Nixtla’s TimeGPT is a generative pre-trained forecasting model for time series data. TimeGPT can produce accurate forecasts for new time series without training, using only historical values as inputs. TimeGPT can be used across a plethora of tasks including demand forecasting, anomaly detection, financial forecasting, and more.

The TimeGPT model “reads” time series data much like the way humans read a sentence – from left to right. It looks at windows of past data, which we can think of as “tokens”, and predicts what comes next. This prediction is based on patterns the model identifies in past data and extrapolates into the future.

The API provides an interface to TimeGPT, allowing users to leverage its forecasting capabilities to predict future events. TimeGPT can also be used for other time series-related tasks, such as what-if scenarios, anomaly detection, and more.

https://nixtla.github.io/nixtla/docs/getting-started/getting_started_short.html

https://youtube.com/watch?v=POBcYr0sbcg&si=VD5odGEisjt2fzUi

DSPy is the framework for solving advanced tasks with language models (LMs) and retrieval models (RMs). DSPy unifies techniques for prompting and fine-tuning LMs — and approaches for reasoning, self-improvement, and augmentation with retrieval and tools. All of these are expressed through modules that compose and learn.

To make this possible:

• DSPy provides composable and declarative modules for instructing LMs in a familiar Pythonic syntax. It upgrades « prompting techniques » like chain-of-thought and self-reflection from hand-adapted string manipulation tricks into truly modular generalized operations that learn to adapt to your task.
• DSPy introduces an automatic compiler that teaches LMs how to conduct the declarative steps in your program. Specifically, the DSPy compiler will internally trace your program and then craft high-quality prompts for large LMs (or train automatic finetunes for small LMs) to teach them the steps of your task.

The DSPy compiler bootstraps prompts and finetunes from minimal data without needing manual labels for the intermediate steps in your program. Instead of brittle « prompt engineering » with hacky string manipulation, you can explore a systematic space of modular and trainable pieces.

For complex tasks, DSPy can routinely teach powerful models like GPT-3.5 and local models like T5-base or Llama2-13b to be much more reliable at tasks. DSPy will compile the same programinto different few-shot prompts and/or finetunes for each LM.

If you want to see DSPy in action, open our intro tutorial notebook.

Graph RAG is an Knowledge-enabled RAG approach to retrieve information from Knowledge Graph on given task. Typically, this is to build context based on entities’ SubGraph related to the task.

GraphStore backed RAG vs VectorStore RAG

As we compared how Graph RAG helps in some use cases in this tutorial, it’s shown Knowledge Graph as the unique format of information could mitigate several issues caused by the nature of the “split and embedding” RAG approach.

Graph RAG

https://www.philschmid.de/gptq-llama

• Hugging Face Optimum team collaborated with AutoGPTQ library for a simple API to apply GPTQ quantization on language models.
• GPTQ quantization allows open LLMs to 8, 4, 3, or 2 bits, enabling them to run on smaller hardware with minimal performance loss.
• The blog covers:

1. Setting up the development environment.
2. Preparing the quantization dataset.
3. Loading and quantizing the model.
4. Testing performance and inference speed.
5. Bonus: Running inference with text generation.

• GPTQ’s purpose is explained before diving into the tutorial.

• Large Language Models (LLMs) and prompt-based heuristics are being used for off-the-shelf solutions to various NLP problems.
• LLM-based few-shot methods have shown promise but lag in Named Entity Recognition (NER) compared to other methods.
• « PromptNER » is introduced as a new algorithm for few-shot and cross-domain NER.
• PromptNER needs entity definitions and few-shot examples for a new NER task.
• PromptNER uses LLM to generate potential entities and explanations for their compatibility with entity type definitions.
• PromptNER achieves state-of-the-art performance in few-shot NER on ConLL, GENIA, and FewNERD datasets.
• It also outperforms previous methods in Cross Domain NER, setting new records on 3 out of 5 CrossNER domains with an average F1 gain of 3%.

https://arxiv.org/pdf/2305.15444.pdf

https://github.com/promptslab/Promptify