a44e3db3f96f462b20cc1ac161ce", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1157, 203, 111, 203, 203, 6357, 4687, 26, 5910, 2177, 203, 6357, 4568, 26, 4538, 23215, 403, 311, 20015, 81, 4071, 101, 2177, 203, 2862, 2771, 2421, 81, 11893, 46, 66, 44, 2894, 2084, 46, 1215, 15165, 81, 983, 44, 447, 27, 967, 3363, 403, 1394, 31012, 301, 284, 434, 2704, 4017, 30, 4227, 884, 13744, 29928, 461, 458, 667, 1957, 7553, 32, 284, 6311, 20268, 203, 111, 203, 203, 6357, 4687, 26, 858, 2177, 203, 1803, 3312, 301, 664, 3, 45, 446, 5496, 858, 79, 284, 2771, 10194, 81, 4918, 81, 10410, 81, 363, 81, 268, 21332, 81, 3242, 346, 967, 1346, 6893, 403, 1394, 31012, 301, 291, 1207, 1779, 280, 5969, 2976, 403, 890, 34192, 291, 1207, 3320, 81, 2388, 280, 1779, 32, 983, 922, 2524, 440, 2613, 724, 291, 5980, 81, 530, 403, 1297, 81, 1515, 81, 464, 26, 2613, 81, 2388, 32, 2524, 440, 15377, 33, 8327, 2131, 12370, 291, 5980, 81, 530, 403, 1821, 26, 24127, 2], "prompt_token_count": 163, "reference_codepoints": 64, "repo": "j178/prek", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [261, 1207, 3100, 280, 549, 4243, 77, 35, 970, 284, 1207], "continuation_token_count": 11, "decoded": " let second = &names[1];\n let", "decoded_codepoints": 34, "document_id": "microsoft/RustTraining@6bbe5330c4d5480b12cd10739572b03f3f73160c:python-book/src/ch07-ownership-and-borrowing.md", "example_id": "000a6dfcf2d1807c17727102d59b38732ffda9386613076028e71f1468097a64", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 96, 9170, 109, 44969, 13626, 203, 111, 203, 203, 3359, 1930, 81, 44969, 26, 426, 44, 892, 27, 967, 892, 301, 284, 2179, 9170, 8279, 30, 301, 426, 111, 15981, 203, 111, 203, 914, 203, 203, 46, 3958, 48, 203, 46, 1367, 48, 22758, 244, 12186, 377, 1367, 48, 203, 203, 914, 7421, 203, 3359, 2575, 346, 301, 284, 1207, 4031, 4467, 280, 4712, 19, 1365, 40880, 2296, 452, 81, 800, 1026, 313, 31596, 2296, 452, 81, 800, 22086, 284, 1207, 1932, 280, 549, 4243, 77, 34, 970, 334, 3, 33, 4417, 33187, 6744, 17382, 4031, 1741, 284, 4467, 32, 2018, 440, 2659, 16970, 2296, 452, 81, 800, 1035, 434, 9080, 10061, 12011, 1289, 10912, 26055, 33187, 446, 1207, 485, 32668, 280, 1930, 81, 44969, 1652, 4243, 77, 34, 1989, 434, 14131, 4121, 30, 646, 25913, 284, 11662, 9170, 109, 44969, 13626, 203, 111, 203, 203, 3359, 1930, 81, 44969, 26, 426, 44, 549, 466, 27, 967, 892, 301, 434, 2], "prompt_token_count": 162, "reference_codepoints": 32, "repo": "microsoft/RustTraining", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [11383, 328, 3438, 32, 15937, 47883, 301, 357, 202, 325, 18548, 32, 11307, 620, 610, 313, 405, 6053, 20, 1276, 18548], "continuation_token_count": 21, "decoded": "smart in sm.SmartDataMap {\n\t\tif smart.DiskType == \"emmc\" || smart", "decoded_codepoints": 65, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:agent/emmc_linux_test.go", "example_id": "000a6ec4a4f0906b9f73e10fdaeea0cbbfebd9141f301fb2f71556f93c2905a5", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 102, 55, 36943, 10033, 26, 46831, 77, 34, 1130, 203, 202, 325, 1137, 863, 1302, 1276, 653, 1253, 301, 357, 202, 102, 32, 14616, 440, 6174, 55, 36943, 10033, 346, 280, 308, 1253, 6132, 104, 30, 1137, 6132, 104, 471, 2637, 308, 1508, 