Optimizar modelos de razonamiento como Deepseek con optimización inmediata en Amazon Bedrock

Modelos Deepseek-R1, ahora disponible en Mercado de roca en Amazon, Amazon Sagemaker Jumpstartasí como un modelo sin servidor en Roca madre de Amazonse popularizaron recientemente por su largo y elaborado estilo de pensamiento, que, según los resultados publicados de Deepseek, condujo a un rendimiento impresionante en puntos de referencia de matemáticas altamente desafiantes como AIME-2024 y Math-500, así como un rendimiento competitivo en comparación con los modelos de vanguardia como el Claude Sonnet 3.5, GPT 4O y OpenAi O1 (más detalles en esto de este arte. papel).

Durante la capacitación, los investigadores mostraron cómo Deepseek-R1-Zero aprende naturalmente a resolver tareas con más tiempo de pensamiento, lo que lleva a un impulso en el rendimiento. Sin embargo, lo que a menudo se ignora es la cantidad de tokens de pensamiento requeridos en el momento de la inferencia, y el tiempo y el costo de generar estos tokens antes de responder la pregunta original.

En esta publicación, demostramos cómo optimizar modelos de razonamiento como Deepseek-R1 utilizando una optimización inmediata en Amazon Bedrock.

Largas cadenas de razonamiento y desafíos con límites de token máximos

Probemos una pregunta directa sobre Deepseek-R1:

Para el problema matemático dado: el perro de Nate puede cavar seis hoyos al día. Cava durante 14 días mientras Nate está de vacaciones. Cuando Nate llega a casa, comienza a llenar 9 hoyos al día, pero el perro sigue cavando 6 nuevos agujeros todas las noches. ¿Cuántas semanas le lleva completar todos los agujeros?, Escriba los pasos que tomaría para resolverlo.

En el patio de chat/texto de Amazon Bedrock, puede seguir eligiendo el nuevo modelo Deepseek-R1, como se muestra en la siguiente captura de pantalla.

Puede ver que a veces, en función de la pregunta, los modelos de razonamiento no terminan de pensar dentro del presupuesto general de token máximo.

El aumento del presupuesto de token de salida permite que el modelo piense por más tiempo. Con los tokens máximos aumentados de 2.048 a 4,096, debe ver el razonamiento del modelo durante un tiempo antes de imprimir la respuesta final.

El apéndice al final de esta publicación proporciona la respuesta completa. También puede colapsar los pasos de razonamiento para ver solo la respuesta final.

Como podemos ver en el caso con el presupuesto de 2,048 token, el proceso de pensamiento no terminó. Esto no solo nos costó 2,048 tokens de tiempo y dinero, ¡sino que tampoco obtuvimos la respuesta final! Esta observación de los tokens altos para pensar generalmente conduce a algunas preguntas de seguimiento, como:

  • ¿Es posible reducir las fichas de pensamiento y aún así obtener una respuesta correcta?
  • ¿Se puede restringir el pensamiento a un número máximo de tokens de pensamiento o un presupuesto de pensamiento?
  • En un alto nivel, ¿deberían usarse modelos intensivos como Deepseek en aplicaciones en tiempo real?

En esta publicación, le mostramos cómo puede optimizar modelos de pensamiento como Deepseek-R1 utilizando una optimización rápida en Amazon Bedrock, lo que resulta en trazas de pensamiento más sucintas sin sacrificar la precisión.

Optimizar las indicaciones de Deepseek-R1

Para comenzar con la optimización rápida, seleccione Deepseek-R1 en el patio de recreo del modelo en Amazon Bedrock, ingrese su aviso y elija el icono de la varita mágica, o use el lecho de roca de Amazon optimize_prompt() API. También puede utilizar la optimización de inmediato en la consola, agregar variables si es necesario, establecer su modelo en parámetros Deepseek-R1 y modelo, y haga clic en “Optimizar”:

