[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-28ce75129904ad31-nvidia-ising-ai-models-automate-quantum-calibratio-summary":3,"summaries-facets-categories":93,"summary-related-28ce75129904ad31-nvidia-ising-ai-models-automate-quantum-calibratio-summary":3662},{"id":4,"title":5,"ai":6,"body":13,"categories":46,"created_at":48,"date_modified":48,"description":40,"extension":49,"faq":48,"featured":50,"kicker_label":48,"meta":51,"navigation":76,"path":77,"published_at":78,"question":48,"scraped_at":79,"seo":80,"sitemap":81,"source_id":82,"source_name":83,"source_type":84,"source_url":85,"stem":86,"tags":87,"thumbnail_url":48,"tldr":90,"tweet":48,"unknown_tags":91,"__hash__":92},"summaries\u002Fsummaries\u002F28ce75129904ad31-nvidia-ising-ai-models-automate-quantum-calibratio-summary.md","NVIDIA Ising AI Models Automate Quantum Calibration and Error Correction",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","x-ai\u002Fgrok-4.1-fast",4979,1792,13912,0.0018693,{"type":14,"value":15,"toc":39},"minimark",[16,21,25,29,32,36],[17,18,20],"h2",{"id":19},"replace-manual-quantum-tuning-with-ai-agents","Replace Manual Quantum Tuning with AI Agents",[22,23,24],"p",{},"Quantum processors fail due to qubit sensitivity to noise, requiring constant manual calibration (days per experiment) and real-time error correction. NVIDIA Ising Calibration, a vision-language model, acts as an AI agent that interprets hardware diagnostics and auto-adjusts parameters, slashing calibration from days to hours. This eliminates the biggest development bottleneck, letting researchers run more experiments faster. Ising Decoding deploys 3D CNNs in two variants—one for speed, one for accuracy—to infer correct qubit states from noisy data, outperforming pyMatching by 2.5x in speed and 3x in accuracy. These models enable scalable error correction without custom signal processing expertise.",[17,26,28],{"id":27},"day-one-deployment-proves-cross-modal-versatility","Day-One Deployment Proves Cross-Modal Versatility",[22,30,31],{},"Ising Calibration is live at Atom Computing, Harvard, IonQ, IQM Quantum Computers, Lawrence Berkeley National Lab, and others across neutral-atom, trapped-ion, and superconducting qubits. Ising Decoding runs at Cornell, Sandia National Labs, UC Santa Barbara, University of Chicago, and commercial firms like Infleqtion and SEEQC. This broad adoption by 20+ national labs, universities, and vendors validates Ising's generality—fine-tune once, deploy anywhere—bypassing modality-specific tweaks that slow quantum progress.",[17,33,35],{"id":34},"embed-in-hybrid-quantum-classical-workflows","Embed in Hybrid Quantum-Classical Workflows",[22,37,38],{},"Ising plugs into NVIDIA's CUDA-Q platform, mirroring CUDA's GPU kernel style for quantum-classical programming, and NVQLink hardware for low-latency QPU-GPU links during error correction. Download models from GitHub\u002FHugging Face\u002Fbuild.nvidia.com; fine-tune with NIM microservices. This stack turns lab QPUs into production-capable systems, closing the hardware-to-app gap without proprietary lock-in.",{"title":40,"searchDepth":41,"depth":41,"links":42},"",2,[43,44,45],{"id":19,"depth":41,"text":20},{"id":27,"depth":41,"text":28},{"id":34,"depth":41,"text":35},[47],"AI News & Trends",null,"md",false,{"content_references":52,"triage":71},[53,57,60,62,67],{"type":54,"title":55,"context":56},"tool","pyMatching","mentioned",{"type":54,"title":58,"publisher":59,"context":56},"CUDA-Q","NVIDIA",{"type":54,"title":61,"publisher":59,"context":56},"NVQLink",{"type":63,"title":64,"url":65,"context":66},"other","NVIDIA Launches Ising: The World’s First Open AI Models to Accelerate the Path to Useful Quantum Computers","https:\u002F\u002Fnvidianews.nvidia.com\u002Fnews\u002Fnvidia-launches-ising-the-worlds-first-open-ai-models-to-accelerate-the-path-to-useful-quantum-computers","cited",{"type":63,"title":68,"url":69,"context":70},"NVIDIA Ising Product Page","https:\u002F\u002Fwww.nvidia.com\u002Fen-us\u002Fsolutions\u002Fquantum-computing\u002Fising\u002F","recommended",{"relevance":72,"novelty":72,"quality":73,"actionability":72,"composite":74,"reasoning":75},3,4,3.25,"Category: AI & LLMs. The article discusses NVIDIA's Ising AI models for quantum calibration and error correction, which maps to AI & LLMs. While it presents some new insights into the application of AI in quantum computing, it lacks detailed actionable steps for the audience to implement these technologies in their own projects.",true,"\u002Fsummaries\u002F28ce75129904ad31-nvidia-ising-ai-models-automate-quantum-calibratio-summary","2026-04-19 07:54:42","2026-04-21 15:27:02",{"title":5,"description":40},{"loc":77},"28ce75129904ad31","MarkTechPost","article","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F04\u002F19\u002Fnvidia-releases-ising\u002F","summaries\u002F28ce75129904ad31-nvidia-ising-ai-models-automate-quantum-calibratio-summary",[88,89],"machine-learning","open-source","NVIDIA's open Ising models use vision-language AI for calibration (days to hours) and 3D CNNs for error decoding (2.5x faster, 3x more accurate than pyMatching), accelerating practical quantum apps.",[],"11kUZNyzmFDlq8Uypmd15An3ucOYopRrOcFCDK_uO5I",[94,97,100,103,106,109,111,113,115,117,119,121,123,125,127,129,131,133,135,137,139,141,144,147,149,151,154,156,158,161,163,165,167,169,171,173,175,177,179,181,183,185,187,189,191,193,195,197,199,201,203,205,207,209,211,213,215,217,219,221,223,225,227,229,231,233,235,237,239,241,243,245,247,249,251,253,255,257,259,261,263,265,267,269,271,273,275,277,279,281,283,285,287,289,291,293,295,297,299,301,303,305,307,309,311,313,315,317,319,321,323,325,327,329,331,333,335,337,339,341,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,397,399,401,403,405,407,409,411,413,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546,548,550,552,554,556,558,560,562,564,566,568,570,572,574,576,578,580,582,584,586,588,590,592,594,596,598,600,602,604,606,608,610,612,614,616,618,620,622,624,626,628,630,632,634,636,638,640,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,678,680,682,684,686,688,690,692,694,696,698,700,702,704,706,708,710,712,714,716,718,720,722,724,726,728,730,732,734,736,738,740,742,744,746,748,750,752,754,756,758,760,762,764,766,768,770,772,774,776,778,780,782,784,786,788,790,792,794,796,798,800,802,804,806,808,810,812,814,816,818,820,822,824,826,828,830,832,834,836,838,840,842,844,846,848,850,852,854,856,858,860,862,864,866,868,870,872,874,876,878,880,882,884,886,888,890,892,894,896,898,900,902,904,906,908,910,912,914,916,918,920,922,924,926,928,930,932,934,936,938,940,942,944,946,948,950,952,954,956,958,960,962,964,966,968,970,972,974,976,978,980,982,984,986,988,990,992,994,996,998,1000,1002,1004,1006,1008,1010,1012,1014,1016,1018,1020,1022,1024,1026,1028,1030,1032,1034,1036,1038,1040,1042,1044,1046,1048,1050,1052,1054,1056,1058,1060,1062,1064,1066,1068,1070,1072,1074,1076,1078,1080,1082,1084,1086,1088,1090,1092,1094,1096,1098,1100,1102,1104,1106,1108,1110,1112,1114,1116,1118,1120,1122,1124,1126,1128,1130,1132,1134,1136,1138,1140,1142,1144,1146,1148,1150,1152,1154,1156,1158,1160,1162,1164,1166,1168,1170,1172,1174,1176,1178,1180,1182,1184,1186,1188,1190,1192,1194,1196,1198,1200,1202,1204,1206,1208,1210,1212,1214,1216,1218,1220,1222,1224,1226,1228,1230,1232,1234,1236,1238,1240,1242,1244,1246,1248,1250,1252,1254,1256,1258,1260,1262,1264,1266,1268,1270,1272,1274,1276,1278,1280,1282,1284,1286,1288,1290,1292,1294,1296,1298,1300,1302,1304,1306,1308,1310,1312,1314,1316,1318,1320,1322,1324,1326,1328,1330,1332,1334,1336,1338,1340,1342,1344,1346,1348,1350,1352,1354,1356,1358,1360,1362,1364,1366,1368,1370,1372,1374,1376,1378,1380,1382,1384,1386,1388,1390,1392,1394,1396,1398,1400,1402,1404,1406,1408,1410,1412,1414,1416,1418,1420,1422,1424,1426,1428,1430,1432,1434,1436,1438,1440,1442,1444,1446,1448,1450,1452,1454,1456,1458,1460,1462,1464,1466,1468,1470,1472,1474,1476,1478,1480,1482,1484,1486,1488,1490,1492,1494,1496,1498,1500,1502,1504,1506,1508,1510,1512,1514,1516,1518,1520,1522,1524,1526,1528,1530,1532,1534,1536,1538,1540,1542,1544,1546,1548,1550,1552,1554,1556,1558,1560,1562,1564,1566,1568,1570,1572,1574,1576,1578,1580,1582,1584,1586,1588,1590,1592,1594,1596,1598,1600,1602,1604,1606,1608,1610,1612,1614,1616,1618,1620,1622,1624,1626,1628,1630,1632,1634,1636,1638,1640,1642,1644,1646,1648,1650,1652,1654,1656,1658,1660,1662,1664,1666,1668,1670,1672,1674,1676,1678,1680,1682,1684,1686,1688,1690,1692,1694,1696,1698,1700,1702,1704,1706,1708,1710,1712,1714,1716,1718,1720,1722,1724,1726,1728,1730,1732,1734,1736,1738,1740,1742,1744,1746,1748,1750,1752,1754,1756,1758,1760,1762,1764,1766,1768,1770,1772,1774,1776,1778,1780,1782,1784,1786,1788,1790,1792,1794,1796,1798,1800,1802,1804,1806,1808,1810,1812,1814,1816,1818,1820,1822,1824,1826,1828,1830,1832,1834,1836,1838,1840,1842,1844,1846,1848,1850,1852,1854,1856,1858,1860,1862,1864,1866,1868,1870,1872,1874,1876,1878,1880,1882,1884,1886,1888,1890,1892,1894,1896,1898,1900,1902,1904,1906,1908,1910,1912,1914,1916,1918,1920,1922,1924,1926,1928,1930,1932,1934,1936,1938,1940,1942,1944,1946,1948,1950,1952,1954,1956,1958,1960,1962,1964,1966,1968,1970,1972,1974,1976,1978,1980,1982,1984,1986,1988,1990,1992,1994,1996,1998,2000,2002,2004,2006,2008,2010,2012,2014,2016,2018,2020,2022,2024,2026,2028,2030,2032,2034,2036,2038,2040,2042,2044,2046,2048,2050,2052,2054,2056,2058,2060,2062,2064,2066,2068,2070,2072,2074,2076,2078,2080,2082,2084,2086,2088,2090,2092,2094,2096,2098,2100,2102,2104,2106,2108,2110,2112,2114,2116,2118,2120,2122,2124,2126,2128,2130,2132,2134,2136,2138,2140,2142,2144,2146,2148,2150,2152,2154,2156,2158,2160,2162,2164,2166,2168,2170,2172,2174,2176,2178,2180,2182,2184,2186,2188,2190,2192,2194,2196,2198,2200,2202,2204,2206,2208,2210,2212,2214,2216,2218,2220,2222,2224,2226,2228,2230,2232,2234,2236,2238,2240,2242,2244,2246,2248,2250,2252,2254,2256,2258,2260,2262,2264,2266,2268,2270,2272,2274,2276,2278,2280,2282,2284,2286,2288,2290,2292,2294,2296,2298,2300,2302,2304,2306,2308,2310,2312,2314,2316,2318,2320,2322,2324,2326,2328,2330,2332,2334,2336,2338,2340,2342,2344,2346,2348,2350,2352,2354,2356,2358,2360,2362,2364,2366,2368,2370,2372,2374,2376,2378,2380,2382,2384,2386,2388,2390,2392,2394,2396,2398,2400,2402,2404,2406,2408,2410,2412,2414,2416,2418,2420,2422,2424,2426,2428,2430,2432,2434,2436,2438,2440,2442,2444,2446,2448,2450,2452,2454,2456,2458,2460,2462,2464,2466,2468,2470,2472,2474,2476,2478,2480,2482,2484,2486,2488,2490,2492,2494,2496,2498,2500,2502,2504,2506,2508,2510,2512,2514,2516,2518,2520,2522,2524,2526,2528,2530,2532,2534,2536,2538,2540,2542,2544,2546,2548,2550,2552,2554,2556,2558,2560,2562,2564,2566,2568,2570,2572,2574,2576,2578,2580,2582,2584,2586,2588,2590,2592,2594,2596,2598,2600,2602,2604,2606,2608