30, 4930, 5715, 3835, 30, 1137, 27, 203, 202, 111, 203, 202, 325, 2069, 26, 1745, 32, 15937, 47883, 27, 863, 225, 35, 301, 357, 202, 102, 32, 14616, 440, 15937, 47883, 2069, 6132, 86, 30, 2637, 225, 35, 392, 2069, 26, 1745, 32, 15937, 47883, 490, 203, 202, 111, 203, 202, 869, 5424, 319, 11383, 32, 15937, 750, 203, 202, 979, 225, 3, 4930, 301, 357, 202, 102, 32, 14616, 440, 15937, 47883, 786, 1302, 657, 203, 202, 111, 203, 202, 325, 5424, 32, 11307, 620, 863, 313, 405, 6053, 20, 1276, 5424, 32, 11307, 558, 863, 2430, 1902, 33, 36943, 13216, 34, 20, 301, 357, 202, 102, 32, 14616, 440, 10300, 3829, 280, 308, 681, 6132, 99, 636, 6132, 99, 471, 2637, 308, 405, 6053, 46841, 1902, 33, 36943, 13216, 34, 5715, 5424, 32, 11307, 620, 30, 5424, 32, 11307, 558, 27, 203, 202, 111, 203, 202, 325, 5424, 32, 15937, 1533, 863, 313, 10431, 20, 301, 357, 202, 102, 32, 8038, 2], "prompt_token_count": 209, "reference_codepoints": 64, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [377, 87, 20941, 81, 26049, 48, 203, 46, 1141], "continuation_token_count": 9, "decoded": "\n{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [11383, 5630, 203, 202, 2946, 1572, 225, 319, 2946, 1572, 77, 2946, 1572, 1078, 79, 2071], "continuation_token_count": 16, "decoded": "smart fetch\n\tsystemManager *systemManager[systemManagerState] ", "decoded_codepoints": 77, "document_id": "henrygd/beszel@d3a1d61955b0e45fb6b6c76e3ef970cb6518a7e1:internal/hub/systems/system_manager.go", "example_id": "000a76a54acee0d0694bd16a3741c363a031979d764ce350a27a856bc8e8f0d9", "language": "go", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 88, 3777, 29922, 10737, 461, 3623, 12215, 32, 203, 306, 2030, 13650, 2664, 24828, 30, 2287, 7775, 30, 461, 48628, 4335, 17727, 461, 22337, 12215, 32, 203, 681, 1171, 1572, 1671, 301, 203, 202, 8494, 2264, 20089, 12054, 12740, 434, 17347, 2568, 436, 3500, 461, 225, 3, 647, 434, 7800, 31, 4770, 2968, 432, 4523, 10737, 203, 202, 9404, 1063, 262, 319, 9404, 32, 43138, 6022, 434, 17727, 2043, 3488, 436, 2664, 12215, 203, 202, 11383, 8675, 1208, 319, 31504, 1110, 32, 30283, 1208, 77, 11383, 8675, 1078, 79, 434, 40579, 2401, 13723, 3004, 5630, 1133, 33, 1267, 45, 44104, 438, 1755, 16870, 2], "prompt_token_count": 105, "reference_codepoints": 64, "repo": "henrygd/beszel", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "64_token_ish", "continuation_ids": [330, 426, 950, 1056, 32, 605, 32, 426, 30, 284, 3048, 44, 1056, 32, 605, 32, 2310, 30, 284, 2968, 606, 44, 1056, 32, 605, 32, 2157, 606, 30, 284, 2968, 558, 44, 1056, 32, 605, 32, 2157, 558, 30, 284, 2968, 3234, 44, 1056, 32, 605, 32, 2157, 3234, 30, 284, 2968, 1078, 44, 1056, 32, 605, 32, 2157, 1078, 30, 284, 2968, 5378, 44, 1056], "continuation_token_count": 67, "decoded": " 'name': result.data.name,\n description: result.data.description,\n storeId: result.data.storeId,\n storeName: result.data.storeName,\n storeDescription: result.data.storeDescription,\n storeState: result.data.storeState,\n storeRegistry: result", "decoded_codepoints": 258, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:src/core/store/foundation.ts", "example_id": "000a781a05d981498e27053631d3c23622372d4599a7040f8f41ced3e6d49589", "language": "typescript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 