Para demostrar cómo la optimización rápida en Amazon Bedrock puede ayudar con los modelos de razonamiento, primero necesitamos un conjunto de datos desafiante. El último examen de Humanity (HLE), un punto de referencia de preguntas extremadamente desafiantes de docenas de áreas temáticas, está diseñado para ser el punto de referencia cerrado “final” de las amplias capacidades académicas. HLE es multimodal, con preguntas que son solo de texto o acompañadas de una referencia de imagen, e incluye preguntas de opción múltiple y de combate exacto para la verificación de respuestas automatizadas. Las preguntas requieren un profundo conocimiento del dominio en varias verticales; Son inequívocos y resistentes a las búsquedas simples de Internet o la recuperación de la base de datos. Para el contexto, varios modelos de vanguardia (incluidos los modelos de pensamiento) funcionan mal en el punto de referencia (consulte la tabla de resultados en esto papel completo).

Veamos una pregunta de ejemplo de este conjunto de datos:

In an alternate universe where the mass of the electron was 1% heavier and the charges of the
electron and proton were both 1% smaller, but all other fundamental constants stayed the same, 
approximately how would the speed of sound in diamond change? 

Answer Choices:
A. Decrease by 2%
B. Decrease by 1.5%
C. Decrease by 1%
D. Decrease by 0.5%
E. Stay approximately the same 
F. Increase by 0.5%
G. Increase by 1%
H. Increase by 1.5%
I. Increase by 2%

La pregunta requiere una comprensión profunda de la física, que la mayoría de los modelos de idiomas grandes (LLM) hoy fallarán. Nuestro objetivo con una optimización rápida en Amazon Bedrock para modelos de razonamiento es reducir la cantidad de tokens pensantes pero no la precisión del sacrificio. Después de usar la optimización rápida, el aviso optimizado es el siguiente:

## Question
<extracted_question_1>In an alternate universe where the mass of the electron was 1% heavier 
and the charges of the electron and proton were both 1% smaller, but all other fundamental constants
stayed the same, approximately how would the speed of sound in diamond change?

Answer Choices:
A. Decrease by 2%
B. Decrease by 1.5%
C. Decrease by 1%
D. Decrease by 0.5%
E. Stay approximately the same
F. Increase by 0.5%
G. Increase by 1%
H. Increase by 1.5%
I. Increase by 2%</extracted_question_1>

## Instruction
Read the question above carefully and provide the most accurate answer possible.
If multiple choice options are provided within the question, respond with the entire text of the
correct answer option, not just the letter or number. Do not include any additional explanations or
preamble in your response.

Remember, your goal is to answer as precisely and accurately as possible!

La siguiente figura muestra cómo, para este caso específico, el número de tokens de pensamiento se redujo en un 35%, al tiempo que obtiene la respuesta final correcta (B. disminuye en un 1,5%). Aquí, el número de tokens de pensamiento se redujo de 5,000 a 3,300. También notamos que en este y otros ejemplos con las indicaciones originales, parte del razonamiento se resume o se repite antes de la respuesta final. Como podemos ver en este ejemplo, el aviso optimizado proporciona instrucciones claras, separa diferentes secciones de solicitud y proporciona orientación adicional basada en el tipo de pregunta y cómo responder. Esto conduce a rastros de razonamiento más cortos y claros y una respuesta final directamente extraíble.

Las indicaciones optimizadas también pueden conducir a respuestas correctas en lugar de las incorrectas después del pensamiento de forma larga, porque pensar no garantiza una respuesta final correcta. En este caso, vemos que el número de tokens de pensamiento se redujo de 5,000 a 1,555, y la respuesta se obtiene directamente, en lugar de otra explicación larga y posterior al pensamiento. La siguiente figura muestra un ejemplo.

Los dos ejemplos anteriores demuestran formas en que la optimización rápida puede mejorar los resultados al tiempo que acorta los tokens de salida para modelos como Deepseek R1. La optimización rápida también se aplicó a 400 preguntas de HLE. La siguiente tabla resume los resultados.

Experimento Precisión general Número promedio de tokens rápidos Número promedio de tokens de finalización
(Pensamiento + respuesta)
Número promedio de tokens (respuesta
Solo)
Número promedio de tokens (solo pensando) Porcentaje de pensamiento completado
(6,000 token de salida máximo)
Baseline DeepSeek 8.75 288 3334 271 3063 80.0%
Información de profundidad optimizada 11 326 1925 27 1898 90.3%

Como podemos ver, la precisión general aumenta al 11% en este subconjunto del conjunto de datos HLE, el número de tokens de pensamiento y salida se reduce (por lo tanto, reduce el tiempo para el último token y costo), y la tasa de completar el pensamiento aumentó al 90% en general. A partir de nuestros experimentos, vemos que, aunque no hay una referencia explícita para reducir los tokens de pensamiento, las instrucciones más claras y detalladas sobre la tarea en cuestión después de la optimización rápida podrían reducir el esfuerzo adicional involucrado para modelos como Deepseek-R1 para hacer una auto-clarificación o una comprensión de problemas más profundo. La optimización rápida para los modelos de razonamiento asegura que la calidad del pensamiento y el flujo general, que es autoadaptativo y depende de la pregunta, no se vea afectada en gran medida, lo que lleva a mejores respuestas finales.

Conclusión

En esta publicación, demostramos cómo la optimización rápida en Amazon Bedrock puede mejorar efectivamente el rendimiento de los modelos intensivos en pensamiento como Deepseek-R1. A través de nuestros experimentos con el conjunto de datos HLE, mostramos que las indicaciones optimizadas no solo redujeron el número de tokens de pensamiento en un margen significativo, sino que también mejoraron la precisión general de 8.75% a 11%. La optimización resultó en caminos de razonamiento más eficientes sin sacrificar la calidad de las respuestas, lo que llevó a tiempos de respuesta más rápidos y costos más bajos. Esta mejora tanto en la eficiencia como en la efectividad sugiere que la optimización rápida puede ser una herramienta valiosa para implementar modelos pesados ​​de razonamiento en entornos de producción donde la precisión y los recursos computacionales deben equilibrarse cuidadosamente. A medida que el campo de la IA continúa evolucionando con modelos de pensamiento más sofisticados, las técnicas como la optimización rápida serán cada vez más importantes para aplicaciones prácticas.

Para comenzar con la rápida optimización en Amazon Bedrock, consulte Optimizar un aviso y Mejorar el rendimiento de sus aplicaciones de IA generativas con una optimización rápida en Amazon Bedrock.

Apéndice

La siguiente es la respuesta completa de la pregunta sobre el perro de Nate:


Okay, let's see. So the problem is about Nate's dog digging holes and Nate trying to fill them.
I need to figure out how many weeks it takes Nate to fill all the holes once he starts. Let me break
it down step by step.\n\nFirst, the dog digs 6 holes a day. He does this for 14 days while Nate is on
vacation. So when Nate comes back, there are a certain number of holes already dug. Let me calculate
that first. If the dog digs 6 holes each day for 14 days, that's 6 multiplied by 14. Let me do that
math: 6*14=84. So there are 84 holes when Nate gets home.\n\nNow, once Nate starts filling the holes,
he fills 9 holes per day. But here's the catch: the dog keeps digging 6 new holes every night. So 
each day, Nate fills 9 holes, but the dog adds 6 more overnight. I need to figure out the net change
per day. That would be the number of holes filled minus the new holes dug. So 9 filled - 6 dug = 3 
holes net reduction per day. Wait, but does this happen every day? Let me make sure.\n\nSo Nate works
during the day, filling 9 holes. Then, during the night, the dog digs 6 new holes. So each full day
(day and night) results in a net decrease of 3 holes. So starting from 84 holes, each day the total
number decreases by 3. But I need to check if the process is that Nate fills 9, then the dog digs 6,
so the next day starts with 84 -9 +6 = 84 -3 =81, and so on. So yes, each day the net is -3.\n\nBut
wait, maybe the timing is important. Let's think: when Nate starts filling, does he fill 9 holes on
the first day, and then the dog digs 6 that night? So each day after Nate fills, the dog adds 6. So
the sequence is: Day 1: Nate fills 9, holes become 84-9=75. Then night: dog digs 6, holes become
75+6=81. Day 2: Nate fills 9, holes 81-9=72. Night: +6=78. So each full day cycle (day and night)
reduces the total by 3. So yes, net 3 per day.\n\nBut wait, maybe on the last day, if Nate fills the
remaining holes and the dog doesn't get to dig that night because all holes are filled. Hmm, that's a
crucial point. For example, if on a certain day, the number of holes left is less than or equal to 9,
Nate can fill them all in that day, and the dog doesn't add any more because there are no holes left
to dig. So we need to check if on the day when Nate fills the remaining holes, the total would reach
zero, and the dog doesn't dig that night. So we can't just do total holes divided by 3, because the
last day might not have the dog digging.\n\nSo let's model this properly. Let's denote the number of
holes each day.\n\nStarting with 84 holes.\n\nEach day:\n\n1. Nate fills 9 holes. Subtract 9.\n\n2.
If the result is zero or negative, then done.\n\n3. Otherwise, the dog digs 6 holes. Add 6.\n\nSo we
need to iterate this until the number of holes is zero or less after Nate fills them.\n\nLet me try
to calculate day by day.\n\nStart: 84\n\nDay 1:\n\nAfter Nate fills: 84 -9 =75\n\nSince 75 >0, dog
digs 6: 75 +6=81\n\nDay 2:\n\nAfter Nate fills:81-9=72\n\nDog digs 6:72+6=78\n\nDay3:\n\n78-
9=69\n\n+6=75\n\nDay4:75-9=66+6=72\n\nDay5:72-9=63+6=69\n\nDay6:69-9=60+6=66\n\nDay7:66-
9=57+6=63\n\nDay8:63-9=54+6=60\n\nDay9:60-9=51+6=57\n\nDay10:57-9=48+6=54\n\nDay11:54-
9=45+6=51\n\nDay12:51-9=42+6=48\n\nDay13:48-9=39+6=45\n\nDay14:45-9=36+6=42\n\nDay15:42-
9=33+6=39\n\nDay16:39-9=30+6=36\n\nDay17:36-9=27+6=33\n\nDay18:33-9=24+6=30\n\nDay19:30-
9=21+6=27\n\nDay20:27-9=18+6=24\n\nDay21:24-9=15+6=21\n\nDay22:21-9=12+6=18\n\nDay23:18-
9=9+6=15\n\nDay24:15-9=6+6=12\n\nDay25:12-9=3+6=9\n\nDay26:9-9=0\n\nAt this point, after Nate fills
on day26, the holes are 0. Since there are no holes left, the dog can't dig any more that night. So
the process stops here.\n\nSo total days:26 days.\n\nBut the question asks for how many weeks. Since
a week is 7 days, we divide 26 by7.\n\n26 divided by7 is 3 with a remainder of5. So 3 weeks and5
days. But the question says \"how many weeks does it take him to fill in all the holes\". Depending
on whether they want it rounded up to full weeks or expressed as a fraction. Let me check the problem
statement again.\n\n\"How many weeks does it take him to fill in all the holes?\"\n\nTypically, such
problems expect the answer in whole weeks, rounded up if there's a remainder. Because you can't have
a fraction of a week in practical terms. So 26 days is 3 weeks and5 days, which is more than3 weeks
but less than4. So they might expect 4 weeks. But let me verify.\n\nAlternatively, maybe they want
the exact number in weeks as a fraction. 26 days is 26/7 weeks \u22483.714 weeks. But the problem
might expect an integer number of weeks, rounded up. Let's see.\n\nBut let's check the problem again.
It says \"how many weeks does it take him to fill in all the holes?\" So if it takes 26 days, which
is 3 weeks and5 days, then the answer would be 4 weeks if we're counting full weeks needed. Because
after 3 weeks (21 days), he still has 5 days left. So total weeks is4.\n\nBut maybe the answer is