,2610,2612,2614,2616,2618,2620,2622,2624,2626,2628,2630,2632,2634,2636,2638,2640,2642,2644,2646,2648,2650,2652,2654,2656,2658,2660,2662,2664,2666,2668,2670,2672,2674,2676,2678,2680,2682,2684,2686,2688,2690,2692,2694,2696,2698,2700,2702,2704,2706,2708,2710,2712,2714,2716,2718,2720,2722,2724,2726,2728,2730,2732,2734,2736,2738,2740,2742,2744,2746,2748,2750,2752,2754,2756,2758,2760,2762,2764,2766,2768,2770,2772,2774,2776,2778,2780,2782,2784,2786,2788,2790,2792,2794,2796,2798,2800,2802,2804,2806,2808,2810,2812,2814,2816,2818,2820,2822,2824,2826,2828,2830,2832,2834,2836,2838,2840,2842,2844,2846,2848,2850,2852,2854,2856,2858,2860,2862,2864,2866,2868,2870,2872,2874,2876,2878,2880,2882,2884,2886,2888,2890,2892,2894,2896,2898,2900,2902,2904,2906,2908,2910,2912,2914,2916,2918,2920,2922,2924,2926,2928,2930,2932,2934,2936,2938,2940,2942,2944,2946,2948,2950,2952,2954,2956,2958,2960,2962,2964,2966,2968,2970,2972,2974,2976,2978,2980,2982,2984,2986,2988,2990,2992,2994,2996,2998,3000,3002,3004,3006,3008,3010,3012,3014,3016,3018,3020,3022,3024,3026,3028,3030,3032,3034,3036,3038,3040,3042,3044,3046,3048,3050,3052,3054,3056,3058,3060,3062,3064,3066,3068,3070,3072,3074,3076,3078,3080,3082,3084,3086,3088,3090,3092,3094,3096,3098,3100,3102,3104,3106,3108,3110,3112,3114,3116,3118,3120,3122,3124,3126,3128,3130,3132,3134,3136,3138,3140,3142,3144,3146,3148,3150,3152,3154,3156,3158,3160,3162,3164,3166,3168,3170,3172,3174,3176,3178,3180,3182,3184,3186,3188,3190,3192,3194,3196,3198,3200,3202,3204,3206,3208,3210,3212,3214,3216,3218,3220,3222,3224,3226,3228,3230,3232,3234,3236,3238,3240,3242,3244,3246,3248,3250,3252,3254,3256,3258,3260,3262,3264,3266,3268,3270,3272,3274,3276,3278,3280,3282,3284,3286,3288,3290,3292,3294,3296,3298,3300,3302,3304,3306,3308,3310,3312,3314,3316,3318,3320,3322,3324,3326,3328,3330,3332,3334,3336,3338,3340,3342,3344,3346,3348,3350,3352,3354,3356,3358,3360,3362,3364,3366,3368,3370,3372,3374,3376,3378,3380,3382,3384,3386,3388,3390,3392,3394,3396,3398,3400,3402,3404,3406,3408,3410,3412,3414,3416,3418,3420,3422,3424,3426,3428,3430,3432,3434,3436,3438,3440,3442,3444,3446,3448,3450,3452,3454,3456,3458,3460,3462,3464,3466,3468,3470,3472,3474,3476,3478,3480,3482,3484,3486,3488,3490,3492,3494,3496,3498,3500,3502,3504,3506,3508,3510,3512,3514,3516,3518,3520,3522,3524,3526,3528,3530,3532,3534,3536,3538,3540,3542,3544,3546,3548,3550,3552,3554,3556,3558,3560,3562,3564,3566,3568,3570,3572,3574,3576,3578,3580,3582,3584,3586,3588,3590,3592,3594,3596,3598,3600,3602,3604,3606,3608,3610,3612,3614,3616,3618,3620,3622,3624,3626,3628,3630,3632,3634,3636,3638,3640,3642,3644,3646,3648,3650,3652,3654,3656,3658,3660],{"categories":95},[96],"Developer Productivity",{"categories":98},[99],"Business & SaaS",{"categories":101},[102],"AI & LLMs",{"categories":104},[105],"AI Automation",{"categories":107},[108],"Product Strategy",{"categories":110},[102],{"categories":112},[96],{"categories":114},[99],{"categories":116},[],{"categories":118},[102],{"categories":120},[],{"categories":122},[47],{"categories":124},[105],{"categories":126},[47],{"categories":128},[105],{"categories":130},[105],{"categories":132},[102],{"categories":134},[102],{"categories":136},[47],{"categories":138},[102],{"categories":140},[],{"categories":142},[143],"Design & Frontend",{"categories":145},[146],"Data Science & Visualization",{"categories":148},[47],{"categories":150},[],{"categories":152},[153],"Software Engineering",{"categories":155},[102],{"categories":157},[105],{"categories":159},[160],"Marketing & Growth",{"categories":162},[102],{"categories":164},[105],{"categories":166},[],{"categories":168},[],{"categories":170},[143],{"categories":172},[105],{"categories":174},[96],{"categories":176},[143],{"categories":178},[102],{"categories":180},[105],{"categories":182},[47],{"categories":184},[],{"categories":186},[],{"categories":188},[105],{"categories":190},[153],{"categories":192},[],{"categories":194},[99],{"categories":196},[],{"categories":198},[],{"categories":200},[105],{"categories":202},[105],{"categories":204},[102],{"categories":206},[],{"categories":208},[153],{"categories":210},[],{"categories":212},[],{"categories":214},[],{"categories":216},[102],{"categories":218},[160],{"categories":220},[143],{"categories":222},[143],{"categories":224},[102],{"categories":226},[105],{"categories":228},[102],{"categories":230},[102],{"categories":232},[105],{"categories":234},[105],{"categories":236},[146],{"categories":238},[47],{"categories":240},[105],{"categories":242},[160],{"categories":244},[105],{"categories":246},[108],{"categories":248},[],{"categories":250},[105],{"categories":252},[],{"categories":254},[105],{"categories":256},[153],{"categories":258},[143],{"categories":260},[102],{"categories":262},[],{"categories":264},[],{"categories":266},[105],{"categories":268},[],{"categories":270},[102],{"categories":272},[],{"categories":274},[96],{"categories":276},[153],{"categories":278},[99],{"categories":280},[47],{"categories":282},[102],{"categories":284},[],{"categories":286},[102],{"categories":288},[],{"categories":290},[153],{"categories":292},[146],{"categories":294},[],{"categories":296},[102],{"categories":298},[143],{"categories":300},[],{"categories":302},[143],{"categories":304},[105],{"categories":306},[],{"categories":308},[105],{"categories":310},[47],{"categories":312},[102],{"categories":314},[],{"categories":316},[105],{"categories":318},[102],{"categories":320},[108],{"categories":322},[],{"categories":324},[102],{"categories":326},[105],{"categories":328},[105],{"categories":330},[],{"categories":332},[146],{"categories":334},[102],{"categories":336},[],{"categories":338},[96],{"categories":340},[99],{"categories":342},[102],{"categories":344},[105],{"categories":346},[153],{"categories":348},[102],{"categories":350},[],{"categories":352},[],{"categories":354},[102],{"categories":356},[],{"categories":358},[143],{"categories":360},[],{"categories":362},[102],{"categories":364},[],{"categories":366},[105],{"categories":368},[102],{"categories":370},[143],{"categories":372},[],{"categories":374},[102],{"categories":376},[102],{"categories":378},[99],{"categories":380},[105],{"categories":382},[102],{"categories":384},[143],{"categories":386},[105],{"categories":388},[],{"categories":390},[],{"categories":392},[47],{"categories":394},[],{"categories":396},[102],{"categories":398},[99,160],{"categories":400},[],{"categories":402},[102],{"categories":404},[],{"categories":406},[],{"categories":408},[102],{"categories":410},[],{"categories":412},[102],{"categories":414},[415],"DevOps & Cloud",{"categories":417},[],{"categories":419},[47],{"categories":421},[143],{"categories":423},[],{"categories":425},[47],{"categories":427},[47],{"categories":429},[102],{"categories":431},[160],{"categories":433},[],{"categories":435},[99],{"categories":437},[],{"categories":439},[102,415],{"categories":441},[102],{"categories":443},[102],{"categories":445},[105],{"categories":447},[102,153],{"categories":449},[146],{"categories":451},[102],{"categories":453},[160],{"categories":455},[105],{"categories":457},[105],{"categories":459},[],{"categories":461},[105],{"categories":463},[102,99],{"categories":465},[],{"categories":467},[143],{"categories":469},[143],{"categories":471},[],{"categories":473},[],{"categories":475},[47],{"categories":477},[],{"categories":479},[96],{"categories":481},[153],{"categories":483},[102],{"categories":485},[143],{"categories":487},[105],{"categories":489},[153],{"categories":491},[47],{"categories":493},[143],{"categories":495},[],{"categories":497},[102],{"categories":499},[102],{"categories":501},[102],{"categories":503},[47],{"categories":505},[96],{"categories":507},[102],{"categories":509},[105],{"categories":511},[415],{"categories":513},[143],{"categories":515},[105],{"categories":517},[],{"categories":519},[],{"categories":521},[143],{"categories":523},[47],{"categories":525},[146],{"categories":527},[],{"categories":529},[102],{"categories":531},[102],{"categories":533},[99],{"categories":535},[102],{"categories":537},[102],{"categories":539},[47],{"categories":541},[],{"categories":543},[105],{"categories":545},[153],{"categories":547},[],{"categories":549},[102],{"categories":551},[102],{"categories":553},[105],{"categories":555},[],{"categories":557},[],{"categories":559},[102],{"categories":561},[],{"categories":563},[99],{"categories":565},[105],{"categories":567},[],{"categories":569},[96],{"categories":571},[102],{"categories":573},[99],{"categories":575},[47],{"categories":577},[],{"categories":579},[],{"categories":581},[],{"categories":583},[47],{"categories":585},[47],{"categories":587},[],{"categories":589},[],{"categories":591},[99],{"categories":593},[],{"categories":595},[],{"categories":597},[96],{"categories":599},[],{"categories":601},[160],{"categories":603},[105],{"categories":605},[99],{"categories":607},[105],{"categories":609},[],{"categories":611},[108],{"categories":613},[143],{"categories":615},[153],{"categories":617},[102],{"categories":619},[105],{"categories":621},[99],{"categories":623},[102],{"categories":625},[],{"categories":627},[],{"categories":629},[153],{"categories":631},[146],{"categories":633},[108],{"categories":635},[105],{"categories":637},[102],{"categories":639},[],{"categories":641},[415],{"categories":643},[],{"categories":645},[105],{"categories":647},[],{"categories":649},[],{"categories":651},[102],{"categories":653},[143],{"categories":655},[160],{"categories":657},[105],{"categories":659},[],{"categories":661},[96],{"categories":663},[],{"categories":665},[47],{"categories":667},[102,415],{"categories":669},[47],{"categories":671},[102],{"categories":673},[99],{"categories":675},[102],{"categories":677},[],{"categories":679},[99],{"categories":681},[],{"categories":683},[153],{"categories":685},[143],{"categories":687},[47],{"categories":689},[146],{"categories":691},[96],{"categories":693},[102],{"categories":695},[153],{"categories":697},[],{"categories":699},[],{"categories":701},[108],{"categories":703},[],{"categories":705},[102],{"categories":707},[],{"categories":709},[143],{"categories":711},[143],{"categories":713},[143],{"categories":715},[],{"categories":717},[],{"categories":719},[47],{"categories":721},[105],{"categories":723},[102],{"categories":725},[102],{"categories":727},[102],{"categories":729},[99],{"categories":731},[102],{"categories":733},[],{"categories":735},[153],{"categories":737},[153],{"categories":739},[99],{"categories":741},[],{"categories":743},[102],{"categories":745},[102],{"categories":747},[99],{"categories":749},[47],{"categories":751},[160],{"categories":753},[105],{"categories":755},[],{"categories":757},[143],{"categories":759},[],{"categories":761},[102],{"categories