Blog
-
LLama 2 AWS Environment Cost
Ever wondered how much it would cost to deploy an LLM (Llama 2 or Mistral 7b) on AWS for production? AdithyaSK tested it out by deploying it himself, and we’ll be sharing the details in the blog post. The Production LLama 2 AWS Environment Cost comes to $1.5k per month. Read related article where we…
-
LLaVA – an open-source alternatives to GPT-4 Vision
The field of generative AI is swiftly advancing with the introduction of large multimodal models (LMM). These models are revolutionizing our engagement with AI by accepting both text and images as inputs. While OpenAI’s GPT-4 Vision stands out in this domain, its proprietary and commercial nature may restrict its application in some areas. Yet, the…
-
Llama 2 As Accurate as GPT-4 for Summaries
Llama 2 provides summaries with a factual accuracy comparable to GPT-4, but at 1/30th the cost. In this experiment, Anyscale team found Llama-2-70b is almost as strong at factuality as gpt-4, and considerably better than gpt-3.5-turbo. The Anyscale Team used Anyscale Endpoints to compare Llama 2 7b, 13b, and 70b (chat-hf fine-tuned) against OpenAI gpt-3.5-turbo…
-
Llama 2 on Hugging Face
Llama 2 encompasses a series of generative text models that have been both pretrained and fine-tuned, with sizes varying from 7 billion up to 70 billion parameters. This specific repository is dedicated to the 7B version. For other model links, please refer to the index provided below. Details on the Model Please note: Accessing this…
-
LLama Long
Meta built LLama Long on the foundation of OpenLLaMA and refined it using the Focused Transformer (FoT) method. LongLLaMA Code stands upon the base of Code Llama. Dev team released a more compact 3B base variant (not instruction tuned) of the LongLLaMA model under a lenient license (Apache 2.0) and offered inference code that accommodates…
-
LLamaIndex Installation and Setup
LlamaIndex, previously known as GPT Index, is a data framework designed for LLM applications, facilitating the intake, organization, and retrieval of specialized or private data. Here’s what LlamaIndex offers: Installation from Pip You can simply do: IMPORTANT: LlamaIndex might download and save files locally from different packages like NLTK, HuggingFace, etc. To specify the storage…
-
Llama 2 on Amazon SageMaker
Philipp Schmid and his team at HuggingFace highlighted the challenges in deploying large language models (LLMs) and other generative AI models because of their computational demands and latency considerations. They crafted a detailed benchmark that scrutinized over 60 distinct deployment configurations for Llama 2, aiming to aid companies keen on deploying this model on Amazon…
-
How To Train a LLaMA 2 ChatBot
In this guide, Andrew Jardine and Abhishek Thakur will demonstrate how you can easily create your own open-source ChatGPT without any coding expertise! Using the LLaMA 2 base model, they’ll refine it for chat interactions using an open-source dataset and then integrate it into a chat application for you to share. The best part? It’s…
-
The Llama Ecosystem
It’s been approximately seven months since Meta released Llama 1 and just a few months since the introduction of Llama 2, which was soon followed by the launch of Code Llama. The feedback from the community has been overwhelming. There’s been significant momentum and innovation, with over 30 million downloads of Llama-based models via HuggingFace…