26/7 weeks, which is approximately3.714, but since the problem might expect an exact answer in weeks,
possibly as a fraction. However, the problem might be designed to have a whole number. Wait, let's
check the math again.\n\nWait, when I did the day-by-day count, I got 26 days. Let me recount to make
sure I didn't make a mistake.\n\nStarting from day1 to day26. Let's check day26:\n\nStart with
day1:84\n\nAfter day1:81\n\n...\n\nLet me check day25:\n\nAfter day24:12\n\nDay25:12-9=3, then dog
digs6:3+6=9\n\nDay26:9-9=0. So day26 is the day when Nate fills the last 9 holes. So yes, 26
days.\n\n26 days divided by7 days/week=3.714... weeks. So the answer is 26/7 weeks, which is3 and5/7
weeks. But the problem might want it expressed as a mixed number or an exact number. However, the
question says \"how many weeks does it take him\", so likely they expect the answer in weeks,
possibly as a fraction. But let's see if there's a better way to model this without counting each
day.\n\nAlternative approach:\n\nTotal holes after vacation:84\n\nEach day, Nate fills9, dog digs6,
net -3 per day, except possibly the last day.\n\nBut if on the last day, Nate fills the remaining
holes without the dog digging, then we need to adjust.\n\nLet\u2019s model it as:\n\nLet H be the
number of holes. Start with H=84.\n\nEach day, H decreases by9, then if H>0, increases by6.\n\nWe
need to find the number of days until H<=0.\n\nThis can be modeled as:\n\nEach full cycle (day and
night) reduces H by3, except the last day where if H<=9, then H becomes0 and no addition.\n\nSo
the number of full cycles (days where H>9 after filling) plus the final day.\n\nLet\u2019s
denote:\n\nLet\u2019s say after n days, the holes would be:\n\nEach day, H = H -9 +6 = H -3, but only
if after subtracting9, H >=1 (since if H-9 <=0, then the dog doesn\u2019t dig). Wait, no. Wait,
the dog digs6 only if after Nate fills9, there are still holes left. Wait, no. Wait, the problem says
the dog keeps digging6 new holes every night. So regardless of whether there are holes left, the dog
digs6 every night. Wait, but if all holes are filled, can the dog dig new ones? The problem says
\"fill in all the holes\", so once all holes are filled, the dog can't dig new ones because there are
no existing holes? Wait, the problem might be implying that the dog digs new holes regardless, but
Nate is filling the existing ones. Wait, the problem says \"the dog keeps digging6 new holes every
night\". So perhaps every night, regardless of the current state, the dog digs6 new holes. But that
would mean that even if Nate fills all holes on a day, the dog digs6 new ones that night, making it
impossible to ever finish. But that can't be, because the problem asks how long to fill all holes,
which implies that eventually Nate can catch up.\n\nWait, this is a critical point. Let me re-examine
the problem statement:\n\n\"When Nate gets home, he starts filling in 9 holes a day, but the dog
keeps digging 6 new holes every night. How many weeks does it take him to fill in all the holes?
\"\n\nSo the key is: every night, the dog digs6 new holes. So even if Nate fills all the holes during
the day, the dog will dig6 new ones that night. But that would mean the process never ends. But the
problem must assume that once all holes are filled, the dog stops. But the wording is ambiguous.
However, logically, if all holes are filled, there's nothing for the dog to dig. So perhaps the dog
only digs6 holes if there's ground to dig, but the problem states \"keeps digging6 new holes every
night\", implying that regardless of the current state, the dog digs6 each night. This is a problem
because if Nate ever fills all holes, the next night the dog digs6, so Nate would have to fill those6
the next day, but then the dog digs6 again, leading to an infinite loop. But the problem must have a
solution, so likely the dog stops digging once all holes are filled. Therefore, the correct
interpretation is that each night, the dog digs6 new holes, but if there are no holes (i.e., all
filled), the dog can't dig. Therefore, the last day when Nate fills the remaining holes, the dog
doesn't dig that night.\n\nTherefore, the correct model is:\n\nEach day:\n\n1. Nate fills9
holes.\n\n2. If holes remain after filling, the dog digs6 that night.\n\nSo the process is:\n\nStart
with H=84.\n\nWhile H>0:\n\n H = H -9\n\n if H >0:\n\n H = H +6\n\n days +=1\n\nSo let's model
this with equations.\n\nLet\u2019s find the number of days required.\n\nThis is similar to the
classic problem where each day you have a net change, but with a different condition on the last
day.\n\nLet\u2019s denote that each \"cycle\" (day and night) reduces H by3, except possibly the last
day where H <=9, so after filling, H becomes0, and no addition.\n\nSo the total number of days is
the number of full cycles (each reducing H by3) plus the final day.\n\nBut how to calculate this?
