Step-by-Step Guide to Deploying and Using Llama 3 LLMs on TIR AI Studio

October 3, 2024

The Llama 3 series of LLMs is being increasingly adopted by companies looking to build data-sovereign AI APIs, workflows, and applications on their cloud infrastructure. The latest models in the series, Llama 3.2-11B and Llama 3.2-90B, also incorporate vision capabilities and are multimodal. This means you can use them to build AI solutions that need to reason over both text and images in combination. Examples include invoice parsing and processing, document understanding, infographic explainers, and more.

There are multiple ways to use the Llama 3 series models, including Llama 3.2. You can deploy them using Ollama on an advanced cloud GPU on E2E Cloud, or you can use vLLM, which offers you more control.

However, the easiest approach is to use TIR AI Studio, where you can deploy the Llama 3 series of LLMs without the help of a DevOps engineer, and get going in less than 10 minutes. The biggest advantage to this approach is that you can use the cutting-edge cloud GPUs on E2E Cloud and get extreme performance out of your AI model.

In this article, we will walk you through the steps to deploy and use the Llama 3 series on TIR. We will also show you how to query the endpoint, so that you can integrate it easily and build AI applications that are production ready.

Let’s get started!

Understanding the Llama 3 Series of LLMs

The Llama 3 series, including Llama 3.1, Llama 3.2 (11B and 90B), and the original Llama 3, bring several architectural improvements that optimize both inference and fine-tuning for developers working with diverse computational resources. Let’s first take a quick look at them. We will skip the original Llama 3, as it has been replaced by Llama 3.1 and Llama 3.2.

Llama 3.1 Series

The Llama 3.1 series introduced several powerful enhancements over its previous versions. Notably, it offered an expanded context length of up to 128,000 tokens, allowing it to manage longer inputs and maintain coherence over extended text generation. This feature is critical for applications where you need in-depth conversations, long-form summarization, and detailed content creation.

Llama 3.1 variants come in different sizes, such as 8B, 70B, and the massive 405B, with each variant optimized for various tasks like zero-shot learning, fine-tuning, and multi-modal applications. For developers, these models are available for deployment via platforms like E2E Cloud and TIR, and they support efficient inference through 8-bit quantization, significantly reducing computational demands during deployment

The Llama 3.1 models also support multilingual tasks, covering eight languages, which makes it versatile for global applications. The largest model in the series, the 405B parameter variant, is one of the most advanced open-source models available today, capable of high-level reasoning, coding, and tool usage.

Llama 3.2 Series

The recently launched Llama 3.2 introduced significant advancements over its predecessors, primarily through its multimodal and vision capabilities.

This series includes the 11B and 90B Vision Instruct models, designed to integrate both image and text inputs. These models enable complex image reasoning tasks, such as visual question answering, chart interpretation, and document visual analysis, positioning Llama 3.2 as a huge step up on other platform models like GPT-4 and Claude on multimodal benchmarks.

This is the best-in-class model you can use if you want to incorporate multimodality into your AI. Similar to the previous Llama models, they also feature 128K-token context windows and multilingual features.

Understanding TIR AI Studio

TIR AI Studio is a powerful AI/ML development platform designed to streamline the training, deployment, and management of large AI models. It provides users with access to high-performance GPU containers and pre-configured environments for frameworks like PyTorch, TensorFlow, and Triton. The platform includes an easy-to-use Jupyter Notebook interface.

TIR also supports end-to-end pipelines for training and deployment, enabling users to handle the entire model lifecycle, from data ingestion to inference. It integrates with popular tools such as Qdrant and PGVector for building RAG applications, making it a comprehensive solution for both research and production environments.

Using Llama 3 on TIR

To start with, first sign up or sign in to TIR. Once that’s done, on the left sidebar, click on Model Endpoints.

Step 1: Select Endpoint

‍

Then click on the CREATE ENDPOINT button as shown below.

‍

Next, you need to select the right model endpoint. You will have options for Llama 3.2, Llama 3.1 and Llama 3.

Alternatively, you can choose the vLLM option as well, and then select any model you want that vLLM supports.

