Today, we’re excited to announce that the جما این مدل اکنون برای مشتریانی که استفاده می کنند در دسترس است Amazon SageMaker JumpStart. Gemma is a family of مدل های زبان based on Google’s Gemini models, trained on up to 6 trillion tokens of text. The Gemma family consists of two sizes: a 7 billion parameter model and a 2 billion parameter model. Now, you can use Gemma 2B and Gemma 7B pretrained and instruction-tuned models within SageMaker JumpStart. JumpStart مرکز یادگیری ماشینی (ML) SageMaker است که علاوه بر الگوریتمهای داخلی و الگوهای راهحل انتها به انتها، به مدلهای پایه دسترسی دارد تا به شما کمک کند تا به سرعت با ML شروع کنید.
In this post, we walk through how to deploy the Gemma model and fine tune it for your use cases in SageMaker JumpStart. The complete notebook is available on GitHub.
Gemma model
جما is a family of lightweight, state-of-the-art مدل built from the same research and technology used to create the برج جوزا models. Developed by Google DeepMind and other teams across Google, Gemma is inspired by Gemini. Gemma exhibits strong generalist capabilities in text domains and state-of-the-art understanding and reasoning skills at scale. It achieves better performance compared to other publicly available models of similar or larger scales across different domains, including question answering, commonsense reasoning, mathematics and science, and coding. Gemma released the model weights to support developer innovation using Gemma models. Gemma was launched with a new جعبه ابزار هوش مصنوعی مولد مسئول that provides guidance and essential tools for creating safer AI applications with Gemma.
مدل های پایه در SageMaker
JumpStart دسترسی به طیف وسیعی از مدلها را از هابهای مدل محبوب از جمله Hugging Face، PyTorch Hub، و TensorFlow Hub فراهم میکند، که میتوانید در گردش کار توسعه ML خود در SageMaker استفاده کنید. پیشرفتهای اخیر در ML منجر به پیدایش دسته جدیدی از مدلها شده است که به آنها میگویند مدل های پایه، که معمولاً بر روی میلیاردها پارامتر آموزش داده می شوند و با دسته بندی گسترده ای از موارد استفاده مانند خلاصه سازی متن، تولید هنر دیجیتال و ترجمه زبان سازگار هستند. از آنجایی که آموزش این مدلها گران است، مشتریان میخواهند به جای آموزش این مدلها، از مدلهای پایه از پیش آموزشدیده موجود استفاده کنند و در صورت نیاز آنها را تنظیم کنند. SageMaker لیستی از مدلهایی را ارائه میکند که میتوانید از میان آنها در کنسول SageMaker انتخاب کنید.
You can now find foundation models from different model providers within JumpStart, enabling you to get started with foundation models quickly. You can find foundation models based on different tasks or model providers, and review model characteristics and usage terms. You can also try these models using a test UI widget. When you want to use a foundation model at scale, you can do so without leaving SageMaker by using pre-built notebooks from model providers. Because the models are hosted and deployed on AWS, your data, whether used for evaluating the model or using it at scale, is never shared with third parties.
Let’s explore how you can use the Llama Guard model in JumpStart.
Explore the Gemma model in Jumpstart
You can access Gemma foundation models through SageMaker JumpStart in the SageMaker Studio UI and the SageMaker Python SDK. In this section, we go over how to discover the models in SageMaker Studio.
SageMaker Studio is an integrated development environment (IDE) that provides a single web-based visual interface where you can access purpose-built tools to perform all ML development steps, from preparing data to building, training, and deploying your ML models. For more details on how to get started and set up SageMaker Studio, see Amazon SageMaker Studio.
In the AWS Management Console for SageMaker Studio, go to SageMaker JumpStart under راه حل های از پیش ساخته شده و خودکار. Jumpstart contains pre-trained models, notebooks, and prebuilt solutions.
On the SageMaker JumpStart landing page, you can find the Gemma model by searching for Gemma.
You can then select from a variety of Gemma model variants, including Gemma 2B, Gemma 7B, Gemma 2B instruct, and Gemma 7B instruct.
Choose the model card to view details about the model such as the license, data used to train, and how to use the model. You will also find a گسترش button, which takes you to a landing page where you can test inference with an example payload.
Deploy Gemma with SageMaker Python SDK
You can find the code showing the deployment of Gemma on JumpStart and an example of how to use the deployed model in this GitHub notebook.
Start by selecting the SageMaker Model Hub model ID and model version to use when deploying Gemma.
Choose a model ID from the following table, which details the default configuration options for the JumpStart deployment. Because of the large vocabulary size of 256 thousand tokens, Gemma 7B can only fit on a single A10G GPU when supporting a 1 thousand context length. For this reason, JumpStart uses a larger default instance for Gemma 7B.
شناسه مدل | Default inference instance | Tensor parallel degree | Supported context Length |
huggingface-llm-gemma-2b | ml.g5.xlarge | 1 | 8k |
huggingface-llm-gemma-2b-instruct | ml.g5.xlarge | 1 | 8k |
huggingface-llm-gemma-7b | ml.g5.12xlarge | 4 | 8k |
huggingface-llm-gemma-7b-instruct | ml.g5.12xlarge | 4 | 8k |
You can now deploy the model using SageMaker JumpStart. The following code uses the default instance ml.g5.12xlarge
for the inference endpoint You can deploy the model on other instance types by passing instance_type
در JumpStartModel
class. The deployment might take 5-10 minutes.
