Technical sharing by programmers
🧭 Introduction: Why Modal? Traditionally, deploying AI models in the cloud is a painful process: Modal completely changes that.It lets you define your infrastructure as code — in pure Python.You …
PyTorch-based LLaMA model architecture The overall architecture of the LLaMA model Waht embed_tokens does Suppose your vocabulary has only 5 words: [“I”, “want”, “to”, “learn”, “English”], Instead of representing them …
（Base → Refiner 粗生成到細化修飾流程）是一種「粗生成 → 細化修飾」的方法，使用 Stable Diffusion XL 生成潛空間影像，再由 Refiner 模型細化紋理與光影，提升影像品質與真實感。 ⚙️ 關鍵參數與流程說明 1️⃣ Base 模型：兩階段擴散模型的粗生成步驟 這裡： → 目的：產生一張粗略但有整體構圖的潛在影像。 2️⃣ Refiner 模型：兩階段擴散模型的細化修飾步驟 這裡： → 目的：讓影像更細膩、真實、視覺品質更高。 🧩 為什麼要分兩階段？ 這樣做的理由主要有三個： 🔍 …
Writing meeting minutes has always been a time-consuming task. Thanks to advances in AI, we can now automate the process: In this post, we’ll walk through the full workflow. Step …
Introduction In this large language model Colab tutorial, I’ll walk you through how to efficiently load and run multiple large language models (LLMs) in Hugging Face Transformers using 4-bit quantization …
![How to Run Hugging Face Models on Google Colab [Step-by-Step Guide]](https://blog.winerva.com/wp-content/uploads/2025/09/Screenshot-2025-09-18-105913-300x150.png)
Hugging Face provides a wide variety of pre-trained models for tasks like text generation, summarization, translation, and more. Google Colab, on the other hand, offers free cloud-based Jupyter notebooks with …
Introduction Mention that this blog demonstrates how to build a chatbot that can respond with text, speech, and images while remembering conversation context. Briefly introduce Agentic AI: LLMs that can …
Extending OpenAI with External Tools When working with OpenAI models, you might face situations where the model cannot directly provide real-time or domain-specific answers — such as looking up the …
Gradio is an open-source Python framework that makes it easy to build interactive web-based UIs for machine learning (ML) models, data pipelines, or any Python function. Instead of writing frontend …
You’re already familar with prompts being organized into lists like: In fact this structure can be used to reflect a longer conversation history: Import Rule: Please remember this prompt rule. …