Open in app
Sign inGet started
Prompt Caching with Claude 3.5 Sonnet

Prompt Caching with Claude 3.5 Sonnet

This new video tutorial provides an overview of the recent prompt caching feature introduced by Anthropic for their Claude 3.5 Sonnet…
Go to the profile of elvis
elvis
Fine-tuning with GPT-4o Models

Fine-tuning with GPT-4o Models

We are working on tiny tutorials that explore fine-tuning with LLMs.
Go to the profile of elvis
elvis
[LLMs News] GPT-4o mini, Codestral Mamba, Prompt Engineering Methods, Mistral Nemo, Spreadsheet LLM

[LLMs News] GPT-4o mini, Codestral Mamba, Prompt Engineering Method...

Huge efforts in small language models and improving reasoning efficiency in LLMs.
Go to the profile of elvis
elvis
LLM News: ESM3, CriticGPT, Gemma 2, LLM Compiler, LongRAG, GraphReader

LLM News: ESM3, CriticGPT, Gemma 2, LLM Compiler, LongRAG, GraphReader

Lots of exciting developments in AI and LLMs in the past couple of days.
Go to the profile of elvis
elvis
[LLM News] Claude 3.5 Sonnet, Open-Sora, Context Caching, PlanRAG, Safe SuperIntelligence Inc

[LLM News] Claude 3.5 Sonnet, Open-Sora, Context Caching, PlanRAG, ...

Developments in AI and LLMs just don’t slow down.
Go to the profile of elvis
elvis
Papers Explained: Mistral 7B

Papers Explained: Mistral 7B

Mistral 7B is an LLM engineered for superior performance and efficiency. It leverages grouped-query attention (GQA) for faster inference…
Go to the profile of Ritvik Rastogi
Ritvik Rastogi
Papers Explained 63: LLaMA 2 Long

Papers Explained 63: LLaMA 2 Long

LLaMA 2 Long is a series of long-context LLMs built through continual pretraining from LLAMA 2 with longer training sequences that support…
Go to the profile of Ritvik Rastogi
Ritvik Rastogi
Papers Explained 62: Code Llama

Papers Explained 62: Code Llama

Code Llama is a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models…
Go to the profile of Ritvik Rastogi
Ritvik Rastogi
Papers Explained 61: Humpback

Papers Explained 61: Humpback

Instruction back translation is a scalable method to build a high-quality instruction following language model by automatically labeling…
Go to the profile of Ritvik Rastogi
Ritvik Rastogi
Most Popular
Detecting Sarcasm with Deep Convolutional Neural Networks

Detecting Sarcasm with Deep Convolutional Neural Networks

Overview This paper addresses a key NLP problem known as sarcasm detection using a combination of models based on convolutional neural…
Go to the profile of elvis
elvis
A Light Introduction to Transfer Learning for NLP

A Light Introduction to Transfer Learning for NLP

In this post, I will introduce transfer learning for natural language processing and key questions necessary to better understand this…
Go to the profile of elvis
elvis
Deep Learning for NLP: An Overview of Recent Trends

Deep Learning for NLP: An Overview of Recent Trends

In a timely new paper, Young and colleagues discuss some of the recent trends in deep learning based natural language processing (NLP)…
Go to the profile of elvis
elvis
About DAIR.AILatest StoriesArchiveAbout MediumTermsPrivacyTeams