For successful deployment, you must manually change the accept_eula
آرگومان در روش استقرار مدل به True
. This model is deployed using the text-generation-inference (TGI) deep learning container.
Invoke endpoint
You can programmatically retrieve example payloads from the JumpStartModel
object. This will help you get started by observing pre-formatted instruction prompts that Gemma can ingest.
Before we look at specific prompts, let’s consider the chat template for Gemma Instruct models.
Here, you place your prompt in the [USER_PROMPT]
location. There’s no support for a system instruction; instead, you can prepend the desired instruction to the user prompt. Additionally, if you have a multi-turn conversation, then the model prompt can alternate between user and assistant as needed.
Now consider a few instruction example prompts. Here, you ask Gemma to write a Hello World program.
The following is the expected output:
Next, invoke Gemma for the creative task of writing a poem.
خروجی زیر است:
This looks pretty good!
Now, let’s look at latency and throughput performance benchmarking for model serving with the default JumpStart deployment configuration. Here, we show how model performance might differ for your typical endpoint workload. In the following tables, you can observe that small-sized queries (256 input words and 256 output tokens) are quite performant under a large number of concurrent users, reaching token throughput on the order of one thousand to two thousand tokens per second. However, as the number of input words approaches Gemma’s maximum supported context length of eight thousand tokens, the endpoint saturates its batching capacity—the number of concurrent requests allowed to be processed simultaneously—due to instance memory-bound constraints.
For more information on how to consider this information and adjust deployment configurations for your specific use case, see Benchmark and optimize endpoint deployment in Amazon SageMaker JumpStart.
. | Throughput (tokens/s) | ||||||||||
کاربران همزمان | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128 | |||
مدل | نوع نمونه | کلمات ورودی | Output tokens | . | . | . | . | . | . | . | . |
gemma-2b-instruct | ml.g5.xlarge | 256 | 256 | 73 | 137 | 262 | 486 | 829 | 1330 | 1849 | 1834 |
2048 | 256 | 69 | 126 | 227 | 373 | 537 | 704 | 764 | - | ||
7936 | 256 | 60 | 100 | 147 | 195 | 226 | 230 | - | - | ||
gemma-7b-instruct | ml.g5.12xlarge | 256 | 256 | 62 | 119 | 227 | 413 | 601 | 811 | 937 | 962 |
2048 | 256 | 56 | 100 | 172 | 245 | 267 | 273 | - | - | ||
7936 | 256 | 44 | 67 | 77 | 77 | 78 | - | - | - |
. | P50 latency (ms/token) | ||||||||||
کاربران همزمان | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128 | |||
مدل | نوع نمونه | کلمات ورودی | Output tokens | . | . | . | . | . | . | . | . |
gemma-2b-instruct | ml.g5.xlarge | 256 | 256 | 13 | 14 | 15 | 16 | 19 | 23 | 33 | 49 |
2048 | 256 | 14 | 15 | 17 | 20 | 28 | 43 | 79 | - | ||
7936 | 256 | 16 | 19 | 26 | 39 | 68 | 136 | - | - | ||
Gemma-7b-instruct | ml.g5.12xlarge | 256 | 256 | 16 | 16 | 17 | 19 | 26 | 38 | 57 | 110 |
2048 | 256 | 17 | 19 | 23 | 32 | 52 | 119 | - | - | ||
7936 | 256 | 22 | 29 | 45 | 105 | 197 | - | - | - |
Fine-tune Gemma using SageMaker Python SDK
Next, we show you how to fine-tune the Gemma 7B instruct model on a conversational-formatted dataset using QLoRA technique. As mentioned previously, due to the large vocabulary size of 256 thousand and the 8 thousand context length, JumpStart offers the following default configurations for QLoRA fine-tuning.
شناسه مدل | Default training instance | Maximum input sequence length | Per device training batch size | Gradient accumulation steps |
huggingface-llm-gemma-2b | ml.g5.2xlarge | 1024 | 1 | 4 |
huggingface-llm-gemma-2b-instruct | ml.g5.2xlarge | 1024 | 1 | 4 |
huggingface-llm-gemma-7b | ml.g5.12xlarge | 2048 | 1 | 4 |
huggingface-llm-gemma-7b-instruct | ml.g5.12xlarge | 2048 | 1 | 4 |
Let’s load and process the dataset in conversational format. The example dataset for this demonstration is OpenAssistant’s TOP-1 Conversation Threads.
The training data should be formulated in JSON lines (.jsonl
) format, where each line is a dictionary representing a set of conversations. One example within the JSON lines file is shown below. For details on how to process the dataset, see the notebook in GitHub.
Underlying the training scripts, JumpStart uses HuggingFace SFTTrainer با QLoRA و فلش توجه. Flash Attention enables scaling efficiency, leading to faster training and inference. Besides chat-based fine-tuning, JumpStart also supports instruction and domain adaptation fine-tuning with QLoRA. For details, see the notebook in GitHub.
After the fine-tuning, you can deploy the fine-tuned model to a SageMaker endpoint.
You can choose to deploy the model fine-tuned on conversation data in SageMaker endpoint with HuggingFace messages API feature as an alternative approach. The benefit of using Message API feature is that it allow users to pass the query examples in raw format as shown in the following table and chat_template within the endpoint will convert the query examples into the proper format before sending them into the model. For details, see the deployment section after fine-tuning in the دفتر یادداشت.