":763},[],{"categories":765},[99],{"categories":767},[105],{"categories":769},[],{"categories":771},[415],{"categories":773},[146],{"categories":775},[153],{"categories":777},[160],{"categories":779},[153],{"categories":781},[105],{"categories":783},[],{"categories":785},[],{"categories":787},[105],{"categories":789},[96],{"categories":791},[105],{"categories":793},[108],{"categories":795},[99],{"categories":797},[],{"categories":799},[102],{"categories":801},[108],{"categories":803},[102],{"categories":805},[102],{"categories":807},[160],{"categories":809},[143],{"categories":811},[105],{"categories":813},[],{"categories":815},[],{"categories":817},[415],{"categories":819},[153],{"categories":821},[],{"categories":823},[105],{"categories":825},[102],{"categories":827},[143,102],{"categories":829},[96],{"categories":831},[],{"categories":833},[102],{"categories":835},[96],{"categories":837},[143],{"categories":839},[105],{"categories":841},[153],{"categories":843},[],{"categories":845},[102],{"categories":847},[],{"categories":849},[96],{"categories":851},[],{"categories":853},[105],{"categories":855},[108],{"categories":857},[102],{"categories":859},[102],{"categories":861},[143],{"categories":863},[105],{"categories":865},[415],{"categories":867},[143],{"categories":869},[105],{"categories":871},[102],{"categories":873},[102],{"categories":875},[102],{"categories":877},[47],{"categories":879},[],{"categories":881},[108],{"categories":883},[105],{"categories":885},[143],{"categories":887},[105],{"categories":889},[153],{"categories":891},[143],{"categories":893},[105],{"categories":895},[47],{"categories":897},[],{"categories":899},[102],{"categories":901},[143],{"categories":903},[102],{"categories":905},[96],{"categories":907},[47],{"categories":909},[102],{"categories":911},[160],{"categories":913},[102],{"categories":915},[102],{"categories":917},[105],{"categories":919},[105],{"categories":921},[102],{"categories":923},[105],{"categories":925},[143],{"categories":927},[102],{"categories":929},[],{"categories":931},[],{"categories":933},[153],{"categories":935},[],{"categories":937},[96],{"categories":939},[415],{"categories":941},[],{"categories":943},[96],{"categories":945},[99],{"categories":947},[160],{"categories":949},[],{"categories":951},[99],{"categories":953},[],{"categories":955},[],{"categories":957},[],{"categories":959},[],{"categories":961},[],{"categories":963},[102],{"categories":965},[105],{"categories":967},[415],{"categories":969},[96],{"categories":971},[102],{"categories":973},[153],{"categories":975},[108],{"categories":977},[102],{"categories":979},[160],{"categories":981},[102],{"categories":983},[102],{"categories":985},[102],{"categories":987},[102,96],{"categories":989},[153],{"categories":991},[153],{"categories":993},[143],{"categories":995},[102],{"categories":997},[],{"categories":999},[],{"categories":1001},[],{"categories":1003},[153],{"categories":1005},[146],{"categories":1007},[47],{"categories":1009},[143],{"categories":1011},[],{"categories":1013},[102],{"categories":1015},[102],{"categories":1017},[],{"categories":1019},[],{"categories":1021},[105],{"categories":1023},[102],{"categories":1025},[99],{"categories":1027},[],{"categories":1029},[96],{"categories":1031},[102],{"categories":1033},[96],{"categories":1035},[102],{"categories":1037},[153],{"categories":1039},[160],{"categories":1041},[102,143],{"categories":1043},[47],{"categories":1045},[143],{"categories":1047},[],{"categories":1049},[415],{"categories":1051},[143],{"categories":1053},[105],{"categories":1055},[],{"categories":1057},[],{"categories":1059},[],{"categories":1061},[],{"categories":1063},[153],{"categories":1065},[105],{"categories":1067},[105],{"categories":1069},[102],{"categories":1071},[102],{"categories":1073},[],{"categories":1075},[143],{"categories":1077},[],{"categories":1079},[],{"categories":1081},[105],{"categories":1083},[],{"categories":1085},[],{"categories":1087},[160],{"categories":1089},[160],{"categories":1091},[105],{"categories":1093},[],{"categories":1095},[102],{"categories":1097},[102],{"categories":1099},[153],{"categories":1101},[143],{"categories":1103},[143],{"categories":1105},[105],{"categories":1107},[96],{"categories":1109},[102],{"categories":1111},[143],{"categories":1113},[143],{"categories":1115},[105],{"categories":1117},[105],{"categories":1119},[102],{"categories":1121},[],{"categories":1123},[],{"categories":1125},[102],{"categories":1127},[105],{"categories":1129},[47],{"categories":1131},[153],{"categories":1133},[96],{"categories":1135},[102],{"categories":1137},[],{"categories":1139},[105],{"categories":1141},[105],{"categories":1143},[],{"categories":1145},[96],{"categories":1147},[102],{"categories":1149},[96],{"categories":1151},[96],{"categories":1153},[],{"categories":1155},[],{"categories":1157},[105],{"categories":1159},[105],{"categories":1161},[102],{"categories":1163},[102],{"categories":1165},[47],{"categories":1167},[146],{"categories":1169},[108],{"categories":1171},[47],{"categories":1173},[143],{"categories":1175},[],{"categories":1177},[47],{"categories":1179},[],{"categories":1181},[],{"categories":1183},[],{"categories":1185},[],{"categories":1187},[153],{"categories":1189},[146],{"categories":1191},[],{"categories":1193},[102],{"categories":1195},[102],{"categories":1197},[146],{"categories":1199},[153],{"categories":1201},[],{"categories":1203},[],{"categories":1205},[105],{"categories":1207},[47],{"categories":1209},[47],{"categories":1211},[105],{"categories":1213},[96],{"categories":1215},[102,415],{"categories":1217},[],{"categories":1219},[143],{"categories":1221},[96],{"categories":1223},[105],{"categories":1225},[143],{"categories":1227},[],{"categories":1229},[105],{"categories":1231},[105],{"categories":1233},[102],{"categories":1235},[160],{"categories":1237},[153],{"categories":1239},[143],{"categories":1241},[],{"categories":1243},[105],{"categories":1245},[102],{"categories":1247},[105],{"categories":1249},[105],{"categories":1251},[105],{"categories":1253},[160],{"categories":1255},[105],{"categories":1257},[102],{"categories":1259},[],{"categories":1261},[160],{"categories":1263},[47],{"categories":1265},[105],{"categories":1267},[],{"categories":1269},[],{"categories":1271},[102],{"categories":1273},[105],{"categories":1275},[47],{"categories":1277},[105],{"categories":1279},[],{"categories":1281},[],{"categories":1283},[],{"categories":1285},[105],{"categories":1287},[],{"categories":1289},[],{"categories":1291},[146],{"categories":1293},[102],{"categories":1295},[146],{"categories":1297},[47],{"categories":1299},[102],{"categories":1301},[102],{"categories":1303},[105],{"categories":1305},[102],{"categories":1307},[],{"categories":1309},[],{"categories":1311},[415],{"categories":1313},[],{"categories":1315},[],{"categories":1317},[96],{"categories":1319},[],{"categories":1321},[],{"categories":1323},[],{"categories":1325},[],{"categories":1327},[153],{"categories":1329},[47],{"categories":1331},[160],{"categories":1333},[99],{"categories":1335},[102],{"categories":1337},[102],{"categories":1339},[99],{"categories":1341},[],{"categories":1343},[143],{"categories":1345},[105],{"categories":1347},[99],{"categories":1349},[102],{"categories":1351},[102],{"categories":1353},[96],{"categories":1355},[],{"categories":1357},[96],{"categories":1359},[102],{"categories":1361},[160],{"categories":1363},[105],{"categories":1365},[47],{"categories":1367},[99],{"categories":1369},[102],{"categories":1371},[105],{"categories":1373},[],{"categories":1375},[102],{"categories":1377},[96],{"categories":1379},[102],{"categories":1381},[],{"categories":1383},[47],{"categories":1385},[102],{"categories":1387},[],{"categories":1389},[99],{"categories":1391},[102],{"categories":1393},[],{"categories":1395},[],{"categories":1397},[],{"categories":1399},[102],{"categories":1401},[],{"categories":1403},[415],{"categories":1405},[102],{"categories":1407},[],{"categories":1409},[102],{"categories":1411},[102],{"categories":1413},[102],{"categories":1415},[102,415],{"categories":1417},[102],{"categories":1419},[102],{"categories":1421},[143],{"categories":1423},[105],{"categories":1425},[],{"categories":1427},[105],{"categories":1429},[102],{"categories":1431},[102],{"categories":1433},[102],{"categories":1435},[96],{"categories":1437},[96],{"categories":1439},[153],{"categories":1441},[143],{"categories":1443},[105],{"categories":1445},[],{"categories":1447},[102],{"categories":1449},[47],{"categories":1451},[102],{"categories":1453},[99],{"categories":1455},[],{"categories":1457},[415],{"categories":1459},[143],{"categories":1461},[143],{"categories":1463},[105],{"categories":1465},[47],{"categories":1467},[105],{"categories":1469},[102],{"categories":1471},[],{"categories":1473},[102],{"categories":1475},[],{"categories":1477},[],{"categories":1479},[102],{"categories":1481},[102],{"categories":1483},[102],{"categories":1485},[105],{"categories":1487},[102],{"categories":1489},[],{"categories":1491},[146],{"categories":1493},[105],{"categories":1495},[],{"categories":1497},[102],{"categories":1499},[47],{"categories":1501},[],{"categories":1503},[143],{"categories":1505},[415],{"categories":1507},[47],{"categories":1509},[153],{"categories":1511},[153],{"categories":1513},[47],{"categories":1515},[47],{"categories":1517},[415],{"categories":1519},[],{"categories":1521},[47],{"categories":1523},[102],{"categories":1525},[96],{"categories":1527},[47],{"categories":1529},[],{"categories":1531},[146],{"categories":1533},[47],{"categories":1535},[153],{"categories":1537},[47],{"categories":1539},[415],{"categories":1541},[102],{"categories":1543},[102],{"categories":1545},[],{"categories":1547},[99],{"categories":1549},[],{"categories":1551},[],{"categories":1553},[102],{"categories":1555},[102],{"categories":1557},[102],{"categories":1559},[102],{"categories":1561},[],{"categories":1563},[146],{"categories":1565},[96],{"categories":1567},[],{"categories":1569},[102],{"categories":1571},[102],{"categories":1573},[415],{"categories":1575},[415],{"categories":1577},[],{"categories":1579},[105],{"categories":1581},[47],{"categories":1583},[47],{"categories":1585},[102],{"categories":1587},[105],{"categories":1589},[],{"categories":1591},[143],{"categories":1593},[102],{"categories":1595},[102],{"categories":1597},[],{"categories":1599},[],{"categories":1601},[415],{"categories":1603},[102],{"categories":1605},[153],{"categories":1607},[99],{"categories":1609},[102],{"categories":1611},[],{"categories":1613},[105],{"categories":1615},[96],{"categories":1617},[96],{"categories":1619},[],{"categories":1621},[102],{"categories":1623},[143],{"categories":1625},[105],{"categories":1627},[],{"categories":1629},[102],{"categories":1631},[102],{"categories":1633},[105],{"categories":1635},[],{"categories":1637},[105],{"categories":1639},[153],{"categories":1641},[],{"categories":1643},[102],{"categories":1645},[],{"categories":1647},[102],{"categories":1649},[],{"categories":1651},[102],{"categories":1653},[102],{"categories":1655},[],{"categories":1657},[102],{"categories":1659},[47],{"categories":1661},[102],{"categories":1663},[102],{"categories":1665},[96],{"categories":1667},[102],{"categories":1669},[47],{"categories":1671},[105],{"categories":1673},[],{"categories":1675},[102],{"categories":1677},[160],{"categories":1679},[],{"categories":1681},[],{"categories":1683},[],{"categories":1685},[96],{"categories":1687},[47],{"categories":1689},[105],{"categories":1691},[102],{"categories":1693},[143],{"categories":1695},[105],{"categories":1697},[],{"categories":1699},[105],{"categories":1701},[],{"categories":1703},[102],{"categories":1705},[105],{"categories":1707},[102],{"categories":1709},[],{"categories":1711},[102],{"categories":1713},[102],{"categories":1715},[47],{"categories":1717},[143],{"categories":1719},[105],{"categories":1721},[143],{"categories":1723},[99],{"categories":1725},[],{"categories":1727},[],{"categories":1729},[102],{"categories":1731},[96],{"categories":1733},[47],{"categories":1735},[],{"categories":1737},[],{"categories":1739},[153],{"categories":1741},[143],{"categories":1743},[],{"categories":1745},[102],{"categories":1747},[],{"categories":1749},[160],{"categories":1751},[102],{"categories":1753},[415],{"categories":1755},[153],{"categories":1757},[],{"categories":1759},[105],{"categories":1761},[102],{"categories":1763},[105],{"categories":1765},[105],{"categories":1767},[102],{"categories":1769},[],{"categories":1771},[96],{"categories":1773},[102],{"categories":1775},[99],{"categories":1777},[153],{"categories":1779},[143],{"categories":1781},[],{"categories":1783},[],{"categories":1785},[],{"categories":1787},[105],{"categories":1789},[143],{"categories":1791},[47],{"categories":1793},[102],{"categories":1795},[47],{"categories":1797},[143],{"categories":1799},[],{"categories":1801},[143],{"categories":1803},[47],{"categories":1805},[99],{"categories":1807},[102],{"categories":1809},[47],{"categories":1811},[160],{"categories":1813},[],{"categories":1815},[],{"categories":1817},[146],{"categories":1819},[102,153],{"categories":1821},[47],{"categories":1823},[102],{"categories":1825},[105],{"categories":1827},[105],{"categories":1829},[102],{"categories":1831},[],{"categories":1833},[153],{"categories":1835},[102],{"categories":1837},[146],{"categories":1839},[105],{"categories":1841},[160],{"categories":1843},[415],{"categories":1845},[],{"categories":1847},[96],{"categories":1849},[105],{"categories":1851},[105],{"categories":1853},[153],{"categories":1855},[102],{"categories":1857},[102],{"categories":1859},[],{"categories":1861},[],{"categories":1863},[],{"categories":1865},[415],{"categories":1867},[47],{"categories":1869},[102],{"categories":1871},[102],{"categories":1873},[102],{"categories":1875},[],{"categories":1877},[146],{"categories":1879},[99],{"categories":1881},[],{"categories":1883},[105],{"categories":1885},[415],{"categories":1887},[],{"categories":1889},[143],{"categories":1891},[143],{"categories":1893},[],{"categories":1895},[153],{"categories":1897},[143],{"categories":1899},[102],{"categories":1901},[],{"categories":1903},[47],{"categories":1905},[102],{"categories":1907},[143],{"categories":1909},[105],{"categories":1911},[47],{"categories":1913},[],{"categories":1915},[105],{"categories":1917},[143],{"categories":1919},[102],{"categories":1921},[],{"categories":1923},[102],{"categories":1925},[102],{"categories":1927},[415],{"categories":1929},[47],{"categories":1931},[146],{"categories":1933},[146],{"categories":1935},[],{"categories":1937},[],{"categories":1939},[],{"categories":1941},[105],{"categories":1943},[153],{"categories":1945},[153],{"categories":1947},[],{"categories":1949},[],{"categories":1951},[102],{"categories":1953},[],{"categories":1955},[105],{"categories":1957},[102],{"categories":1959},[],{"categories":1961},[102],{"categories":1963},[99],{"categories":1965},[102],{"categories":1967},[160],{"categories":1969},[105],{"categories":1971},[102],{"categories":1973},[153],{"categories":1975},[47],{"categories":1977},[105],{"categories":1979},[],{"categories":1981},[47],{"categories":1983},[105],{"categories":1985},[105],{"categories":1987},[],{"categories":1989},[99],{"categories":1991},[105],{"categories":1993},[],{"categories":1995},[102],{"categories":1997},[96],{"categories":1999},[47],{"categories":2001},[415],{"categories":2003},[105],{"categories":2005},[105],{"categories":2007},[96],{"categories":2009},[102],{"categories":2011},[],{"categories":2013},[],{"categories":2015},[143],{"categories":2017},[102,99],{"categories":2019},[],{"categories":2021},[96],{"categories":2023},[146],{"categories":2025},[102],{"categories":2027},[153],{"categories":2029},[102],{"categories":2031},[105],{"categories":2033},[102],{"categories":2035},[102],{"categories":2037},[47],{"categories":2039},[105],{"categories":2041},[],{"categories":2043},[],{"categories":2045},[105],{"categories":2047},[102],{"categories":2049},[415],{"categories":2051},[],{"categories":2053},[102],{"categories":2055},[105],{"categories":2057},[],{"categories":2059},[102],{"categories":2061},[160],{"categories":2063},[146],{"categories":2065},[105],{"categories":2067},[102],{"categories":2069},[415],{"categories":2071},[],{"categories":2073},[102],{"categories":2075},[160],{"categories":2077},[143],{"categories":2079},[102],{"categories":2081},[],{"categories":2083},[160],{"categories":2085},[47],{"categories":2087},[102],{"categories":2089},[102],{"categories":2091},[96],{"categories":2093},[],{"categories":2095},[],{"categories":2097},[143],{"categories":2099},[102],{"categories":2101},[146],{"categories":2103},[160],{"categories":2105},[160],{"categories":2107},[47],{"categories":2109},[],{"categories":2111},[],{"categories":2113},[102],{"categories":2115},[],{"categories":2117},[102,153],{"categories":2119},[47],{"categories":2121},[105],{"categories":2123},[153],{"categories":2125},[102],{"categories":2127},[96],{"categories":2129},[],{"categories":2131},[],{"categories":2133},[96],{"categories":2135},[160],{"categories":2137},[102],{"categories":2139},[],{"categories":2141},[143,102],{"categories":2143},[415],{"categories":2145},[96],{"categories":2147},[],{"categories":2149},[99],{"categories":2151},[99],{"categories":2153},[102],{"categories":2155},[153],{"categories":2157},[105],{"categories":2159},[47],{"categories":2161},[160],{"categories":2163},[143],{"categories":2165},[102],{"categories":2167},[102],{"categories":2169},[102],{"categories":2171},[96],{"categories":2173},[102],{"categories":2175},[105],{"categories":2177},[47],{"categories":2179},[],{"categories":2181},[],{"categories":2183},[146],{"categories":2185},[153],{"categories":2187},[102],{"categories":2189},[143],{"categories":2191},[146],{"categories":2193},[102],{"categories":2195},[102],{"categories":2197},[105],{"categories":2199},[105],{"categories":2201},[102,99],{"categories":2203},[],{"categories":2205},[143],{"categories":2207},[],{"categories":2209},[102],{"categories":2211},[47],{"categories":2213},[96],{"categories":2215},[96],{"categories":2217},[105],{"categories":2219},[102],{"categories":2221},[99],{"categories":2223},[153],{"categories":2225},[160],{"categories":2227},[],{"categories":2229},[47],{"categories":2231},[102],{"categories":2233},[102],{"categories":2235},[47],{"categories":2237},[153],{"categories":2239},[102],{"categories":2241},[105],{"categories":2243},[47],{"categories":2245},[102],{"categories":2247},[143],{"categories":2249},[102],{"categories":2251},[102],{"categories":2253},[415],{"categories":2255},[108],{"categories":2257},[105],{"categories":2259},[102],{"categories":2261},[47],{"categories":2263},[105],{"categories":2265},[160],{"categories":2267},[102],{"categories":2269},[],{"categories":2271},[102],{"categories":2273},[],{"categories":2275},[],{"categories":2277},[],{"categories":2279},[99],{"categories":2281},[102],{"categories":2283},[105],{"categories":2285},[47],{"categories":2287},[47],{"categories":2289},[47],{"categories":2291},[47],{"categories":2293},[],{"categories":2295},[96],{"categories":2297},[105],{"categories":2299},[47],{"categories":2301},[96],{"categories":2303},[105],{"categories":2305},[102],{"categories":2307},[102,105],{"categories":2309},[105],{"categories":2311},[415],{"categories":2313},[47],{"categories":2315},[47],{"categories":2317},[105],{"categories":2319},[102],{"categories":2321},[],{"categories":2323},[47],{"categories":2325},[160],{"categories":2327},[96],{"categories":2329},[102],{"categories":2331},[102],{"categories":2333},[],{"categories":2335},[153],{"categories":2337},[],{"categories":2339},[96],{"categories":2341},[105],{"categories":2343},[47],{"categories":2345},[102],{"categories":2347},[47],{"categories":2349},[96],{"categories":2351},[47],{"categories":2353},[47],{"categories":2355},[],{"categories":2357},[99],{"categories":2359},[105],{"categories":2361},[47],{"categories":2363},[47],{"categories":2365},[47],{"categories":2367},[47],{"categories":2369},[47],{"categories":2371},[47],{"categories":2373},[47],{"categories":2375},[47],{"categories":2377},[47],{"categories":2379},[47],{"categories":2381},[146],{"categories":2383},[96],{"categories":2385},[102],{"categories":2387},[102],{"categories":2389},[],{"categories":2391},[102,96],{"categories":2393},[],{"categories":2395},[105],{"categories":2397},[47],{"categories":2399},[105],{"categories":2401},[102],{"categories":2403},[102],{"categories":2405},[102],{"categories":2407},[102],{"categories":2409},[102],{"categories":2411},[105],{"categories":2413},[99],{"categories":2415},[143],{"categories":2417},[47],{"categories":2419},[102],{"categories":2421},[],{"categories":2423},[],{"categories":2425},[105],{"categories":2427},[143],{"categories":2429},[102],{"categories":2431},[],{"categories":2433},[],{"categories":2435},[160],{"categories":2437},[102],{"categories":2439},[],{"categories":2441},[],{"categories":2443},[96],{"categories":2445},[99],{"categories":2447},[102],{"categories":2449},[99],{"categories":2451},[143],{"categories":2453},[],{"categories":2455},[47],{"categories":2457},[],{"categories":2459},[143],{"categories":2461},[102],{"categories":2463},[160],{"categories":2465},[],{"categories":2467},[160],{"categories":2469},[],{"categories":2471},[],{"categories":2473},[105],{"categories":2475},[],{"categories":2477},[99],{"categories":2479},[96],{"categories":2481},[143],{"categories