‍

Step 2: Download the Model and Launch

To simplify things, you can simply select ‘Download from Hugging Face’ as the option.

‍

You’ll need to add your hf_token from Hugging Face for this step. We will assume that you have applied for access to the Llama 3.2 or Llama 3.1 model of your choosing already.

Provide the token below.

You will also need to choose the GPU node. You will have to select this based on the number of parameters your model has. We will choose the Llama 3.1-8B with the L4 series of cloud GPUs.

Once that’s done, select the Plan Details. You should select a minimum 30GB disk replica size (however, we recommend a minimum 100GB, if you are going to train the model).

Finally, you can set up the environment variables if required.

You can now launch the endpoint.

Step 3: Verify Endpoint

Verify if the endpoint is working. Check the list of endpoints here:

Now, confirm if your model endpoint is working. You can look at the logs of the endpoint you created.

‍

Step 4: Generate Your API_TOKEN

Now, you will need to generate the API token for accessing the model from your application. To do that, create a token.

‍

Once created, you’ll be able to see the list of API Tokens containing the API Key and Auth Token. You will need this Auth Token in the next step.

You will need the following that you can save and create environment variables out of:

Base Endpoint URL
Auth Token

Step 5: Model Inference

We now have a running model endpoint and an API token to access it. How do you use it in your notebook or code?

Since the model endpoint is compatible with the OpenAI client Python library, you can create a virtual environment and install the client.


!pip install -q openai

Next, test the model inference in the following way:


import openai

token = os.getenv("AUTH_TOKEN_FROM_API_TOKEN_SECTION")   # You can get auth token from API Token section on TIR Dashboard

openai.api_key = token
openai.base_url = ""

completion = openai.chat.completions.create(
    model="meta-llama/Meta-Llama-3-8B-Instruct",
    messages=[
        {
            "role": "user",
            "content": "Explain LLMs?",
        },
    ],
     
)
print(completion.choices[0].message.content)

Here’s the response we received from the model endpoint we just made at TIR.

Response:


LLMs stand for Large Language Models, which are a type of artificial intelligence (AI) model specifically designed to process and generate human-like language. These models have revolutionized the field of natural language processing (NLP) and have many applications in various industries.

Here's a brief overview:

**What are LLMs?**

LLMs are neural network-based models that are trained on large amounts of text data, typically in the form of books, articles, websites, and other digital content. The goal is to learn patterns, relationships, and structures within language, enabling the model to generate text that is coherent, natural-sounding, and often indistinguishable from human-written text.

**How do LLMs work?**

LLMs are typically trained using a combination of supervised and unsupervised learning techniques. Supervised learning involves feeding the model labeled data, such as text with corresponding meanings or tasks (e.g., classification, sentiment analysis). Unsupervised learning involves training the model on large amounts of unlabeled data to learn patterns and relationships within the language.

The training process typically involves the following steps:

1. **Text Preprocessing**: The text data is cleaned, tokenized, and converted into a numerical representation.
2. **Model Architecture**: The LLM is designed using a specific architecture, such as transformer-based models (e.g., BERT, RoBERTa) or recurrent neural networks (RNNs).
3. **Training**: The model is trained on the preprocessed text data, using techniques like masked language modeling, next sentence prediction, and sentiment analysis.
4. **Fine-tuning**: The trained model is fine-tuned for specific tasks, such as text classification, language translation, or text generation.

**Applications of LLMs**

LLMs have numerous applications across industries, including:

1. **Natural Language Processing (NLP)**: LLMs can be used for tasks like text classification, sentiment analysis, entity recognition, and language translation.
2. **Chatbots and Virtual Assistants**: LLMs can be used to power chatbots and virtual assistants, enabling them to understand and respond to user queries.
3. **Language Translation**: LLMs can be used for machine translation, enabling the translation of text from one language to another.
4. **Content Generation**: LLMs can be used to generate content, such as articles, blog posts, or social media posts, reducing the need for human writers.
5. **Question Answering**: LLMs can be used to answer questions, providing accurate and relevant information.
6. **Language Understanding**: LLMs can be used to analyze and understand human language, enabling applications like sentiment analysis, topic modeling, and text summarization.