After deploying the fine-tuned model in an endpoint, you can compare output responses from pre-trained and fine-tuned Gemma models. The examples are collected from test data, which is a hold-out set from the training data. The inference parameters are max_tokens
به عنوان 512، top_p
به عنوان 0.9، temperature
به عنوان 0.4، و top_k
به عنوان 50.
As you can see with the fine tuning results, the agent answers are more accurate.
To further evaluate your fine tuned models, you may explore FM evaluation with Amazon SageMaker Clarify to see how your fine tuned model performs in comparison to base model.
ورودی ها | حقیقت زمینی | پاسخ از پایه مدل | پاسخ از مدل دقیق تنظیم شده | |
1 |
User: I want to work on my vocabulary, can you give me some simple ways that I can find new words to use to increase the diversity of my sentences? Assistant: Certainly! Improving your vocabulary is an ongoing process, but here are some simple ways to find new words and increase the diversity of your sentences: 1. Read widely: Reading books, articles, and blogs from different genres and subjects exposes you to new words and phrases. Note down any unfamiliar words you encounter and look up their meanings. 2. Use a thesaurus: Whenever you write or read, use a thesaurus to find synonyms for commonly used words. This not only helps you learn new words but also enhances your understanding of their subtle differences in meaning. 3. Word-a-day calendars or apps: Subscribe to a word-a-day email or download a vocabulary-building app. These tools introduce you to a new word each day, along with its meaning, pronunciation, and usage examples. 4. Join a book club or discussion group: Engaging in conversations and discussions about books, articles, or any other topic exposes you to different perspectives and new vocabulary. Listen attentively to others and try using new words in context. 5. Play word games: Games like Scrabble, Boggle, and crossword puzzles challenge your vocabulary skills and help you learn new words in an enjoyable way. 6. Watch movies, TV shows, or documentaries: Visual media often use diverse language, slang, and jargon. Watching movies, TV shows, or documentaries with subtitles can help you better understand and remember new words. 7. Practice writing: Regularly writing stories, essays, or journal entries encourages you to use new words and phrases. Experiment with different writing styles and genres to expand your vocabulary. 8. Learn a new word’s etymology: Understanding the origin and history of a word can make it easier to remember and use correctly. Researching the etymology also exposes you to related words and concepts. 9. Use flashcards or spaced repetition software: Create flashcards with new words, their meanings, and example sentences. Review them regularly or use spaced repetition software like Anki to optimize your learning. 10. Set personal goals: Set achievable targets, such as learning five new words per week. Keep track of your progress and reward yourself for meeting your goals. By consistently incorporating these strategies into your daily routine, you’ll gradually build a diverse and robust vocabulary. User: Hm, i really like the idea of reading. Can you recomend me a cool science-fiction thriller which i could read? |
Assistant: Certainly! Here are a few recommendations for science-fiction thrillers that you might enjoy: 1. “The Three-Body Problem” by Liu Cixin – This award-winning novel explores the first contact between humanity and an alien civilization, and the political and personal ramifications that result. It’s a gripping and thought-provoking read that delves into deep questions about the nature of existence and the universe. 2. “Annihilation” by Jeff Vandermeer – This novel follows a group of scientists as they venture into a mysterious area known as “Area X,” where they encounter strange and unsettling phenomena. As they delve deeper into the area, they begin to uncover dark secrets about the nature of reality and the world around them. 3. “Dark Matter” by Blake Crouch – This novel follows a brilliant physicist named Jason Dessen, who is abducted and transported to a parallel universe. As he tries to find his way back to his own reality, he must confront his own choices and the consequences of his actions. 4. “The Andromeda Strain” by Michael Crichton – This classic novel follows a team of scientists as they try to contain and study a deadly extraterrestrial microbe that has landed on Earth. As they race against time to find a way to neutralize the microbe, they must also contend with political intrigue and personal conflicts. 5. “Ready Player One” by Ernest Cline – This novel is set in a dystopian future where the majority of the population spends their time in a virtual reality world known as the OASIS. When the creator of the OASIS dies and leaves behind a challenge to find a hidden Easter egg, a young protagonist sets out on a thrilling quest that will change his life forever. I hope one of these recommendations sparks your interest! |
Assistant: The text does not contain information about your reading preferences or interests, therefore I cannot provide a book recommendation. |
Assistant: Sure, here are a few science-fiction thriller recommendations that you might enjoy: – “Dune” by Frank Herbert: This epic sci-fi novel is set on the desert planet of Arrakis, where a young prince named Paul Atreides must face the challenges of a hostile environment and a treacherous political landscape. – “The Martian” by Andy Weir: This gripping sci-fi thriller follows the story of Mark Watney, an astronaut stranded on Mars after a dust storm, as he uses his ingenuity and resourcefulness to survive and eventually make his way back to Earth. – “The Time Machine” by H.G. Wells: This classic sci-fi novel takes a philosophical approach to the concept of time travel, exploring the consequences of altering the past and the future. – “The Blade Runner” by Philip K. Dick: This neo-noir sci-fi novel, set in a futuristic Los Angeles, explores the intersection of human and artificial intelligence, and its influence on society and the nature of reality. – “The Androids” by Isaac Asimov: This sci-fi novel explores the concept of artificial intelligence and its potential consequences, particularly when humans develop advanced androids that challenge traditional human values and beliefs. These are just a few suggestions, and ultimately the best book for you will depend on your personal preferences and what kind of experience you’re looking for in a sci-fi thriller. But I hope these recommendations give you a good starting point for exploring the genre. Please let me know if you have any further questions or if there’s anything I can help you with. |
