AI TOOLS MASTER

Weights & Biases, developer tools for machine learning

Weights & Biases, developer tools for machine learning

Hello, I have fine tuned a “davinci” base model using hundreds of QA pairs, to build a a customized chatbot. After the model is built, the model can return a response by calling openai.Completion.create( model="davinci-fine-tuned", prompt=my_prompt) Now, I want to evaluate the model performance, should I compare the model performance and true value (from QA pairs) by calculating text similarity? If so, how can I calculate the accuracy/F1 of the fine tuned model? Thank you.

Launch a job into any target environment with W&B Launch, and dramatically scale machine learning training workloads from local machine to distributed compute.

Interact with Massive Datasets and Embedding Spaces In Your Web Browser

Stanford Question Answering Dataset (SQuAD) is a new reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage. With 100,000+ question-answer pairs on 500+ articles, SQuAD is significantly larger than previous reading comprehension datasets.

We break down social media so you can understand narratives, detect authenticity and reach true audiences.

Explore developer resources, tutorials, API docs, and dynamic examples to get the most out of OpenAI's platform.

We introduce the fine-tuning augmented embedding (FAE), a method that can improve OpenAI's embedding model for your data.

In this codelab, you’ll learn how to build a simple app for Android and iOS capable of correctly labeling an image.

The easiest way to scrape the web — a fast, free, and easy to use Chrome extension for scraping websites in your browser or automated in the cloud.

gpt4all: open-source LLM chatbots that you can run anywhere - GitHub - nomic-ai/gpt4all: gpt4all: open-source LLM chatbots that you can run anywhere