World Wire

While recent breakthroughs in AI reasoning have largely been driven by massive scale, pouring in billions of parameters to cross complex cognitive thresholds— VibeThinker-3B is charting a completely different path. Created by researchers from Sina Weibo Inc (China), this 3-billion-parameter model proves that efficiency can punch far above its weight class. Released under an open-source MIT license, VibeThinker-3B matches the performance of models hundreds of times its size on verifiable tasks like mathematics, coding, and STEM disciplines. What is VibeThinker-3B VibeThinker-3B is a compact dense model built on the Qwen2.5-Coder-3B base. It is post-trained, not pretrained from scratch. The research team applies supervised fine-tuning, reinforcement learning, and self-distillation on top. The training framework continues the Spectrum-to-Signal Principle (SSP) from the earlier VibeThinker-1.5B. SFT (Supervised Fine-Tuning) builds a broad space of valid reasoning paths, t...

This week, Liquid AI released two new retrieval models. They are LFM2.5-ColBERT-350M and LFM2.5-Embedding-350M . Both hold 350M parameters. Both are the first bidirectional members of the LFM family. They build on LFM2.5-350M-Base , released in March. The pair targets fast multilingual and cross-lingual search across 11 languages. Their footprint is small enough to run almost anywhere. Both are available now on Hugging Face under the LFM Open License v1.0. LFM2.5 Retrievers The two models share one backbone but represent text differently. LFM2.5-Embedding-350M is a dense bi-encoder. It turns each document into a single vector. Pick it when you want the fastest search and the smallest, cheapest index. LFM2.5-ColBERT-350M is a late-interaction model. It converts each token into a vector rather than one vector per document. This lets it match queries word-by-word for higher accuracy and better generalization. The trade-off is a larger index. Pick it when accuracy matters m...

In this tutorial, we implement an end-to-end workflow for Salesforce CodeGen . We load a CodeGen model from Hugging Face, prepare it for code generation, and use it to generate Python functions from natural-language prompts. We then move beyond basic inference by adding function extraction, syntax checking, static safety checks, unit-test-based validation, best-of-N candidate reranking, multi-step program synthesis, prompt-style experimentation, benchmark visualization, and artifact export. Through this workflow, we learn how CodeGen can be used not only as a code completion model but also as part of a structured code-generation pipeline that evaluates, filters, and organizes generated solutions. Loading the Salesforce CodeGen Model from Hugging Face Copy Code Copied Use a different Browser import os, sys, subprocess, textwrap, json, re, time, math, ast, tempfile, multiprocessing as mp from pathlib import Path def sh(cmd): print(f"\n$ {cmd}") subprocess.run(cm...