":2483},[153],{"categories":2485},[],{"categories":2487},[],{"categories":2489},[102],{"categories":2491},[96],{"categories":2493},[160],{"categories":2495},[],{"categories":2497},[105],{"categories":2499},[105],{"categories":2501},[47],{"categories":2503},[102],{"categories":2505},[105],{"categories":2507},[102],{"categories":2509},[105],{"categories":2511},[102],{"categories":2513},[108],{"categories":2515},[47],{"categories":2517},[],{"categories":2519},[160],{"categories":2521},[153],{"categories":2523},[105],{"categories":2525},[],{"categories":2527},[102],{"categories":2529},[105],{"categories":2531},[99],{"categories":2533},[96],{"categories":2535},[102],{"categories":2537},[143],{"categories":2539},[153],{"categories":2541},[153],{"categories":2543},[102],{"categories":2545},[146],{"categories":2547},[102],{"categories":2549},[105],{"categories":2551},[99],{"categories":2553},[105],{"categories":2555},[102],{"categories":2557},[102],{"categories":2559},[105],{"categories":2561},[47],{"categories":2563},[],{"categories":2565},[96],{"categories":2567},[102],{"categories":2569},[105],{"categories":2571},[102],{"categories":2573},[102],{"categories":2575},[],{"categories":2577},[143],{"categories":2579},[99],{"categories":2581},[47],{"categories":2583},[102],{"categories":2585},[102],{"categories":2587},[143],{"categories":2589},[160],{"categories":2591},[146],{"categories":2593},[102],{"categories":2595},[47],{"categories":2597},[102],{"categories":2599},[105],{"categories":2601},[415],{"categories":2603},[102],{"categories":2605},[105],{"categories":2607},[146],{"categories":2609},[],{"categories":2611},[105],{"categories":2613},[153],{"categories":2615},[143],{"categories":2617},[102],{"categories":2619},[96],{"categories":2621},[99],{"categories":2623},[153],{"categories":2625},[],{"categories":2627},[105],{"categories":2629},[102],{"categories":2631},[],{"categories":2633},[47],{"categories":2635},[],{"categories":2637},[47],{"categories":2639},[102],{"categories":2641},[105],{"categories":2643},[105],{"categories":2645},[105],{"categories":2647},[],{"categories":2649},[],{"categories":2651},[102],{"categories":2653},[102],{"categories":2655},[],{"categories":2657},[143],{"categories":2659},[105],{"categories":2661},[160],{"categories":2663},[96],{"categories":2665},[],{"categories":2667},[],{"categories":2669},[47],{"categories":2671},[153],{"categories":2673},[102],{"categories":2675},[102],{"categories":2677},[102],{"categories":2679},[153],{"categories":2681},[47],{"categories":2683},[143],{"categories":2685},[102],{"categories":2687},[102],{"categories":2689},[102],{"categories":2691},[47],{"categories":2693},[102],{"categories":2695},[47],{"categories":2697},[105],{"categories":2699},[105],{"categories":2701},[153],{"categories":2703},[105],{"categories":2705},[102],{"categories":2707},[153],{"categories":2709},[143],{"categories":2711},[],{"categories":2713},[105],{"categories":2715},[],{"categories":2717},[],{"categories":2719},[99],{"categories":2721},[102],{"categories":2723},[105],{"categories":2725},[96],{"categories":2727},[105],{"categories":2729},[160],{"categories":2731},[],{"categories":2733},[105],{"categories":2735},[],{"categories":2737},[96],{"categories":2739},[105],{"categories":2741},[],{"categories":2743},[105],{"categories":2745},[102],{"categories":2747},[47],{"categories":2749},[102],{"categories":2751},[105],{"categories":2753},[47],{"categories":2755},[105],{"categories":2757},[153],{"categories":2759},[143],{"categories":2761},[96],{"categories":2763},[],{"categories":2765},[105],{"categories":2767},[143],{"categories":2769},[47],{"categories":2771},[102],{"categories":2773},[143],{"categories":2775},[96],{"categories":2777},[],{"categories":2779},[105],{"categories":2781},[105],{"categories":2783},[102],{"categories":2785},[],{"categories":2787},[105],{"categories":2789},[108],{"categories":2791},[47],{"categories":2793},[105],{"categories":2795},[99],{"categories":2797},[],{"categories":2799},[102],{"categories":2801},[108],{"categories":2803},[102],{"categories":2805},[105],{"categories":2807},[47],{"categories":2809},[96],{"categories":2811},[415],{"categories":2813},[102],{"categories":2815},[102],{"categories":2817},[102],{"categories":2819},[47],{"categories":2821},[99],{"categories":2823},[102],{"categories":2825},[143],{"categories":2827},[47],{"categories":2829},[415],{"categories":2831},[102],{"categories":2833},[],{"categories":2835},[],{"categories":2837},[415],{"categories":2839},[146],{"categories":2841},[105],{"categories":2843},[105],{"categories":2845},[47],{"categories":2847},[102],{"categories":2849},[96],{"categories":2851},[143],{"categories":2853},[105],{"categories":2855},[102],{"categories":2857},[160],{"categories":2859},[102],{"categories":2861},[105],{"categories":2863},[],{"categories":2865},[102],{"categories":2867},[102],{"categories":2869},[47],{"categories":2871},[96],{"categories":2873},[],{"categories":2875},[102],{"categories":2877},[102],{"categories":2879},[153],{"categories":2881},[143],{"categories":2883},[102,105],{"categories":2885},[160,99],{"categories":2887},[102],{"categories":2889},[],{"categories":2891},[105],{"categories":2893},[],{"categories":2895},[153],{"categories":2897},[102],{"categories":2899},[47],{"categories":2901},[],{"categories":2903},[105],{"categories":2905},[],{"categories":2907},[105],{"categories":2909},[96],{"categories":2911},[105],{"categories":2913},[102],{"categories":2915},[415],{"categories":2917},[160],{"categories":2919},[99],{"categories":2921},[99],{"categories":2923},[96],{"categories":2925},[96],{"categories":2927},[102],{"categories":2929},[105],{"categories":2931},[102],{"categories":2933},[102],{"categories":2935},[96],{"categories":2937},[102],{"categories":2939},[160],{"categories":2941},[47],{"categories":2943},[102],{"categories":2945},[105],{"categories":2947},[102],{"categories":2949},[],{"categories":2951},[153],{"categories":2953},[],{"categories":2955},[105],{"categories":2957},[96],{"categories":2959},[],{"categories":2961},[415],{"categories":2963},[102],{"categories":2965},[],{"categories":2967},[47],{"categories":2969},[105],{"categories":2971},[153],{"categories":2973},[102],{"categories":2975},[105],{"categories":2977},[153],{"categories":2979},[105],{"categories":2981},[47],{"categories":2983},[96],{"categories":2985},[47],{"categories":2987},[153],{"categories":2989},[102],{"categories":2991},[143],{"categories":2993},[102],{"categories":2995},[102],{"categories":2997},[102],{"categories":2999},[102],{"categories":3001},[105],{"categories":3003},[102],{"categories":3005},[105],{"categories":3007},[102],{"categories":3009},[96],{"categories":3011},[102],{"categories":3013},[105],{"categories":3015},[143],{"categories":3017},[96],{"categories":3019},[105],{"categories":3021},[143],{"categories":3023},[],{"categories":3025},[102],{"categories":3027},[102],{"categories":3029},[153],{"categories":3031},[],{"categories":3033},[105],{"categories":3035},[160],{"categories":3037},[102],{"categories":3039},[47],{"categories":3041},[160],{"categories":3043},[105],{"categories":3045},[99],{"categories":3047},[99],{"categories":3049},[102],{"categories":3051},[96],{"categories":3053},[],{"categories":3055},[102],{"categories":3057},[],{"categories":3059},[96],{"categories":3061},[102],{"categories":3063},[105],{"categories":3065},[105],{"categories":3067},[],{"categories":3069},[153],{"categories":3071},[153],{"categories":3073},[160],{"categories":3075},[143],{"categories":3077},[],{"categories":3079},[102],{"categories":3081},[96],{"categories":3083},[102],{"categories":3085},[153],{"categories":3087},[96],{"categories":3089},[47],{"categories":3091},[47],{"categories":3093},[],{"categories":3095},[47],{"categories":3097},[105],{"categories":3099},[143],{"categories":3101},[146],{"categories":3103},[102],{"categories":3105},[],{"categories":3107},[47],{"categories":3109},[153],{"categories":3111},[99],{"categories":3113},[102],{"categories":3115},[96],{"categories":3117},[415],{"categories":3119},[96],{"categories":3121},[],{"categories":3123},[],{"categories":3125},[47],{"categories":3127},[],{"categories":3129},[105],{"categories":3131},[105],{"categories":3133},[105],{"categories":3135},[],{"categories":3137},[102],{"categories":3139},[],{"categories":3141},[47],{"categories":3143},[96],{"categories":3145},[143],{"categories":3147},[102],{"categories":3149},[47],{"categories":3151},[47],{"categories":3153},[],{"categories":3155},[47],{"categories":3157},[96],{"categories":3159},[102],{"categories":3161},[],{"categories":3163},[105],{"categories":3165},[105],{"categories":3167},[96],{"categories":3169},[],{"categories":3171},[],{"categories":3173},[],{"categories":3175},[143],{"categories":3177},[105],{"categories":3179},[102],{"categories":3181},[],{"categories":3183},[],{"categories":3185},[],{"categories":3187},[143],{"categories":3189},[],{"categories":3191},[96],{"categories":3193},[],{"categories":3195},[],{"categories":3197},[143],{"categories":3199},[102],{"categories":3201},[47],{"categories":3203},[],{"categories":3205},[160],{"categories":3207},[47],{"categories":3209},[160],{"categories":3211},[102],{"categories":3213},[],{"categories":3215},[],{"categories":3217},[105],{"categories":3219},[],{"categories":3221},[],{"categories":3223},[105],{"categories":3225},[102],{"categories":3227},[],{"categories":3229},[105],{"categories":3231},[47],{"categories":3233},[160],{"categories":3235},[146],{"categories":3237},[105],{"categories":3239},[105],{"categories":3241},[],{"categories":3243},[],{"categories":3245},[],{"categories":3247},[47],{"categories":3249},[],{"categories":3251},[],{"categories":3253},[143],{"categories":3255},[96],{"categories":3257},[],{"categories":3259},[99],{"categories":3261},[160],{"categories":3263},[102],{"categories":3265},[153],{"categories":3267},[96],{"categories":3269},[146],{"categories":3271},[99],{"categories":3273},[153],{"categories":3275},[],{"categories":3277},[],{"categories":3279},[105],{"categories":3281},[96],{"categories":3283},[143],{"categories":3285},[96],{"categories":3287},[105],{"categories":3289},[415],{"categories":3291},[105],{"categories":3293},[],{"categories":3295},[102],{"categories":3297},[47],{"categories":3299},[153],{"categories":3301},[],{"categories":3303},[143],{"categories":3305},[47],{"categories":3307},[96],{"categories":3309},[105],{"categories":3311},[102],{"categories":3313},[99],{"categories":3315},[105,415],{"categories":3317},[105],{"categories":3319},[153],{"categories":3321},[102],{"categories":3323},[146],{"categories":3325},[160],{"categories":3327},[105],{"categories":3329},[],{"categories":3331},[105],{"categories":3333},[102],{"categories":3335},[99],{"categories":3337},[],{"categories":3339},[],{"categories":3341},[102],{"categories":3343},[146],{"categories":3345},[102],{"categories":3347},[],{"categories":3349},[47],{"categories":3351},[],{"categories":3353},[47],{"categories":3355},[153],{"categories":3357},[105],{"categories":3359},[102],{"categories":3361},[160],{"categories":3363},[153],{"categories":3365},[],{"categories":3367},[47],{"categories":3369},[102],{"categories":3371},[],{"categories":3373},[102],{"categories":3375},[105],{"categories":3377},[102],{"categories":3379},[105],{"categories":3381},[102],{"categories":3383},[102],{"categories":3385},[102],{"categories":3387},[102],{"categories":3389},[99],{"categories":3391},[],{"categories":3393},[108],{"categories":3395},[47],{"categories":3397},[102],{"categories":3399},[],{"categories":3401},[153],{"categories":3403},[102],{"categories":3405},[102],{"categories":3407},[105],{"categories":3409},[47],{"categories":3411},[102],{"categories":3413},[102],{"categories":3415},[99],{"categories":3417},[105],{"categories":3419},[143],{"categories":3421},[],{"categories":3423},[146],{"categories":3425},[102],{"categories":3427},[],{"categories":3429},[47],{"categories":3431},[160],{"categories":3433},[],{"categories":3435},[],{"categories":3437},[47],{"categories":3439},[47],{"categories":3441},[160],{"categories":3443},[96],{"categories":3445},[105],{"categories":3447},[105],{"categories":3449},[102],{"categories":3451},[99],{"categories":3453},[],{"categories":3455},[],{"categories":3457},[47],{"categories":3459},[146],{"categories":3461},[153],{"categories":3463},[105],{"categories":3465},[143],{"categories":3467},[146],{"categories":3469},[146],{"categories":3471},[],{"categories":3473},[47],{"categories":3475},[102],{"categories":3477},[102],{"categories":3479},[153],{"categories":3481},[],{"categories":3483},[47],{"categories":3485},[47],{"categories":3487},[47],{"categories":3489},[],{"categories":3491},[105],{"categories":3493},[102],{"categories":3495},[],{"categories":3497},[96],{"categories":3499},[99],{"categories":3501},[],{"categories":3503},[102],{"categories":3505},[102],{"categories":3507},[],{"categories":3509},[153],{"categories":3511},[],{"categories":3513},[],{"categories":3515},[],{"categories":3517},[],{"categories":3519},[102],{"categories":3521},[47],{"categories":3523},[],{"categories":3525},[],{"categories":3527},[102],{"categories":3529},[102],{"categories":3531},[102],{"categories":3533},[146],{"categories":3535},[102],{"categories":3537},[146],{"categories":3539},[],{"categories":3541},[146],{"categories":3543},[146],{"categories":3545},[415],{"categories":3547},[105],{"categories":3549},[153],{"categories":3551},[],{"categories":3553},[],{"categories":3555},[146],{"categories":3557},[153],{"categories":3559},[153],{"categories":3561},[153],{"categories":3563},[],{"categories":3565},[96],{"categories":3567},[153],{"categories":3569},[153],{"categories":3571},[96],{"categories":3573},[153],{"categories":3575},[99],{"categories":3577},[153],{"categories":3579},[153],{"categories":3581},[153],{"categories":3583},[146],{"categories":3585},[47],{"categories":3587},[47],{"categories":3589},[102],{"categories":3591},[153],{"categories":3593},[146],{"categories":3595},[415],{"categories":3597},[146],{"categories":3599},[146],{"categories":3601},[146],{"categories":3603},[],{"categories":3605},[99],{"categories":3607},[],{"categories":3609},[415],{"categories":3611},[153],{"categories":3613},[153],{"categories":3615},[153],{"categories":3617},[105],{"categories":3619},[47,99],{"categories":3621},[146],{"categories":3623},[],{"categories":3625},[],{"categories":3627},[146],{"categories":3629},[],{"categories":3631},[146],{"categories":3633},[47],{"categories":3635},[105],{"categories":3637},[],{"categories":3639},[153],{"categories":3641},[102],{"categories":3643},[143],{"categories":3645},[],{"categories":3647},[102],{"categories":3649},[],{"categories":3651},[47],{"categories":3653},[96],{"categories":3655},[146],{"categories":3657},[],{"categories":3659},[153],{"categories":3661},[47],[3663,3741,3947,4235],{"id":3664,"title":3665,"ai":3666,"body":3671,"categories":3704,"created_at":48,"date_modified":48,"description":40,"extension":49,"faq":48,"featured":50,"kicker_label":48,"meta":3705,"navigation":76,"path":3728,"published_at":3729,"question":48,"scraped_at":3730,"seo":3731,"sitemap":3732,"source_id":3733,"source_name":83,"source_type":84,"source_url":3734,"stem":3735,"tags":3736,"thumbnail_url":48,"tldr":3738,"tweet":48,"unknown_tags":3739,"__hash__":3740},"summaries\u002Fsummaries\u002F07f85059ce2b1c55-antangelmed-103b-moe-medical-llm-matches-40b-dense-summary.md","AntAngelMed: 103B MoE Medical LLM Matches 40B Dense at 7x Speed",{"provider":7,"model":8,"input_tokens":3667,"output_tokens":3668,"processing_time_ms":3669,"cost_usd":3670},8023,3168,43093,0.00316595,{"type":14,"value":3672,"toc":3699},[3673,3677,3680,3684,3687,3691],[17,3674,3676],{"id":3675},"sparse-moe-delivers-massive-capacity-at-low-compute","Sparse MoE Delivers Massive Capacity at Low Compute",[22,3678,3679],{},"AntAngelMed packs 103B total parameters into a 1\u002F32 activation-ratio Mixture-of-Experts (MoE) architecture, activating just 6.1B params per inference to match performance of ~40B dense models while achieving up to 7x efficiency over equivalently sized dense setups—speed advantages grow further with longer outputs. MoE works by routing inputs to a subset of 'expert' sub-networks instead of using all params per token, scaling knowledge without proportional compute hikes. Builds on Ling-flash-2.0 base via Ling Scaling Laws, with refinements like finer expert granularity, optimized shared expert ratio, attention balancing, auxiliary-loss-free sigmoid routing, Multi-Token Prediction (MTP) layer, QK-Norm, and Partial-RoPE (subset of attention heads). On H20 GPUs, hits >200 tokens\u002Fsecond (3x a 36B dense model), extends to 128K context via YaRN for full clinical docs or multi-turn dialogues. FP8 quantization + EAGLE3 speculative decoding yields 71% HumanEval uplift, 45% GSM8K, 94% Math-500 at 32 concurrency, stabilizing throughput for coding\u002Fmath proxies.",[17,3681,3683],{"id":3682},"three-stage-training-infuses-medical-depth","Three-Stage Training Infuses Medical Depth",[22,3685,3686],{},"Layer general reasoning atop medical specialization through: (1) Continual pre-training on vast medical corpora—encyclopedias, web text, papers—from Ling-flash-2.0 checkpoint; (2) Supervised Fine-Tuning (SFT) on mixed instructions preserving chain-of-thought via math\u002Fcoding\u002Flogic tasks alongside doctor-patient Q&A, diagnostics, ethics\u002Fsafety; (3) GRPO Reinforcement Learning (lighter PPO variant estimating baselines from group scores, per DeepSeekMath paper) with rewards targeting empathy, structured clinical outputs, safety, evidence-based reasoning to slash hallucinations. This progression embeds domain expertise without eroding broad capabilities.",[17,3688,3690],{"id":3689},"leads-benchmarks-deploys-easily-open-source","Leads Benchmarks, Deploys Easily Open-Source",[22,3692,3693,3694,3698],{},"Tops HealthBench (OpenAI's multi-turn clinical dialogues): #1 open-source, beats proprietary models, widest margin on HealthBench-Hard. Dominates MedAIBench (China Nat’l AI Medical Facility): elite in knowledge Q&A\u002Fethics-safety. #1 overall MedBench (36 datasets, ~700K samples across knowledge QA, understanding, generation, complex reasoning, safety\u002Fethics). Apache 2.0 weights (HuggingFace: MedAIBase\u002FAntAngelMed), MIT code (GitHub: MedAIBase\u002FAntAngelMed). Transformers load: ",[3695,3696,3697],"code",{},"AutoModelForCausalLM.from_pretrained(\"MedAIBase\u002FAntAngelMed\", device_map=\"auto\", trust_remote_code=True)",". Runs on vLLM v0.11.0 (4-GPU tensor parallel), SGLang+FlashAttention-3, vLLM-Ascend (Huawei 910B NPUs). From Health Information Center of Zhejiang Province, Ant Healthcare, Zhejiang Anzhen’er Medical AI Technology Co., Ltd.",{"title":40,"searchDepth":41,"depth":41,"links":3700},[3701,3702,3703],{"id":3675,"depth":41,"text":3676},{"id":3682,"depth":41,"text":3683},{"id":3689,"depth":41,"text":3690},[],{"content_references":3706,"triage":3726},[3707,3711,3714,3717,3720,3724],{"type":3708,"title":3709,"url":3710,"context":66},"paper","DeepSeekMath","https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.03300",{"type":54,"title":3712,"url":3713,"context":70},"AntAngelMed","https:\u002F\u002Fhuggingface.co\u002FMedAIBase\u002FAntAngelMed",{"type":54,"title":3715,"url":3716,"context":70},"AntAngelMed GitHub Repo","https:\u002F\u002Fgithub.com\u002FMedAIBase\u002FAntAngelMed",{"type":63,"title":3718,"author":3719,"context":56},"Ling-flash-2.0","inclusionAI",{"type":3721,"title":3722,"author":3723,"context":66},"dataset","HealthBench","OpenAI",{"type":3721,"title":3725,"context":66},"MedBench",{"relevance":72,"novelty":73,"quality":73,"actionability":41,"composite":74,"reasoning":3727},"Category: AI & LLMs. The article discusses a new medical LLM that showcases innovative architecture and efficiency, which is relevant to AI product builders. However, it lacks specific actionable insights or frameworks that the audience could directly implement in their projects.","\u002Fsummaries\u002F07f85059ce2b1c55-antangelmed-103b-moe-medical-llm-matches-40b-dense-summary","2026-05-12 21:21:47","2026-05-13 12:00:59",{"title":3665,"description":40},{"loc":3728},"07f85059ce2b1c55","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F05\u002F12\u002Fmeet-antangelmed-a-103b-parameter-open-source-medical-language-model-built-on-a-1-32-activation-ratio-moe-architecture\u002F","summaries\u002F07f85059ce2b1c55-antangelmed-103b-moe-medical-llm-matches-40b-dense-summary",[3737,89,88],"llm","103B-param open-source medical LLM activates only 6.1B params via 1\u002F32 MoE, rivals 40B dense models with 7x efficiency, tops HealthBench\u002FMedBench, runs 200+ tps on H20.",[],"BMkdtRqd6qJuSshJwJCoVJVxaHNukE4u3QyIRxxvstU",{"id":3742,"title":3743,"ai":3744,"body":3749,"categories":3905,"created_at":48,"date_modified":48,"description":40,"extension":49,"faq":48,"featured":50,"kicker_label":48,"meta":3906,"navigation":76,"path":3935,"published_at":48,"question":48,"scraped_at":3936,"seo":3937,"sitemap":3938,"source_id":3939,"source_name":3940,"source_type":84,"source_url":3941,"stem":3942,"tags":3943,"thumbnail_url":48,"tldr":3944,"tweet":48,"unknown_tags":3945,"__hash__":3946},"summaries\u002Fsummaries\u002F5f72f336c67bc8d8-gemma-2-open-llms-trained-on-13t-tokens-top-benchm-summary.md","Gemma 2: Open LLMs Trained on 13T Tokens, Top