605, 1078, 3694, 32, 4770, 4480, 26, 1294, 293, 719, 415, 1429, 1267, 32, 3127, 27, 301, 284, 1422, 5535, 2780, 1078, 924, 26, 397, 330, 2157, 5035, 1603, 370, 397, 2179, 76, 431, 25092, 26, 1267, 32, 731, 27, 284, 1093, 334, 320, 719, 6042, 2780, 606, 26, 1267, 32, 605, 32, 314, 293, 719, 442, 301, 284, 1503, 44, 225, 35, 30, 284, 804, 44, 1056, 32, 605, 32, 314, 30, 3, 5261, 5535, 2780, 1078, 924, 26, 397, 330, 2157, 10880, 1603, 370, 397, 2179, 76, 431, 25092, 26, 1267, 32, 731, 27, 284, 1093, 334, 320, 719, 1201, 2303, 2780, 5332, 26, 959, 32, 3494, 26, 1267, 32, 605, 32, 26231, 471, 330, 2157, 804, 895, 719, 442, 37410, 22824, 1371, 284, 1503, 44, 225, 35, 30, 284, 15321, 44, 1056, 32, 605, 32, 26231, 30, 334, 1122, 203, 2], "prompt_token_count": 145, "reference_codepoints": 256, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [1201, 32, 2228, 26, 5139, 15098, 710, 6172, 32, 1436, 2188, 330, 1126, 370, 330, 6172], "continuation_token_count": 16, "decoded": " assert.equal(typeof handlers['chat.message'], 'function', 'chat", "decoded_codepoints": 64, "document_id": "JuliusBrussee/caveman@0d95a81d35a9f2d123a5e9430d1cfc43d55f1bb0:tests/installer/opencode.test.mjs", "example_id": "000a84e3b5f30b350906ac22585819d17cde727dd62362c2605937d5dc319154", "language": "javascript", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 1381, 526, 312, 667, 895, 284, 1201, 32, 2228, 26, 5139, 15098, 710, 6172, 32, 1436, 2188, 330, 1126, 370, 330, 6172, 32, 1436, 1395, 526, 312, 667, 895, 284, 1201, 32, 2228, 26, 5139, 15098, 710, 19561, 32, 6172, 32, 2946, 32, 3792, 2188, 330, 1126, 370, 397, 330, 2946, 32, 3792, 1395, 526, 312, 667, 895, 446, 3, 261, 2014, 15098, 710, 6172, 32, 1436, 41062, 6807, 301, 8710, 44, 7316, 827, 44, 330, 878, 370, 1344, 44, 3056, 85, 453, 37076, 8194, 2692, 25, 16752, 1122, 284, 1201, 32, 2228, 26, 2548, 32, 27192, 26, 4555, 1215, 30, 330, 3310, 42, 1425, 330, 338, 2692, 895, 446, 434, 2156, 687, 2910, 5986, 2430, 85, 453, 37076, 333, 2649, 5844, 1991, 322, 2016, 3079, 2670, 284, 434, 11210, 32, 1436, 37957, 2], "prompt_token_count": 135, "reference_codepoints": 64, "repo": "JuliusBrussee/caveman", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "32_token_ish", "continuation_ids": [3732, 27, 2276, 32, 203, 40, 32, 35225, 529, 1877, 18119, 1801, 1974, 4905, 2276, 308, 462, 31, 3732, 27, 2276, 32, 203, 41, 32, 35225, 529, 1877, 18119, 1801, 1974, 4905, 2276], "continuation_token_count": 33, "decoded": "tool) files.\n6. During `updateExisting`, update existing files (per-tool) files.\n7. During `updateExisting`, update existing files", "decoded_codepoints": 130, "document_id": "Fission-AI/OpenSpec@19d41714c8b790488732687443713e406ef5aeef:openspec/changes/archive/2025-09-29-add-slash-command-support/proposal.md", "example_id": "000a992a2456873fd8fd8e093859fdae427c68049ce22da999cab475815c8be8", "language": "markdown", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 85, 31, 25520, 4529, 372, 7358, 43253, 32, 203, 38, 32, 26881, 518, 12877, 44, 5597, 2016, 35875, 5049, 461, 23261, 10160, 8684, 45, 4871, 16645, 1292, 31, 3732, 44431, 308, 43305, 30, 12770, 30, 26719, 547, 203, 39, 32, 