Posts

OCRmyPDF Tutorial: Convert Scanned Documents into Searchable PDF/A Files with Sidecar Text Extraction and Batch Processing

By
Image
In this tutorial , we build an advanced, self-contained OCRmyPDF workflow. We start by installing the required system and Python dependencies, then create a synthetic image-only PDF for scanning so we can test OCR without relying on external files. From there, we use OCRmyPDF’s real public API to convert scanned documents into searchable PDFs, generate PDF/A outputs, extract sidecar text, validate the results, compare file sizes, tune Tesseract settings, clean noisy scans, handle already-OCRed files, process images with DPI hints, run OCR in memory, and batch-process multiple PDFs. Through this workflow, we understand how OCRmyPDF can serve as a practical document digitization pipeline for archival, search, extraction, and automated processing tasks. Installing OCRmyPDF System Dependencies Copy Code Copied Use a different Browser import io import os import re import sys import time import shutil import logging import textwrap import subprocess from pathlib import Path INSTAL...
Post a Comment
Read more

Building a Stable Fable 5 Traces Workflow in Colab: Parsing Tool Calls, Auditing Data, and Training Baselines

By
In this tutorial , we work with the Fable 5 Traces dataset from Hugging Face and build a complete workflow around real coding-agent trace data. We start by setting up a lightweight environment that avoids fragile dependencies such as datasets, scikit-learn, and scipy. Then we manually download and parse the merged JSONL file to keep the notebook stable in Colab. From there, we inspect repository files, preview raw trace examples, normalize tool calls and text outputs, audit the dataset structure, detect potential secret-like patterns, and visualize key distributions, including output types, tools, source roots, and text lengths. We also create safe no-CoT chat/SFT exports, build a simple keyword-search helper, and train pure-Python Naive Bayes baselines to assess whether trace context can predict the assistant’s output type and tool usage. Setting Up the Fable 5 Traces Colab Environment and Helpers Copy Code Copied Use a different Browser import os import sys import jso...
Post a Comment
Read more

Liquid AI Ships LFM2.5-230M with llama.cpp, MLX, vLLM, SGLang, and ONNX Support for On-Device Inference

By
Liquid AI shipped LFM2.5-230M , it’s the company’s smallest model to date. The release targets a specific job: running agentic tasks on phones, robots, and automation devices. Both the base and instruction-tuned checkpoints are open-weight on Hugging Face. The pitch is narrow on purpose. This is not a general reasoning model. It is built for data extraction and tool use on edge hardware. TL;DR Liquid AI’s LFM2.5-230M is its smallest model yet: 230M params, open-weight, built on LFM2. Runs on-device at 213 tok/s on a Galaxy S25 Ultra and 42 on a Raspberry Pi 5. Beats larger models (Qwen3.5-0.8B, Gemma 3 1B) on instruction following and data extraction. Tuned for tool use and extraction; not for math, code generation, or creative writing. Day-one support across llama.cpp, MLX, vLLM, SGLang, and ONNX, with a 293–375 MB footprint. What is LFM2.5-230M? LFM2.5-230M is a 230-million-parameter, text-only model. It is built on the LFM2 arc...
Post a Comment
Read more