nicar-2025-scraping/README.md at main · simonw/nicar-2025-scraping
Interested in new and effective advanced web scraping techniques? Join this session to learn about: Video scraping: a new technique where you take a screen capture video and feed it into Google's Gemini models to turn it into structured data. Using image models such as Gemini, GPT-4o and Claude 3.7 Sonnet are also extremely effective. It's possible to extract structured data from images, or poorly
Docling Technical Report
This technical report introduces Docling, an easy to use, self-contained, MIT-licensed open-source package for PDF document conversion. It is powered by state-of-the-art specialized AI models for layout analysis (DocLayNet) and table structure recognition (TableFormer), and runs efficiently on commodity hardware in a small resource budget. The code interface allows for easy extensibility and addit
LLM: A CLI utility and Python library for interacting with Large Language Models
LLM# A CLI utility and Python library for interacting with Large Language Models, both via remote APIs and models that can be installed and run on your own machine. Run prompts from the command-line, store the results in SQLite, generate embeddings and more. Here’s a YouTube video demo and accompanying detailed notes. Background on this project: llm, ttok and strip-tags—CLI tools for working with
Metaがコード生成AIモデルの新バージョン「Code Llama 70B」をリリース、コードの正確性が向上・Pythonに最適化されたバリアントも提供
FacebookやInstagramを運営するMetaが、テキスト入力を元にプログラムのコードを生成するAI「Code Llama」の700億パラメータのモデルをリリースしたと発表しました。モデルはLlama 2と同じ「Llama 2 Community License」で公開されており、月間アクティブユーザー数が7億人以下の場合は無償で商用利用することが可能です。 Introducing Code Llama, a state-of-the-art large language model for coding https://ai.meta.com/blog/code-llama-large-language-model-coding/ Code LlamaはMetaが2023年7月にリリースしたLlama 2をコード固有のデータセットでさらにトレーニングしたもの。Python、C++
LMQL is a programming language for LLM interaction. | LMQL
LMQL is a programming language for LLMs. Robust and modular LLM prompting using types, templates, constraints and an optimizing runtime. @lmql.query def meaning_of_life(): '''lmql # top-level strings are prompts "Q: What is the answer to life, the \ universe and everything?" # generation via (constrained) variables "A: [ANSWER]" where \ len(ANSWER) < 120 and STOPS_AT(ANSWER, ".") # results are dir
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