35225, 529, 11593, 897, 1974, 1801, 9737, 1755, 4905, 29659, 2016, 2276, 308, 462, 31, 3, 11856, 4609, 2276, 1292, 4559, 32, 334, 429, 1283, 3605, 11420, 9283, 2784, 312, 3982, 529, 1163, 6777, 82, 308, 87, 32, 89, 4317, 529, 371, 17329, 2262, 2629, 25506, 1519, 44, 802, 45, 6186, 44, 330, 16227, 920, 804, 44, 802, 320, 5856, 547, 334, 429, 14112, 529, 5536, 1934, 26, 2250, 1215, 30, 2156, 2285, 2976, 7601, 436, 3219, 461, 529, 1877, 18119, 26, 2250, 9913, 2], "prompt_token_count": 126, "reference_codepoints": 128, "repo": "Fission-AI/OpenSpec", "role": "native_fim_comparator", "stop_event": "oracle_length_reached", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [5877, 6753], "continuation_token_count": 2, "decoded": "------------------------------------------------------", "decoded_codepoints": 54, "document_id": "browser-use/browser-use@0964ad452a9f3fe249042a5ffb235e5f98519b2e:tests/ci/test_multi_act_guards.py", "example_id": "000ab325a422bcd779acd4ff4594db4d8912e0396dfa981886cca28012a4b199", "language": "python", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 265, 81, 539, 32, 4867, 32, 2122, 1188, 14225, 203, 1070, 5427, 81, 539, 32, 7128, 1188, 14161, 3135, 203, 1070, 5427, 81, 539, 32, 7128, 32, 3959, 1188, 14161, 4290, 203, 1070, 5427, 81, 539, 32, 4280, 32, 2122, 1188, 15635, 203, 1070, 3312, 32, 1871, 32, 468, 708, 445, 1188, 1487, 81, 3613, 81, 611, 95, 203, 203, 21, 8583, 7985, 3, 34278, 478, 203, 50, 12408, 32, 12940, 26, 3473, 1057, 2848, 683, 203, 589, 1913, 81, 1786, 2262, 203, 202, 2993, 1006, 4808, 2145, 623, 7853, 436, 16314, 3312, 7103, 203, 202, 1786, 280, 4808, 2059, 346, 203, 202, 1786, 32, 1366, 346, 478, 202, 1786, 32, 2358, 81, 1357, 3247, 599, 1814, 5243, 2], "prompt_token_count": 120, "reference_codepoints": 64, "repo": "browser-use/browser-use", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "16_token_ish", "continuation_ids": [528, 638, 5464, 346, 275], "continuation_token_count": 5, "decoded": "\n .trim()\n ", "decoded_codepoints": 33, "document_id": "0xPlaygrounds/rig@7f1a4950fce8c275541c58936e877125cd053f14:tests/providers/anthropic/cassette/messages_thinking.rs", "example_id": "000ab71e98310e851df2fd45e60f45b46bfe7600d0d4d1330ec739a5c02bb747", "language": "rust", "model": "bigcode/tiny_starcoder_py", "prompt_ids": [1, 13519, 6621, 3346, 31004, 81, 16462, 299, 1395, 526, 16187, 724, 1064, 1207, 1344, 44, 892, 280, 3100, 81, 1986, 400, 638, 11447, 400, 638, 1731, 346, 400, 638, 2029, 81, 1110, 12143, 1286, 110, 2530, 1795, 301, 528, 34043, 1777, 403, 1031, 26, 878, 27, 225, 3, 1468, 1790, 400, 638, 6174, 473, 324, 1201, 4482, 400, 653, 878, 32, 5464, 922, 297, 81, 2951, 1026, 400, 313, 10756, 31, 417, 6927, 1395, 13882, 1344, 2685, 28617, 299, 3346, 31004, 19383, 20, 324, 1093, 291, 801, 284, 829, 284, 638, 6240, 45, 203, 111, 203, 203, 6357, 13586, 716, 403, 858, 79, 203, 302, 2], "prompt_token_count": 107, "reference_codepoints": 64, "repo": "0xPlaygrounds/rig", "role": "native_fim_comparator", "stop_event": "stop_token", "template": "{prefix}{suffix}"} {"bin": "8_token_ish", "continuation_ids": [1028, 827, 333, 1423, 48, 4792, 440, 7387, 10620, 657, 377, 1423], "continuation_token_count": 12, "decoded": "of type