2 |
User: Write a Hello World program in VB.NET Assistant: Here you go: “`vbnet User: Make it take input from the $ and then say “Hello, $” instead of “Hello, World!” |
Assistant: Public Module HelloWorld Public Sub Main() System.Console.WriteLine(“What is your name?”) Dim name As String = System.Console.ReadLine() System.Console.WriteLine(“Hello, ” & name & “!”) پایان دادن به زیر ماژول پایان |
Assistant: “`vbnet Public Module HelloWorld Public Sub Main() Dim name As String = Console.ReadLine() Console.WriteLine(“Hello, ” & name) پایان دادن به زیر ماژول پایان |
Assistant: Sure! Here is an example: “`vbnet |
3 |
User: Give me a list of to do items when starting a project to train a large language model that can understanding and respond to human questions Assistant: The following steps are a condensed list of steps to take when starting a project to train a large language model capable of comprehending and responding to human inquiries: 1. Establish project scope and objectives, target audience. This should give you a basic idea of what the required steps are. Should I go into more detail on one of the points? User: These tasks need to be broken down further, could you please provide an updated to-do list with a more detailed breakdown of the tasks ahead |
Assistant: Here is a more detailed breakdown of each step: 1. Establish project scope and objectives: It is important to clearly define the goals of the project and what the target audience is. This will help you make decisions about what type of data to gather and what model architecture is appropriate. 2. Gather and preprocess data: This is an important step as the quality and diversity of the data will directly impact the performance of the model. Preprocessing may involve cleaning the data, tokenizing text, and converting words to numerical representations. 3. Select model architecture: There are many different types of models to choose from, including recurrent neural networks (RNNs), transformer models, and convolutional neural networks (CNNs). The choice will depend on the specific requirements of the project and the amount of data available. 4. Divide dataset and implement data augmentation: Splitting the data into training, validation, and testing subsets is important for monitoring the performance of the model during training. Data augmentation can be used to artificially increase the size of the dataset and improve the robustness of the model. 5. Train model and monitor progress: This step involves training the model on the training data, using the validation set to monitor progress and adjust hyperparameters as needed. It may be necessary to repeat this process several times until the model is performing well on the validation set. 6. Evaluate model on test set: Once the model is trained, it’s important to evaluate its performance on a separate test set to get an idea of its generalization ability. This can be done by comparing the model’s predictions to the actual outcomes and analyzing the errors. 7. Fine-tune for specific tasks or domains: This step involves further training the model on task-specific data to improve its performance for a particular domain. This can be done through transfer learning, where a pre-trained model is fine-tuned on new data, or through fine-tuning, where the model is trained from scratch on the new data. 8. Create an interface for user input: This involves designing an interface that allows users to input questions or requests, and receive responses from the model. 9. Test in controlled environment: Before deploying the model in a real-world setting, it’s important to test it in a controlled environment and gather feedback from users. This will help identify any errors or biases in the model and provide opportunities for improvement. 10. Continuously monitor and improve performance: Finally, it is important to continuously monitor the performance of the model and make updates and improvements as needed. This may involve retraining the model on new data, fine-tuning hyperparameters, or updating the architecture. |
Assistant: ## To-Do List for Training a Large Language Model for Question Answering **1. Project Scope & Objectives:** * Define project goals and desired functionalities. **2. Data Acquisition & Preprocessing:** * Identify sources for training data and gather a diverse text dataset. **3. Model Selection & Configuration:** * Select an appropriate model architecture based on the task complexity and desired performance. **4. Training & Evaluation:** * Divide the training data into training, validation, and testing subsets. **5. Fine-Tuning & Interface Development:** * Fine-tune the model for specific tasks or domains through transfer learning. **6. Testing & Improvement:** * Test the model in a controlled environment with various input scenarios. **Additional Considerations:** * Set a timeline and budget for the project. **Note:** This list is not exhaustive and may need to be adapted based on the specific project requirements. |
Assistant: Sure, here is a more detailed breakdown of the tasks involved in training a large language model to understand and respond to human questions: **1. Establish Project Scope and Objectives** **2. Gather and Preprocess a Comprehensive/Diverse Text Dataset** **3. Select an Appropriate Model Architecture, Adjust Hyperparameters for Accuracy/Speed** **4. Divide Dataset into Training, Validation, Testing Subsets, Implement Data Augmentation** **5. Train Model, Monitor Progress on Validation Set, Adjust as Needed** **6. Evaluate Model on Test Set, Compare to Benchmarks, Analyze Errors and Biases** **7. Fine-Tune for Specific Tasks or Domains Through Transfer Learning or Fine-Tuning** **8. Create Interface for User Input and Model Response** **9. Test in Controlled Environment, Gather Feedback for Improvement** **10. Continuously Monitor and Improve Performance Through Retraining and Fine-Tuning** These are the steps involved in training a large language model to understand and respond to human questions. Please let me know if you have question. |
پاک کردن
After you have tested the endpoints, delete the SageMaker inference endpoints and the model to avoid incurring charges.
نتیجه
In this post, we showed you how to get started with Gemma in SageMaker Studio and deploy the model for inference. We also showed you how you can fine tune Gemma models on SageMaker Jumpstart.
Because foundation models are pre-trained, they can help lower training and infrastructure costs and enable customization for your use case. Visit SageMaker JumpStart in SageMaker Studio now to get started.
