LARGE LANGUAGE MODELS

DEEPNA THALANKI

SAI VIKAS DEVISETTY

AGENDA

• What are Large Language Models?
• Why are large language models important?
• What are applications of large language models?
• How are large language models trained?
• Top 5 Large Language Models
• The Pros and Cons of Using LLMs in the Cloud Versus Running LLMs Locally
• What is the future of LLMs?

​

WHAT ARE LARGE LANGUAGE MODELS?�

Large language models (LLMs) are deep learning algorithms that can recognize, summarize, translate, predict, and generate content using very large datasets.

WHY ARE LARGE LANGUAGE MODELS IMPORTANT?�

Large language models are incredibly flexible. One model can perform completely different tasks such as answering questions, summarizing documents, translating languages and completing sentences. LLMs have the potential to disrupt content creation and the way people use search engines and virtual assistants.

WHAT ARE APPLICATIONS OF LARGE LANGUAGE MODELS?�

There are many practical applications for LLMs:

​

• Copywriting - GPT-3, ChatGPT, Claude, Llama 2, Cohere Command, and Jurassiccan write original copy
• Text classification -Using clustering, LLMs can classify text with similar meanings or sentiments.
• Code generation - LLM are proficient in code generation from natural language prompts
• Text generation - Similar to code generation, text generation can complete incomplete sentences, write product documentation or, like Alexa Create, write a short children's story.

HOW ARE LARGE LANGUAGE MODELS TRAINED?�

Training is performed using a large corpus of high-quality data. During training, the model iteratively adjusts parameter values until the model correctly predicts the next token from an the previous squence of input tokens. It does this through self-learning techniques which teach the model to adjust parameters to maximize the likelihood of the next tokens in the training examples.

TOP 5 LARGE LANGUAGE MODELS�

• GPT-4
• Claude 2
• Llama 2
• Orca
• Cohere

THE PROS AND CONS OF USING LLMS IN THE CLOUD VERSUS RUNNING LLMS LOCALLY�

Running LLMs Locally

​

Pros

-More control

-Lower costs

-Reduced latency

-Greater privacy

​

​

Cons

- Higher upfront costs

- Complexity

- Limited scalability

- Availability

- Accessing pre-trained models

​

Running LLMs in the Cloud

​

Pros

- Cost efficiency

- Ease of use

- Managed services

- Pre-trained models

​

​

Cons

- Loss of control

- Vendor lock-in

- Data privacy and security

- Network latency

WHAT IS THE FUTURE OF LLMS?�

The introduction of large language models like ChatGPT, Claude 2, and Llama 2 that can answer questions and generate text points to exciting possibilities in the future. Slowly, but surely, LLMs are moving closer to human-like performance.