**Challenges and Limitations**

While LLMs have achieved remarkable success, they also face challenges and limitations, including:

1. **Data Quality**: The quality of the training data can significantly impact the model's performance.
2. **Domain Adaptation**: LLMs may struggle to generalize to new domains or topics that are outside the scope of their training data.
3. **Language Understanding**: LLMs may not fully understand the nuances of human language, leading to errors in interpretation.
4. **Explainability**: LLMs may not provide clear explanations for their decisions or outputs, making it challenging to understand their reasoning.

Overall, LLMs have revolutionized the field of NLP, enabling applications that were previously unimaginable. However, there are still challenges and limitations to be addressed, and ongoing research is focused on improving the performance, robustness, and explainability of these models.

That’s it! You can now use the Llama 3 series to build applications. Throughout the entire process of launching the LLM, there was no need for any system administration or coding. The best part is that it’s backed by a powerful L4 cloud GPU, all at a fraction of the cost compared to other hyperscalers

Conclusion

TIR AI Studio simplifies the process of deploying and using large language models (LLMs). Backed by powerful yet affordable cloud GPUs, the platform allows you to easily build production-grade AI applications.

Sign up for Free Trial

Latest Blogs

NVIDIA DGX B300: The Next Leap in AI Performance Coming Soon to E2E Cloud's TIR AI/ML Platform

March 20, 2025

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.
CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels.

Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

‍

Reference Links

https://www.helpscout.com/customer-acquisition/

https://www.cloudways.com/blog/customer-acquisition-strategy-for-startups/

https://blog.hubspot.com/service/customer-acquisition

This is a decorative image for: Constructing 3D objects through Deep Learning

October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

Highly calibrated cameras that take a photograph of the image from various angles.
Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website.

‍

Reference Links

https://tongtianta.site/paper/68922

https://github.com/natowi/3D-Reconstruction-with-Deep-Learning-Methods

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts

October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

https://analyticsindiamag.com/comprehensive-guide-to-deep-q-learning-for-data-science-enthusiasts/

https://medium.com/@jereminuerofficial/a-comprehensive-guide-to-deep-q-learning-8aeed632f52f

October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
GAUDI also removes GANs pathologies like mode collapse and improved GAN.
GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
The scenes are thus synthesized by interpolation within the hidden space.
The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

‍

Reference Links

https://www.researchgate.net/publication/362323995_GAUDI_A_Neural_Architect_for_Immersive_3D_Scene_Generation

https://www.technology.org/2022/07/31/gaudi-a-neural-architect-for-immersive-3d-scene-generation/

https://www.patentlyapple.com/2022/08/apple-has-unveiled-gaudi-a-neural-architect-for-immersive-3d-scene-generation.html

Build on the most powerful infrastructure cloud

Contact Sales Get Started for Free

A vector illustration of a tech city using latest cloud technologies & infrastructure

Step-by-Step Guide to Deploying and Using Llama 3 LLMs on TIR AI Studio

Table of Contents

Understanding the Llama 3 Series of LLMs

Llama 3.1 Series

Llama 3.2 Series

Understanding TIR AI Studio

Using Llama 3 on TIR

Step 1: Select Endpoint

Step 2: Download the Model and Launch

Step 3: Verify Endpoint

Step 4: Generate Your API_TOKEN

Step 5: Model Inference

Conclusion

NVIDIA DGX B300: The Next Leap in AI Performance Coming Soon to E2E Cloud's TIR AI/ML Platform

Redefining The AI Future: GTC 2025 Keynote by NVIDIA CEO Jensen Huang

A Comparison between TIR Containerized VMs vs Traditional VMs

AI Tinkerers Meetup: AI Innovators Assemble!

Accelerate Your AI Application Development Using TIR Containerized VMs

Deepseek Hackathon: Driving AI Innovation with E2E Cloud & Upekkha

A Complete Guide To Customer Acquisition For Startups

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

The Main Objective of the 3D Object Reconstruction

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

GAUDI: A Neural Architect for Immersive 3D Scene Generation

Build on the most powerful infrastructure cloud