این راهنما فقط برای مقاصد اطلاعاتی است. شما همچنان باید ارزیابی مستقل خود را انجام دهید و اقداماتی را انجام دهید تا اطمینان حاصل شود که از رویهها و استانداردهای کنترل کیفیت خاص خود، و قوانین، قوانین، مقررات، مجوزها و شرایط استفاده محلی که در مورد شما، محتوای شما، و مدل شخص ثالث که در این راهنما به آن اشاره شده است. AWS هیچ کنترل یا اختیاری بر مدل شخص ثالث اشاره شده در این راهنما ندارد، و هیچ گونه تضمین یا تضمینی مبنی بر ایمن، عاری از ویروس، عملیاتی بودن مدل شخص ثالث، یا سازگار با محیط تولید و استانداردهای شما ارائه نمی کند. AWS هیچ گونه اظهارنظر، ضمانت یا تضمینی مبنی بر اینکه هر گونه اطلاعات موجود در این راهنما به نتیجه یا نتیجه خاصی منجر شود، ارائه نمی کند.
درباره نویسندگان
دکتر کایل اولریش دانشمند کاربردی با الگوریتم های داخلی آمازون SageMaker تیم علایق تحقیقاتی او شامل الگوریتم های یادگیری ماشین مقیاس پذیر، بینایی کامپیوتر، سری های زمانی، ناپارامتریک های بیزی و فرآیندهای گاوسی است. دکترای او از دانشگاه دوک است و مقالاتی در NeurIPS، Cell و Neuron منتشر کرده است.
دکتر شین هوانگ یک دانشمند کاربردی ارشد برای آمازون SageMaker JumpStart و آمازون SageMaker الگوریتم های داخلی است. او بر توسعه الگوریتمهای یادگیری ماشینی مقیاسپذیر تمرکز دارد. علایق تحقیقاتی او در زمینه پردازش زبان طبیعی، یادگیری عمیق قابل توضیح بر روی داده های جدولی، و تجزیه و تحلیل قوی خوشه بندی ناپارامتری فضا-زمان است. او مقالات زیادی را در کنفرانسهای ACL، ICDM، KDD، و انجمن آماری سلطنتی: سری A منتشر کرده است.
راچنا چادا is a Principal Solution Architect AI/ML in Strategic Accounts at AWS. Rachna is an optimist who believes that ethical and responsible use of AI can improve society in future and bring economical and social prosperity. In her spare time, Rachna likes spending time with her family, hiking, and listening to music.
ایوان کراویتز یک مهندس نرم افزار در خدمات وب آمازون است که روی SageMaker JumpStart کار می کند. او از آشپزی و دویدن در شهر نیویورک لذت می برد.
دکتر آشیش ختان یک دانشمند کاربردی ارشد با الگوریتم های داخلی Amazon SageMaker است و به توسعه الگوریتم های یادگیری ماشین کمک می کند. او دکترای خود را از دانشگاه ایلینویز Urbana-Champaign گرفت. او یک محقق فعال در یادگیری ماشین و استنتاج آماری است و مقالات زیادی در کنفرانس های NeurIPS، ICML، ICLR، JMLR، ACL و EMNLP منتشر کرده است.
- محتوای مبتنی بر SEO و توزیع روابط عمومی. امروز تقویت شوید.
- PlatoData.Network Vertical Generative Ai. به خودت قدرت بده دسترسی به اینجا.
- PlatoAiStream. هوش وب 3 دانش تقویت شده دسترسی به اینجا.
- PlatoESG. کربن ، CleanTech، انرژی، محیط، خورشیدی، مدیریت پسماند دسترسی به اینجا.
- PlatoHealth. هوش بیوتکنولوژی و آزمایشات بالینی. دسترسی به اینجا.
- منبع: https://aws.amazon.com/blogs/machine-learning/gemma-is-now-available-in-amazon-sagemaker-jumpstart/
- : دارد
- :است
- :نه
- :جایی که
- $UP
- 1
- 10
- 100
- 11
- 13
- 135
- 17
- 19
- 1900
- 250
- 28
- 29
- 31
- 39
- 41
- 50
- 7
- 8
- 9
- a
- توانایی
- درباره ما
- بالاتر
- پذیرفتن
- دسترسی
- دسترسی
- حساب
- حساب ها
- تجمع
- دقت
- دقیق
- قابل دستیابی است
- دستیابی به
- اکتساب
- در میان
- اقدامات
- فعال
- واقعی
- انطباق
- اضافه
- علاوه بر این
- تنظیم کردن
- پیشرفته
- پیشرفت
- پس از
- در برابر
- عامل
- AI
- AI / ML
- هواپیما
- الگوریتم
- بیگانه
- معرفی
- اجازه دادن
- مجاز
- اجازه می دهد تا