\n\nLet\u2019s think of it as:\n\nLet\u2019s suppose that after n days, the number of holes is H_n
=84 -3n.\n\nBut this is only true if every day the net change is -3. However, this would be the case
until H_n -9 <=0. Wait, no. Wait, the H after filling is H -9. If H -9 <=0, then the dog
doesn't dig, so the total reduction is H (to 0). So we need to find the day when H -9 <=0.\n\nSo
let\u2019s solve for when H -9 <=0:\n\nH =84 -3(n-1) -9 <=0\n\nWait, this is getting
complicated. Let me use another approach.\n\nLet\u2019s consider that each day before the final day,
the net change is -3. On the final day, the net change is -9 (since the dog doesn\u2019t add
6).\n\nLet\u2019s let x be the number of full days (with net -3), and 1 final day (net -9).\n\nTotal
reduction: 3x +9 =84\n\nSo 3x =84 -9=75\n\nx=75/3=25\n\nSo x=25 days of net -3, and 1 final day of 
-9.\n\nTotal days=25+1=26 days.\n\nYes, this matches the day-by-day count. Therefore, 26 
days.\n\nConvert to weeks:26/7=3.714... weeks. But the problem asks \"how many weeks does it take
him\". If they want a whole number of weeks, rounded up, it's4 weeks. If they accept fractions,
it's26/7\u22483.714. But the problem might expect the answer in weeks as a mixed number, like3 and5/7
weeks. However, typically, such problems expect the answer in whole weeks, rounded up. Let me check
the problem statement again.\n\nThe problem says \"how many weeks does it take him to fill in all the
holes\". The answer should be in weeks, and since it's more than3 weeks but less than4, but you can't
have a fraction of a week in practical terms when scheduling, so they might expect4 weeks. However,
mathematically, it's26/7 weeks. Let me see if the problem expects an exact answer or a whole 
number.\n\nLooking back at the problem statement, it's a math problem, so likely expects the exact
value, which is26/7 weeks, which can be written as3 5/7 weeks. However, sometimes problems like this
expect the answer in whole weeks, rounding up. Let's check both possibilities.\n\nIf the answer is26
days, which is3 weeks and5 days, then depending on the context:\n\n- If partial weeks count as a full
week, then4 weeks.\n\n- If exact, then3 5/7 weeks.\n\nBut the problem doesn't specify, so as a math
problem, the precise answer is26/7 weeks, which is3 and5/7 weeks. However, the question might want it
in weeks as a whole number, rounded up. Let's see.\n\nBut let's check the problem again. The problem
says \"how many weeks does it take him to fill in all the holes?\" The answer choices (if any) aren't
given, but since the user hasn't provided options, we need to infer. In math problems like this,
unless specified otherwise, the answer is expected in the most precise form, which would be26/7 weeks
or3 5/7 weeks. However, sometimes problems expect whole numbers, so maybe the answer is4 weeks. But
let's verify with the day count.\n\n26 days is exactly3 weeks and5 days. If the question asks for the
number of weeks, and if part of a week counts as a full week, then it's4. But if they want the exact
number, it's3 5/7. However, the problem might have an integer answer. Wait, let's check the
calculations again.\n\nWait, when I did the day-by-day count, I got26 days. Let me verify that again
quickly.\n\nStart with84.\n\nEach day:\n\n1. Subtract9.\n\n2. If result >0, add6.\n\nRepeat until
H<=0.\n\nLet\u2019s model this with a formula.\n\nLet\u2019s denote that each day, except the
last, the net change is -3. The last day is -9.\n\nSo total holes =84 =3x +9\n\nSo3x=75 \u2192x=25
days of net -3, plus1 day of -9. Total26 days.\n\nYes, that's correct. So26 days.\n\n26 days divided
by7 days/week=3.714... weeks.\n\nBut the problem might want the answer as a mixed number, so3 and5/7
weeks. However, in some contexts, especially in school problems, they might expect the answer in
whole weeks, rounded up, so4 weeks. But since the problem is from Nate's perspective, he would count
the exact days, so converting26 days to weeks gives3 weeks and5 days. But the question asks for
weeks, so unless specified, it's better to present it as26/7 weeks, which is3 5/7 weeks. However,
let's check if there's a different approach that gives a whole number.\n\nAlternatively, maybe I made
a mistake in the day count. Let me recount the days more carefully.\n\nStarting with84
holes.\n\nDay1:\n\nFill9:84-9=75. Since75>0, dog digs6:75+6=81.\n\nDay2:\n\n81-9=72>0
\u2192+6=78.\n\nDay3:78-9=69>0 \u2192+6=75.\n\nDay4:75-9=66>0 \u2192+6=72.\n\nDay5:72-9=63>0
\u2192+6=69.\n\nDay6:69-9=60>0 \u2192+6=66.\n\nDay7:66-9=57>0 \u2192+6=63.\n\nDay8:63-9=54>0
\u2192+6=60.\n\nDay9:60-9=51>0 \u2192+6=57.\n\nDay10:57-9=48>0 \u2192+6=54.\n\nDay11:54-
9=45>0 \u2192+6=51.\n\nDay12:51-9=42>0 \u2192+6=48.\n\nDay13:48-9=39>0 
\u2192+6=45.\n\nDay14:45-9=36>0 \u2192+6=42.\n\nDay15:42-9=33>0 \u2192+6=39.\n\nDay16:39-
9=30>0 \u2192+6=36.\n\nDay17:36-9="


