Coaching Gemma-3 for Structured Mathematical Reasoning with Tunix GRPO, LoRA Adapters, and GSM8K Rewards

Coaching Gemma-3 for Structured Mathematical Reasoning with Tunix GRPO, LoRA Adapters, and GSM8K Rewards

import importlib.util, os, shutil as _sh if importlib.util.find_spec(“tunix”) is None: print(“Putting in Tunix + JAX ecosystem — this takes ~5-8 min…”) %pip set up -q ipywidgets tensorboardX transformers grain nest_asyncio %pip set up -q datasets huggingface_hub “numpy>2” %pip set up -q tensorflow tensorflow_datasets %pip set up -q git+https://github.com/jax-ml/jax %pip set up -q git+https://github.com/google/tunix %pip set…

Read Full News

Meituan Releases LongCat-2.0: A 1.6T-Parameter Open MoE Model with Native 1M Context and LongCat Sparse Attention

Meituan has released LongCat-2.0, a large-scale Mixture-of-Experts (MoE) language model. It carries 1.6 trillion total parameters and activates about 48 billion per token. The model targets agentic coding: code understanding, generation, and execution inside agent workflows. Two facts stand out. First, LongCat-2.0 supports a native 1-million-token context window. Second, both training and serving ran entirely…

Read Full News

Almost 90 new unicorns have been minted so far this year — here they are

With AI igniting an investor frenzy, more startups are achieving unicorn status every month.  Using data from Crunchbase and PitchBook, TechCrunch tracked down the VC-backed startups that became unicorns in 2026. While most are AI-related, a surprising number are focused on other industries like healthcare and even a few crypto companies. This list will be updated throughout the…

Read Full News

LlamaIndex ‘legal-kb’: Agentic Retrieval over Index v2 with retrieve, find, read, and grep Tools

LlamaIndex has published legal-kb, a public reference application on GitHub. It is described as a knowledge base for legal documents, powered by LlamaIndex Index v2 (the LlamaParse Platform). The project demonstrates a pattern the team calls a Retrieval Harness for agentic retrieval. The approach differs from single-shot retrieval. Instead of one embedding search per query,…

Read Full News