- در امتداد
- همچنین
- جایگزین
- آمازون
- آمازون SageMaker
- Amazon SageMaker JumpStart
- آمازون خدمات وب
- مقدار
- an
- تحلیل
- تحلیل
- تجزیه و تحلیل
- تجزیه و تحلیل
- و
- و زیرساخت
- آندرومدا
- آنجلس
- اعلام
- پاسخ
- پاسخ دادن
- پاسخ
- هر
- هر چیزی
- API
- نرم افزار
- برنامه های کاربردی
- اعمال می شود
- درخواست
- روش
- رویکردها
- مناسب
- برنامه های
- معماری
- هستند
- محدوده
- مناطق
- استدلال
- دور و بر
- هنر
- مقالات
- مصنوعی
- هوش مصنوعی
- AS
- پرسیدن
- ارزیابی
- دستیار
- فضانورد
- At
- حضار
- قدرت
- خودکار
- در دسترس
- اجتناب از
- برنده جایزه
- AWS
- کنسول مدیریت AWS
- به عقب
- متعادل
- پایه
- مستقر
- اساسی
- دسته
- بیزی
- BE
- زیرا
- قبل از
- شروع
- پشت سر
- بودن
- باورهای
- معتقد است که
- در زیر
- معیار
- معیار
- سود
- در کنار
- بهترین
- بهتر
- میان
- تعصب
- تعصبات
- بیلیون
- میلیاردها
- BLADE
- مسدود کردن
- بلاگ
- وبلاگ ها
- شکوفه
- بدن
- کتاب
- کتاب
- تفکیک
- درخشان
- به ارمغان بیاورد
- آوردن
- به ارمغان می آورد
- شکسته
- بودجه
- ساختن
- بنا
- ساخته
- ساخته شده در
- اما
- دکمه
- by
- تقویم
- صدا
- نام
- CAN
- نمی توان
- نقاشی
- قابلیت های
- توانا
- کارت
- مورد
- موارد
- دسته بندی
- احتیاط
- سلول
- به چالش
- چالش ها
- تغییر دادن
- مشخصات
- بار
- گپ
- چک
- انتخاب
- انتخاب
- را انتخاب کنید
- شهر:
- تمدن
- کلاس
- کلاسیک
- تمیز
- تمیز کاری
- به وضوح
- کلیک
- باشگاه
- خوشه بندی
- رمز
- برنامه نویسی
- همکاری
- می آید
- عموما
- مقايسه كردن
- مقایسه
- مقایسه
- مقایسه
- سازگار
- کامل
- پیچیدگی ها
- پیچیدگی
- مطابق
- کامپیوتر
- چشم انداز کامپیوتر
- مفهوم
- مفاهیم
- رقیب
- همایش ها
- پیکر بندی
- درگیری
- عواقب
- در نظر بگیرید
- ملاحظات
- با توجه به
- همواره
- تشکیل شده است
- کنسول
- ثابت
- محدودیت ها
- تماس
- شامل
- ظرف
- شامل
- دعوا کردن
- محتوا
- زمینه
- به طور مداوم
- کنترل
- کنترل
- گفتگو
- محاورهای
- گفتگو
- تبدیل
- تبدیل
- سرد
- به درستی
- هزینه
- میتوانست
- ایجاد
- ایجاد
- خالق
- خالق
- جدول کلمات متقاطع
- سرپرستی
- کنجکاو
- جاری
- مشتریان
- سفارشی سازی
- روزانه
- رقص
- تاریک
- داده ها
- مجموعه داده ها
- روز
- تصمیم گیری
- عمیق
- یادگیری عمیق
- عمیق تر
- Deepmind
- به طور پیش فرض
- تعريف كردن
- تعریف می کند
- غرق کردن
- غوطه ور شدن
- تظاهرات
- بستگی دارد
- گسترش
- مستقر
- استقرار
- گسترش
- کویر
- طرح
- طراحی
- مطلوب
- جزئیات
- دقیق
- جزئیات
- مشخص کردن
- توسعه
- توسعه
- توسعه دهنده
- در حال توسعه
- پروژه
- دستگاه
- تشخیص دادن
- گفتگو
- متفاوت است
- تفاوت
- مختلف
- دیجیتال
- هنر دیجیتال
- مستقیما
- فهرست راهنما
- كشف كردن
- گفتگو
- بحث و گفتگو
- بیماری
- شیرجه رفتن
- مختلف
- تنوع
- تقسیم
- do
- سند
- فیلم های مستند
- میکند
- دامنه
- حوزه
- انجام شده
- پایین
- دانلود
- دو
- دوک
- دانشگاه دوک
- در طی
- گرد و خاک
- دوطرفه
- هر
- زمین
- آسان تر
- بهره وری
- هشت
- پست الکترونیک
- امپراطوری
- قادر ساختن
- را قادر می سازد
- را قادر می سازد
- رویارویی
- تشویق می کند
- پشت سر هم
- نقطه پایانی
- جذاب
- مهندس
- افزایش می یابد
- لذت بردن
- لذت بخش
- اطمینان حاصل شود
- محیط
- EPIC
- خطاهای
- ضروری است
- ایجاد
- اخلاقی
- ارزیابی
- ارزیابی
- ارزیابی
- در نهایت
- هر
- مثال
- مثال ها
- برانگیخته
- جامع
- نمایشگاه ها
- وجود
- موجود
- گسترش
- انتظار می رود
- گران
- تجربه
- تجربه
- کارشناسان
- اکتشاف
- کاوش می کند
- بررسی
- چهره
- عدالت
- غلط
- خانواده
- سریعتر
- ویژگی
- باز خورد
- پا
- کمی از
- رشته