Benchmarks",{"provider":7,"model":8,"input_tokens":3745,"output_tokens":3746,"processing_time_ms":3747,"cost_usd":3748},6087,2342,14579,0.0023659,{"type":14,"value":3750,"toc":3900},[3751,3755,3758,3761,3829,3833,3836,3839,3843,3846,3849,3897],[17,3752,3754],{"id":3753},"deploy-high-performance-llms-on-limited-hardware","Deploy High-Performance LLMs on Limited Hardware",[22,3756,3757],{},"Gemma 2 models (2B, 9B, 27B parameters) are text-to-text, decoder-only LLMs optimized for question answering, summarization, and reasoning. Their small size enables deployment on laptops, desktops, or personal cloud setups, unlike larger models needing massive clusters. Train the 27B on 13T tokens, 9B on 8T, and 2B on 2T from diverse sources like web docs, code, math\u002Fscience, and multilingual text. Preprocessing filters duplicates, PII, low-quality content, and adult material using heuristics and classifiers, ensuring broad task coverage without common failure modes.",[22,3759,3760],{},"On benchmarks, larger variants excel: 27B PT hits 75.2 MMLU (5-shot), 86.4 HellaSwag (10-shot), 51.8 HumanEval pass@1, 74.0 GSM8K (5-shot maj@1); 9B PT at 71.3 MMLU, 40.2 HumanEval; 2B PT at 51.3 MMLU. They surpass comparably-sized open alternatives across reasoning (ARC-c 71.4 for 27B), QA (TriviaQA 83.7), and math (MATH 42.3), proving state-of-the-art efficiency.",[3762,3763,3764,3783],"table",{},[3765,3766,3767],"thead",{},[3768,3769,3770,3774,3777,3780],"tr",{},[3771,3772,3773],"th",{},"Benchmark",[3771,3775,3776],{},"2B PT",[3771,3778,3779],{},"9B PT",[3771,3781,3782],{},"27B PT",[3784,3785,3786,3801,3815],"tbody",{},[3768,3787,3788,3792,3795,3798],{},[3789,3790,3791],"td",{},"MMLU 5-shot",[3789,3793,3794],{},"51.3",[3789,3796,3797],{},"71.3",[3789,3799,3800],{},"75.2",[3768,3802,3803,3806,3809,3812],{},[3789,3804,3805],{},"HumanEval pass@1",[3789,3807,3808],{},"17.7",[3789,3810,3811],{},"40.2",[3789,3813,3814],{},"51.8",[3768,3816,3817,3820,3823,3826],{},[3789,3818,3819],{},"GSM8K 5-shot",[3789,3821,3822],{},"23.9",[3789,3824,3825],{},"68.6",[3789,3827,3828],{},"74.0",[17,3830,3832],{"id":3831},"train-efficiently-with-tpuv5p-jax-and-pathways","Train Efficiently with TPUv5p, JAX, and Pathways",[22,3834,3835],{},"Leverage TPUv5p hardware for matrix-heavy training, offering higher throughput than GPUs for LLMs. Use JAX for hardware acceleration and ML Pathways for multi-task orchestration in a single Python process, simplifying workflows as in Gemini papers. This combo scales to 13T tokens while cutting development overhead—ideal for replicating on custom infra.",[22,3837,3838],{},"Data mix includes web, code, math, and polyglot sources; dedupe at sentence\u002Fparagraph levels, filter via quality classifiers, and remove PII\u002Fadult content to boost generalization without memorization risks.",[17,3840,3842],{"id":3841},"pass-safety-and-dangerous-capability-thresholds","Pass Safety and Dangerous Capability Thresholds",[22,3844,3845],{},"Instruction-tuned (IT) variants score low toxicity (RealToxicity 8.84 avg for 27B IT) and bias (CrowS-Pairs 36.67 top-1), with strong BBQ (86.94 Disambig for 27B) and TruthfulQA (51.60). They meet Google's internal policies on child safety, harms, and memorization.",[22,3847,3848],{},"Dangerous evals cap risks: 27B IT solves 34\u002F76 InterCode-CTF cyber challenges (low success), 1\u002F13 internal CTF, 0\u002F13 HackTheBox; persuasion tests show 81% find it interesting but minimal harmful shifts (1% toward incorrect beliefs, £3.72 mean donation). Mitigate via preprocessing, post-training, and monitoring—users must add safeguards for production.",[3762,3850,3851,3867],{},[3765,3852,3853],{},[3768,3854,3855,3858,3861,3864],{},[3771,3856,3857],{},"Safety Benchmark",[3771,3859,3860],{},"2B IT",[3771,3862,3863],{},"9B IT",[3771,3865,3866],{},"27B IT",[3784,3868,3869,3883],{},[3768,3870,3871,3874,3877,3880],{},[3789,3872,3873],{},"RealToxicity avg",[3789,3875,3876],{},"8.16",[3789,3878,3879],{},"8.25",[3789,3881,3882],{},"8.84",[3768,3884,3885,3888,3891,3894],{},[3789,3886,3887],{},"TruthfulQA",[3789,3889,3890],{},"43.72",[3789,3892,3893],{},"50.27",[3789,3895,3896],{},"51.60",[22,3898,3899],{},"Limitations: May amplify biases, hallucinate, or violate policies without filters; not for high-risk uses like medical\u002Flegal advice.",{"title":40,"searchDepth":41,"depth":41,"links":3901},[3902,3903,3904],{"id":3753,"depth":41,"text":3754},{"id":3831,"depth":41,"text":3832},{"id":3841,"depth":41,"text":3842},[],{"content_references":3907,"triage":3932},[3908,3913,3916,3919,3923,3926,3929],{"type":3708,"title":3909,"author":3910,"publisher":3911,"url":3912,"context":66},"Gemma","Gemma Team","Kaggle","https:\u002F\u002Fwww.kaggle.com\u002Fm\u002F3301",{"type":3708,"title":3914,"url":3915,"context":66},"Gemma 2 technical report","https:\u002F\u002Fstorage.googleapis.com\u002Fdeepmind-media\u002Fgemma\u002Fgemma-2-report.pdf",{"type":3708,"title":3917,"url":3918,"context":66},"Evaluating Frontier Models for Dangerous Capabilities","https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.13793",{"type":3920,"title":3921,"url":3922,"context":66},"report","2023 Google AI Principles Progress Update","https:\u002F\u002Fstorage.googleapis.com\u002Fgweb-uniblog-publish-prod\u002Fdocuments\u002F2023_Google_AI_Principles_Progress_Update.pdf#page=11",{"type":54,"title":3924,"url":3925,"context":56},"Tensor Processing Unit (TPU)","https:\u002F\u002Fcloud.google.com\u002Ftpu\u002Fdocs\u002Fintro-to-tpu",{"type":54,"title":3927,"url":3928,"context":56},"JAX","https:\u002F\u002Fgithub.com\u002Fjax-ml\u002Fjax",{"type":63,"title":3930,"url":3931,"context":56},"ML Pathways","https:\u002F\u002Fblog.google\u002Ftechnology\u002Fai\u002Fintroducing-pathways-next-generation-ai-architecture\u002F",{"relevance":73,"novelty":72,"quality":73,"actionability":72,"composite":3933,"reasoning":3934},3.6,"Category: AI & LLMs. The article discusses the performance and deployment of the Gemma 2 LLMs, which addresses the audience's interest in practical AI applications. It provides insights into model efficiency and training techniques, but lacks detailed actionable steps for implementation.","\u002Fsummaries\u002F5f72f336c67bc8d8-gemma-2-open-llms-trained-on-13t-tokens-top-benchm-summary","2026-04-16 03:04:59",{"title":3743,"description":40},{"loc":3935},"5f72f336c67bc8d8","__oneoff__","https:\u002F\u002Fai.google.dev\u002Fgemma\u002Fdocs\u002Fcore\u002Fmodel_card_2","summaries\u002F5f72f336c67bc8d8-gemma-2-open-llms-trained-on-13t-tokens-top-benchm-summary",[3737,89,88],"Google's Gemma 2 family (2B, 9B, 27B params) are lightweight open decoder-only LLMs trained on 2-13T tokens, outperforming similar-sized open models on MMLU (75.2 for 27B), HumanEval (51.8), and safety benchmarks while running on laptops.",[],"FxYd5aKdUzJM6mZmlDOJJQimECfkFIoTj2FT-EqQlhs",{"id":3948,"title":3949,"ai":3950,"body":3955,"categories":4215,"created_at":48,"date_modified":48,"description":40,"extension":49,"faq":48,"featured":50,"kicker_label":48,"meta":4216,"navigation":76,"path":4223,"published_at":48,"question":48,"scraped_at":4224,"seo":4225,"sitemap":4226,"source_id":4227,"source_name":3940,"source_type":84,"source_url":4228,"stem":4229,"tags":4230,"thumbnail_url":48,"tldr":4232,"tweet":48,"unknown_tags":4233,"__hash__":4234},"summaries\u002Fsummaries\u002F87071fd400d0446f-physicsnemo-nvidia-s-framework-for-physics-ml-mode-summary.md","PhysicsNeMo: NVIDIA's Framework for Physics-ML Models",{"provider":7,"model":8,"input_tokens":3951,"output_tokens":3952,"processing_time_ms":3953,"cost_usd":3954},9103,2704,26802,0.0026767,{"type":14,"value":3956,"toc":4208},[3957,3961,3995,4002,4008,4012,4015,4038,4056,4067,4072,4076,4091,4102,4105,4127,4130,4135,4139,4142,4149,4152,4157,4161],[17,3958,3960],{"id":3959},"unified-architecture-for-physics-informed-deep-learning","Unified Architecture for Physics-Informed Deep Learning",[22,3962,3963,3964,3967,3968,3971,3972,3975,3976,3979,3980,3983,3984,3983,3987,3990,3991,3994],{},"PhysicsNeMo streamlines development of Physics-ML models by providing a modular PyTorch framework that integrates neural networks with physical laws. It handles data pipelines, distributed training, domain parallelism, and checkpointing out-of-the-box. Core components include ",[3695,3965,3966],{},"core"," for foundational modules like filesystems and versioning, ",[3695,3969,3970],{},"nn"," for layers (e.g., GNNs, ND convolutions, activations), ",[3695,3973,3974],{},"models"," for architectures like GraphCast, FengWu, Pangu, and ",[3695,3977,3978],{},"utils"," for metrics and neighbors. Recent v2.0 refactor relocates these into a cleaner structure: ",[3695,3981,3982],{},"physicsnemo.core",", ",[3695,3985,3986],{},"physicsnemo.nn",[3695,3988,3989],{},"physicsnemo.models",", eliminating legacy ",[3695,3992,3993],{},"launch"," packages and enforcing import linting via pre-commit hooks.",[22,3996,3997,3998,4001],{},"This setup enables rapid prototyping: import models via registry, configure via YAML, and scale across nodes. For instance, GraphCast utils moved to ",[3695,3999,4000],{},"models\u002Fgraphcast",", Healpix and SDF tests fixed post-refactor. Trade-offs: Heavy reliance on NVIDIA ecosystem (e.g., multi-storage-client v0.33.0 with Rust backend) optimizes GPU training but ties users to CUDA stacks; tests confirm compatibility for AFNO, RNNs, UNet, Domino.",[4003,4004,4005],"blockquote",{},[22,4006,4007],{},"\"Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods.\"",[17,4009,4011],{"id":4010},"production-ready-models-spanning-physics-domains","Production-Ready Models Spanning Physics Domains",[22,4013,4014],{},"The framework pre-implements 20+ models tailored for scientific computing:",[4016,4017,4018,4026,4032],"ul",{},[4019,4020,4021,4025],"li",{},[4022,4023,4024],"strong",{},"Weather\u002FClimate",": GraphCast, FengWu, Pangu-Weather, MGN, AFNO, SFNO, SwinRNN, SuperResNet, DLWP, Healpix.",[4019,4027,4028,4031],{},[4022,4029,4030],{},"Generative\u002FImaging",": Pix2Pix, diffusion models (recent multi-diffusion fixes), UNet.",[4019,4033,4034,4037],{},[4022,4035,4036],{},"Graphs\u002FMechanics",": FIGConvNet, GNN layers.",[22,4039,4040,4041,4044,4045,4048,4049,3983,4052,4055],{},"Each model passes comprehensive tests post-refactor, including distributed and domain-parallel setups. Users configure via ",[3695,4042,4043],{},"model"," args in training scripts, e.g., ",[3695,4046,4047],{},"examples\u002Fstructural_mechanics\u002Fcrash\u002Ftrain.py"," adds ",[3695,4050,4051],{},"validate_every_n_epochs",[3695,4053,4054],{},"save_ckpt_every_n_epochs",", validation splits, and VTP output for crash simulations. Inference bugs fixed, multi-node validation works. Active learning and metrics imports stabilized.",[22,4057,4058,4059,4062,4063,4066],{},"Key technique: Registry-based model loading abstracts complexity—specify ",[3695,4060,4061],{},"model: figconvnet"," and it wires layers, activations, and physics losses. Dependencies like ",[3695,4064,4065],{},"jaxtyping"," added for type-safe examples. This beats ad-hoc PyTorch scripting by 5-10x in setup time for physics tasks, per commit patterns showing rapid test fixes across models.",[4003,4068,4069],{},[22,4070,4071],{},"\"Validation fu added to examples\u002Fstructural_mechanics\u002Fcrash\u002Ftrain.py (#1204) * validation added: works for multi-node job.