Sobre los autores

Shreyas subramaniano es un científico principal de datos y ayuda a los clientes mediante el uso de IA generativa y el aprendizaje profundo para resolver sus desafíos comerciales utilizando los servicios de AWS. Shreyas tiene antecedentes en la optimización a gran escala y ML y en el uso de ML y el aprendizaje de refuerzo para acelerar las tareas de optimización.

Zhengyuan shen es un científico aplicado en Amazon Bedrock, especializado en modelos fundamentales y modelado de ML para tareas complejas que incluyen lenguaje natural y comprensión de datos estructurados. Le apasiona aprovechar soluciones innovadoras de ML para mejorar los productos o servicios, simplificando así la vida de los clientes a través de una combinación perfecta de ciencia e ingeniería. El trabajo externo, disfruta del deporte y la cocina.

Xuan Qi es una científica aplicada en Amazon Bedrock, donde aplica sus antecedentes en física para enfrentar desafíos complejos en el aprendizaje automático y la inteligencia artificial. A Xuan le apasiona traducir conceptos científicos en aplicaciones prácticas que impulsen mejoras tangibles en la tecnología. Su trabajo se centra en crear sistemas de IA más intuitivos y eficientes que puedan comprender e interactuar mejor con el mundo. Fuera de sus actividades profesionales, Xuan encuentra equilibrio y creatividad a través de su amor por bailar y interpretar el violín, trayendo la precisión y la armonía de estas artes a sus esfuerzos científicos.

Shuai Wang Es un científico y gerente aplicados en Amazon Bedrock, especializado en procedimientos de lenguaje natural, aprendizaje automático, modelado de idiomas grandes y otras áreas de IA relacionadas.