- مبارزه کردن
- پرونده
- سرانجام
- پیدا کردن
- یافته ها
- پایان
- نام خانوادگی
- تماس اول
- مناسب
- پنج
- فلاش
- پرواز
- تمرکز
- پیروی
- به دنبال آن است
- برای
- برای همیشه
- قالب
- پایه
- چارچوب
- رک
- از جانب
- تابع
- ویژگی های
- قابلیت
- عملکرد
- بیشتر
- آینده
- مربوط به اینده
- بازیها
- جمع آوری
- برج جوزا
- مولد
- مولد
- هوش مصنوعی مولد
- ژانر
- ژانرها
- دریافت کنید
- GitHub
- دادن
- داده
- Go
- اهداف
- رفتن
- خوب
- گوگل
- گوگل
- کردم
- GPU
- فضل
- بتدریج
- بزرگ
- قدرت عالی
- گروه
- تضمین می کند
- گارد
- راهنمایی
- راهنمایی
- راهنمایی
- دست
- دهنه
- آیا
- he
- ارتفاع
- سلام
- کمک
- کمک می کند
- او
- اینجا کلیک نمایید
- پنهان
- خود را
- تاریخ
- امید
- میزبانی
- چگونه
- چگونه
- اما
- HTML
- HTTPS
- قطب
- هاب
- صورت در آغوش گرفته
- انسان
- بشریت
- انسان
- i
- ID
- اندیشه
- شناسایی
- if
- ایلینوی
- تصاویر
- تأثیر
- انجام
- پیاده سازی
- واردات
- مهم
- بهبود
- بهبود
- ارتقاء
- بهبود
- in
- شامل
- از جمله
- گنجاندن
- افزایش
- مستقل
- صنعت
- استانداردهای صنعت
- نفوذ
- اطلاعات
- اطلاعاتی
- شالوده
- نبوغ
- ابداع
- ورودی
- ورودی
- سوالات
- بینش
- الهام بخش
- نمونه
- در عوض
- ادغام
- یکپارچه
- اطلاعات
- قصد
- اثر متقابل
- منافع
- رابط
- تقاطع
- به
- معرفی
- حسی
- شامل
- گرفتار
- شامل
- IT
- اقلام
- ITS
- اصطلاحات مخصوص یک صنف
- پیوستن
- روزنامه
- سفر
- JPG
- json
- تنها
- نگاه داشتن
- نوع
- دانستن
- دانش
- شناخته شده
- کایل
- فرود
- چشم انداز
- زبان
- بزرگ
- بزرگتر
- تاخیر
- راه اندازی
- قوانین
- برجسته
- یاد گرفتن
- یادگیری
- می آموزد
- ترک
- طول
- اجازه
- سطح
- قدرت نفوذ
- مجوز
- مجوزها
- زندگی
- رعد و برق
- سرعت رعد و برق
- سبک وزن
- پسندیدن
- دوست دارد
- لاین
- خطوط
- فهرست
- گوش دادن
- استماع
- گوش می کند
- پشم لاما
- بار
- محلی
- محل
- نگاه کنيد
- به دنبال
- مطالب
- آنها
- لس آنجلس
- کاهش
- دستگاه
- فراگیری ماشین
- اکثریت
- ساخت
- مخرب
- مدیریت
- دستی
- بسیاری
- علامت
- بهرام
- ریاضیات
- بیشترین
- ممکن است..
- me
- معنی
- معانی
- معیارهای
- رسانه ها
- پزشکی
- نشست
- ذکر شده
- پیام
- پیام
- روش
- مایکل
- قدرت
- ذهن
- دقیقه
- ML
- مدل
- مدل
- ماژول ها
- مانیتور
- نظارت بر
- بیش
- اکثر
- فیلم ها
- موسیقی
- باید
- my
- مرموز
- نام
- تحت عنوان
- طبیعی
- پردازش زبان طبیعی
- طبیعت
- لازم
- نیاز
- ضروری
- نیازهای
- شبکه
- عصبی
- شبکه های عصبی
- هرگز
- جدید
- نیویورک
- شهر نیویورک
- شب
- نه
- توجه داشته باشید
- دفتر یادداشت
- رمان
- اکنون
- عدد
- واحه
- هدف
- اهداف
- مشاهده کردن
- of
- پیشنهادات
- غالبا
- on
- یک بار
- ONE
- مداوم
- فقط
- قابل استفاده
- فرصت ها
- بهینه سازی
- بهینه سازی
- گزینه
- or
- سفارش
- منشاء
- OS
- دیگر
- دیگران
- خارج
- نتیجه
- نتایج
- تولید
- روی
- خود
- با ما
- اوراق
- موازی
- پارامتر
- پارامترهای
- ویژه
- ویژه
- احزاب
- عبور
- عبور
- گذشته
- مسیر
- الگوهای
- پل
- مردم
- برای
- انجام
- کارایی
- انجام
- انجام می دهد
- شخصی
- دیدگاه
- دکترا
- عبارات
- فیزیکدان
- خلبان
- محل
- سیاره
- برنامه
- افلاطون
- هوش داده افلاطون
- PlatoData
- بازی
- بازیکن
- لطفا
- نقطه
- نقطه
- سیاسی
- محبوب
- جمعیت
- پست
- پتانسیل
- قدرت
- تمرین
- شیوه های
- پیش بینی
- پیشگو
- تنظیمات
- آماده
- زیبا
- قبلا
- شاهزاده
- اصلی
- چاپ
- روند
- فرآوری شده
- فرآیندهای
- در حال پردازش
- تولید
- برنامه
- پیشرفت
- پروژه
- پرسیدن
- مناسب
- رفاه
- ارائه
- ارائه دهندگان
- فراهم می کند
- عمومی
- عمومی
