AI チュートリアル

Get started with Apple's DCLM-7B large language model and learn how to set it up, use it, and fine-tune it for specific tasks.

Learn how to set up PyTorch’s torchchat locally with Python in this hands-on tutorial, which provides step-by-step guidance and examples.

Tiktoken is a fast BPE tokenizer developed by OpenAI, primarily used to count tokens for their large language models and ensure efficient text processing within specified limits.

Learn how to perform data and model validation to ensure robust machine learning performance using our step-by-step guide to automating testing with DeepChecks.

Discover how to enhance PostgreSQL with vector search capabilities using pgvector. This tutorial guides you through installation, basic operations, and integration with AI tools.

Codestral Mamba is a 7-billion parameter code generation model by Mistral AI, utilizing the Mamba architecture for efficient and extended context coding.

DeepSeek-Coder-V2 is an open-source code language model that rivals the performance of GPT-4, Gemini 1.5 Pro, Claude 3 Opus, Llama 3 70B, or Codestral.

This is a simple guide to fine-tuning Gemma 2 9B-It on patient-doctor conversations and converting the model into GGUF format so that it can be used locally with the Jan application.

Get started with the new Llama models and customize Llama-3.1-8B-It to predict various mental health disorders from the text.

ScrapeGraph AI is an open-source tool that simplifies web scraping by automatically extracting structured data from websites, allowing users to interact with and retrieve the data through simple prompts.

Zero-shot prompting is a technique in which an AI model is given a task or question without any prior examples or specific training on that task, relying solely on its pre-existing knowledge to generate a response.

Few-shot prompting is a technique in which an AI model is given a few examples of a task to learn from before generating a response, using those examples to improve its performance on similar tasks.