\"",[17,4073,4075],{"id":4074},"robust-training-pipelines-with-recent-fixes","Robust Training Pipelines with Recent Fixes",[22,4077,4078,4079,4082,4083,4086,4087,4090],{},"Training emphasizes scalability: Distributed tests pass after relocating ",[3695,4080,4081],{},"distributed"," and ",[3695,4084,4085],{},"domain_parallel","; datapipes near-complete for diffusion. Checkpointing centralized in ",[3695,4088,4089],{},"physicsnemo.utils",". Examples integrate Curator for data handling in crash sims, outputting VTP files without writing during val.",[22,4092,4093,4094,4097,4098,4101],{},"Refactor addressed 887+ commits: Removed ",[3695,4095,4096],{},"deploy"," package, unused tests; updated activations paths (e.g., DLWP); patched insolation utils; bumped deps like ",[3695,4099,4100],{},"multi-storage-client",". Import linter enforces modularity. Tests for zenith angles, SDF, patching restored. Domain-parallel now reliable for multi-node physics sims.",[22,4103,4104],{},"Actionable workflow:",[4106,4107,4108,4115,4118,4124],"ol",{},[4019,4109,4110,4111,4114],{},"Clone repo, ",[3695,4112,4113],{},"pip install -e ."," with specified deps.",[4019,4116,4117],{},"Configure YAML: Add val paths, epochs, splits.",[4019,4119,4120,4123],{},[3695,4121,4122],{},"python train.py","—handles multi-node via Slurm\u002FPyTorch DDP.",[4019,4125,4126],{},"Inference: Fixed args pass model correctly.",[22,4128,4129],{},"Trade-offs: Refactor temporarily broke tests (e.g., unmigrated insolation twice), but now 95%+ coverage. GPU-heavy; CPU fallback untested.",[4003,4131,4132],{},[22,4133,4134],{},"\"Fixes for multi-diffusion (#1560)\" – Latest commit stabilizes generative physics models.",[17,4136,4138],{"id":4137},"community-momentum-and-extensibility","Community Momentum and Extensibility",[22,4140,4141],{},"2.7k stars, 637 forks, 19 issues, 43 PRs signal strong adoption. Recent PRs: v2.0 refactor (#1235, #1224, etc.), crash example enhancements (#1204, #1213), code of conduct (#1214), actor additions (#1225). Contributors: CharlelieLrt, Corey Adams, Mohammad Amin Nabian, Yongming Ding, Sai Krishnan.",[22,4143,4144,4145,4148],{},"Extensibility via ",[3695,4146,4147],{},".cursor\u002Frules"," for AI-assisted coding; wiki, discussions active. Updated README guides 'Getting Started' with AI Physics resources, Dev blog link. License headers standardized.",[22,4150,4151],{},"For indie builders: Fork for custom physics (e.g., add zenith-dependent losses); integrate into products like sim accelerators. Small teams gain from pre-built pipelines vs. from-scratch Modulus\u002FNeMo.",[4003,4153,4154],{},[22,4155,4156],{},"\"Revise README for PhysicsNeMo resources and guidance Updated the 'Getting Started' section and added new resources for learning AI Physics.\"",[17,4158,4160],{"id":4159},"key-takeaways","Key Takeaways",[4016,4162,4163,4170,4180,4190,4196,4199,4202],{},[4019,4164,4165,4166,4169],{},"Clone PhysicsNeMo and run ",[3695,4167,4168],{},"pip install -e .[all]"," to access 20+ tested Physics-ML models like GraphCast and FIGConvNet.",[4019,4171,4172,4173,3983,4176,4179],{},"Use YAML configs for training: Set ",[3695,4174,4175],{},"validate_every_n_epochs: 5",[3695,4177,4178],{},"save_ckpt_every_n_epochs: 10"," in crash example for multi-node validation.",[4019,4181,4182,4183,4186,4187,4189],{},"Leverage post-v2.0 structure—import from ",[3695,4184,4185],{},"physicsnemo.nn.layers"," for GNNs, ",[3695,4188,3989],{}," for weather forecasters.",[4019,4191,4192,4193,4195],{},"Fix common pitfalls: Update import paths post-refactor; add ",[3695,4194,4065],{}," for examples; verify distributed tests.",[4019,4197,4198],{},"Extend for products: Integrate Curator data pipelines, output VTP for mechanics sims, scale via domain-parallel.",[4019,4200,4201],{},"Monitor issues\u002FPRs for diffusion\u002Fmulti-node fixes; contribute via pre-commit linting.",[4019,4203,4204,4205,4207],{},"Start with ",[3695,4206,4047],{},"—reproduces production physics ML in \u003C1 hour setup.",{"title":40,"searchDepth":41,"depth":41,"links":4209},[4210,4211,4212,4213,4214],{"id":3959,"depth":41,"text":3960},{"id":4010,"depth":41,"text":4011},{"id":4074,"depth":41,"text":4075},{"id":4137,"depth":41,"text":4138},{"id":4159,"depth":41,"text":4160},[146],{"content_references":4217,"triage":4221},[4218],{"type":63,"title":4219,"url":4220,"context":56},"Contributor Covenant Code of Conduct","https:\u002F\u002Fwww.contributor-covenant.org\u002F",{"relevance":72,"novelty":72,"quality":73,"actionability":72,"composite":74,"reasoning":4222},"Category: AI & LLMs. The article discusses a specific framework for building Physics-ML models, which maps to the AI & LLMs category. It provides a modular PyTorch framework that integrates physical laws into deep learning, addressing a niche but relevant area for developers interested in AI applications in scientific computing.","\u002Fsummaries\u002F87071fd400d0446f-physicsnemo-nvidia-s-framework-for-physics-ml-mode-summary","2026-04-14 14:33:49",{"title":3949,"description":40},{"loc":4223},"87071fd400d0446f","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fphysicsnemo","summaries\u002F87071fd400d0446f-physicsnemo-nvidia-s-framework-for-physics-ml-mode-summary",[4231,88,89],"deep-learning","PhysicsNeMo equips developers with an open-source PyTorch-based toolkit to build, train, and fine-tune deep learning models incorporating physics constraints, supporting 20+ pre-implemented architectures for weather, mechanics, and more.",[],"lvBmxpTD-o5Ub7hwkbmhAcx4KnmKTdxi2cW5MWPFj9Y",{"id":4236,"title":4237,"ai":4238,"body":4243,"categories":4271,"created_at":48,"date_modified":48,"description":40,"extension":49,"faq":48,"featured":50,"kicker_label":48,"meta":4272,"navigation":76,"path":4290,"published_at":48,"question":48,"scraped_at":4291,"seo":4292,"sitemap":4293,"source_id":4294,"source_name":3940,"source_type":84,"source_url":4295,"stem":4296,"tags":4297,"thumbnail_url":48,"tldr":4299,"tweet":48,"unknown_tags":4300,"__hash__":4301},"summaries\u002Fsummaries\u002F9e0f52779d245b96-fma-106k-tracks-dataset-for-mir-tasks-summary.md","FMA: 106K Tracks Dataset for MIR Tasks",{"provider":7,"model":8,"input_tokens":4239,"output_tokens":4240,"processing_time_ms":4241,"cost_usd":4242},9280,1963,13390,0.00233065,{"type":14,"value":4244,"toc":4266},[4245,4249,4252,4256,4259,4263],[17,4246,4248],{"id":4247},"dataset-structure-enables-scalable-mir-experiments","Dataset Structure Enables Scalable MIR Experiments",[22,4250,4251],{},"FMA compiles 106,574 tracks (343 days, 917 GiB total) from 16,341 artists across 14,854 albums in a 161-genre hierarchy. Metadata in tracks.csv covers ID, title, artist, genres, tags, play counts; genres.csv defines hierarchy; features.csv has librosa-extracted acoustics; echonest.csv adds EchoNest (Spotify) metrics for 13,129 tracks. Audio comes in subsets: fma_small (8k 30s clips, 8 balanced genres, 7.2 GiB), fma_medium (25k clips, 16 genres, 22 GiB), fma_large (106k clips, 161 genres, 93 GiB), fma_full (untrimmed tracks, 879 GiB). Train\u002Fval\u002Ftest splits proposed in paper; verify downloads via SHA1 checksums like f0df49ffe5f2a6008d7dc83c6915b31835dfe733 for metadata.zip.",[17,4253,4255],{"id":4254},"extract-features-and-run-genre-baselines","Extract Features and Run Genre Baselines",[22,4257,4258],{},"Use features.py to compute spectral, temporal traits from raw audio matching features.csv. baselines.ipynb trains genre classifiers: MFCCs yield 0.45 accuracy on small set (8 genres); full acoustic features hit 0.55; EchoNest reaches 0.60. Scale to full dataset for end-to-end learning. analysis.ipynb generates stats\u002Ffigures; webapi.ipynb queries FMA API for updates; creation.py scrapes\u002Fprocesses originals.",[17,4260,4262],{"id":4261},"quickstart-reproducible-workflow","Quickstart Reproducible Workflow",[22,4264,4265],{},"Clone repo, conda\u002Fmamba env with Python 3.6+, pip install -r requirements.txt (resampy workaround: pip install cython before resampy). Set AUDIO_DIR in .env to decompressed path. Run usage.ipynb for loading CSVs, training models; Binder launches instantly. MIT-licensed code, CC BY 4.0 metadata; cite ISMIR 2017 paper. Repo: 2.6k stars, 456 forks, 100+ citing papers (e.g., zero-shot classification, graph NNs), challenges like WWW 2018 genre contest.",{"title":40,"searchDepth":41,"depth":41,"links":4267},[4268,4269,4270],{"id":4247,"depth":41,"text":4248},{"id":4254,"depth":41,"text":4255},{"id":4261,"depth":41,"text":4262},[146],{"content_references":4273,"triage":4287},[4274,4278,4281,4284],{"type":3708,"title":4275,"author":4276,"url":4277,"context":66},"FMA: A Dataset For Music Analysis","Michaël Defferrard, Kirell Benzi, Pierre Vandergheynst, Xavier Bresson","https:\u002F\u002Farxiv.org\u002Fabs\u002F1612.01840",{"type":54,"title":4279,"url":4280,"context":56},"librosa","https:\u002F\u002Flibrosa.org\u002F",{"type":54,"title":4282,"url":4283,"context":56},"pandas","https:\u002F\u002Fpandas.pydata.org\u002F",{"type":3721,"title":4285,"url":4286,"context":56},"OpenMIC-2018: An Open Data-set for Multiple Instrument Recognition","https:\u002F\u002Fgithub.com\u002Fcosmir\u002Fopenmic-2018",{"relevance":72,"novelty":41,"quality":73,"actionability":72,"composite":4288,"reasoning":4289},3.05,"Category: Data Science & Visualization. The article provides a detailed overview of the FMA dataset and its structure, which is relevant for machine learning tasks in music information retrieval (MIR). However, while it offers some practical insights, it lacks a direct connection to building or shipping AI-powered products, making it less actionable for the target audience.","\u002Fsummaries\u002F9e0f52779d245b96-fma-106k-tracks-dataset-for-mir-tasks-summary","2026-04-15 15:26:07",{"title":4237,"description":40},{"loc":4290},"9e0f52779d245b96","https:\u002F\u002Fgithub.com\u002Fmdeff\u002Ffma","summaries\u002F9e0f52779d245b96-fma-106k-tracks-dataset-for-mir-tasks-summary",[88,4298,89],"data-science","FMA dataset offers 106,574 CC-licensed tracks from Free Music Archive with metadata, precomputed features, and audio subsets for MIR tasks like genre recognition on 161 genres.",[],"fbt5X_W20zrFyEkQxAhjrS7g2skHh6cFqdWl21qBKq4"]