- منتشر شده
- اهداف
- پازل
- پــایتــون
- مارماهی
- کیفیت
- نمایش ها
- پرس و جو
- جستجو
- سوال
- سوالات
- به سرعت
- کاملا
- نژاد
- انشعابات
- محدوده
- نسبتا
- خام
- رسیدن به
- خواندن
- مطالعه
- دنیای واقعی
- واقعیت
- واقعا
- قلمرو
- دلیل
- گرفتن
- اخیر
- توصیه
- توصیه
- توصیه
- راجعه
- مرجع
- اشاره کرد
- بازتاب می دهد
- به طور منظم
- مقررات
- مربوط
- منتشر شد
- مربوط
- به یاد داشته باشید
- تکرار
- نمایندگی
- درخواست
- ضروری
- مورد نیاز
- تحقیق
- پژوهشگر
- پاسخ
- پاسخ دادن
- پاسخ
- پاسخ
- مسئوليت
- مسئوليت
- نتیجه
- نتایج
- این فایل نقد می نویسید:
- پاداش
- طلوع
- تنومند
- نیرومندی
- نقش
- روال
- سلطنتی
- قوانین
- دویدن
- اجرا می شود
- s
- امن تر
- حکیم ساز
- استنباط SageMaker
- همان
- ذخیره
- گفتن
- مقیاس پذیر
- مقیاس
- مقیاس ها
- مقیاس گذاری
- سناریوها
- Sci-Fi حجم
- علم
- دانشمند
- دانشمندان
- حوزه
- خراش
- خط
- اسکریپت
- sdk
- بدون درز
- جستجو
- دوم
- اسرار
- بخش
- امن
- دیدن
- را انتخاب کنید
- انتخاب شد
- انتخاب
- انتخاب
- در حال ارسال
- ارشد
- جداگانه
- دنباله
- سلسله
- سری A
- خدمات
- خدمت
- جلسه
- تنظیم
- مجموعه
- محیط
- چند
- به اشتراک گذاشته شده
- باید
- نشان
- نشان داد
- نمایش
- نشان داده شده
- نشان می دهد
- طرف
- مشابه
- ساده
- تنها
- اندازه
- اندازه
- مهارت ها
- So
- آگاهی
- جامعه
- نرم افزار
- مهندس نرمافزار
- راه حل
- مزایا
- برخی از
- منابع
- جرقه
- خاص
- سرعت
- هزینه
- صرف می کند
- ایستادن
- استانداردهای
- آغاز شده
- راه افتادن
- دولت
- وضعیت هنر
- بیانیه
- آماری
- گام
- مراحل
- هنوز
- داستان
- طوفان
- داستان
- عجیب
- استراتژیک
- استراتژی ها
- رشته
- قوی
- استودیو
- مهاجرت تحصیلی
- مشترک
- زیرنویس
- موفق
- چنین
- مناسب
- پشتیبانی
- پشتیبانی
- حمایت از
- پشتیبانی از
- مطمئن
- زنده ماندن
- سیستم
- جدول
- گرفتن
- طول می کشد
- داستان
- هدف
- اهداف
- کار
- وظایف
- تیم
- تیم ها
- تکنیک
- تکنیک
- پیشرفته
- قالب
- قالب
- جریان تنسور
- قوانین و مقررات
- آزمون
- آزمایش
- تست
- متن
- نسبت به
- که
- La
- محوطه
- آینده
- جهان
- شان
- آنها
- خودشان
- سپس
- آنجا.
- از این رو
- اینها
- آنها
- سوم
- اشخاص ثالث
- شخص ثالث
- این
- کسانی که
- فکر
- تأمل برانگیز
- هزار
- هیجان انگیز
- از طریق
- توان
- زمان
- سری زمانی
- سفر در زمان
- جدول زمانی
- بار
- به
- رمز
- نشانه گذاری
- نشانه
- گفته شده
- ابزار
- ابزار
- موضوع
- جمع
- مسیر
- سنتی
- قطار
- آموزش دیده
- آموزش
- انتقال
- انتقال
- ترانسفورماتور
- ترجمه
- سفر
- تریلیون
- درست
- امتحان
- اهنگ
- کوک شده
- میزان سازی
- tv
- دو
- نوع
- انواع
- نوعی
- به طور معمول
- ui
- در نهایت
- برملا کردن
- زیر
- فهمیدن
- درک
- نا آشنا
- جهان
- دانشگاه
- بی همتا
- تا
- آشکار شدن
- به روز شده
- به روز رسانی
- به روز رسانی
- us
- قابلیت استفاده
- استفاده
- استفاده کنید
- مورد استفاده
- استفاده
- کاربر
- کاربر پسند
- کاربران
- استفاده
- با استفاده از
- اعتبار سنجی
- ارزشها
- تنوع
- مختلف
- ریسک
- نسخه
- چشم انداز
- مجازی
- واقعیت مجازی
- دید
- بازدید
- بصری
- رسانه های دیداری
- حجم
- راه رفتن
- می خواهم
- ضمانت نامه ها
- بود
- تماشا کردن
- تماشای
- مسیر..
- راه
- we
- وب
- خدمات وب
- مبتنی بر وب
- هفته
- خوب
- ولز
- چی
- چه شده است
- چه زمانی
- هر زمان که
- چه
- که
- WHO
- وسیع
- به طور گسترده ای
- ویدجت
- اراده
- خرد
- با
- در داخل
- بدون
- کلمه
- کلمات
- مهاجرت کاری
- گردش کار
- کارگر
- جهان
- نوشتن
- نوشته
- X
- نیویورک
- شما
- جوان
- شما
- خودت
- زفیرنت