2.5B model, offline, solving a puzzle it first called impossible. MiniCPM5 2B from @OpenBMB. 128K context, top open model under 4B when it landed. Searched Hugging Face inside the RunAnywhere app, downloaded, ran.

Reasoning from scratch round 3: This time, I cover generating a verifier for... a) ...evaluation (base model versus any future model improvement) b) ...the reinforcement learning with verifiable rewards (RLVR) training later on 00:00 Introduction 01:21 Four approaches to LLM evaluation 07:20 Verifiers and reinforcement learning with verifiable rewards 10:52 Notebook setup and dependencies 13:43 Section 3.1 Building a math verifier 18:57 Section 3.2 Loading a pre-trained model to generate text 24:34 Generating and displaying model answers 29:23 Section 3.3 Implementing a wrapper for easier text generation 34:00 Section 3.4 Extracting the final answer box 37:29 Handling answers without boxes 43:17 Section 3.5 Normalizing the extracted answer 46:56 Section 3.6 Verifying mathematical equivalence 53:32 Implementing the equality check 57:48 Section 3.7 Grading answers 59:20 Building and testing the answer grader 1:03:18 Section 3.8 Loading the evaluation dataset (MATH-500) 1:07:51 Section 3.9 Evaluating the model 1:08:34 Prompt templates for evaluation 1:10:47 Prompt sensitivity and memorization 1:13:55 A minimal evaluation example 1:15:32 Building the evaluation loop 1:20:27 Comparing CPU, MPS, and CUDA results 1:21:54 Reproducibility and floating-point math 1:23:37 Base model vs. reasoning model 1:25:30 Summary and next steps

Use code CODEAGENT for 15% off AI Engineering Buildcamp. The next cohort starts September 21. What you'll build: -> Documentation RAG agents with structured outputs -> Tool-using agents with function calling -> Multi-agent architectures and orchestrators -> Production systems with testing, evaluation, and monitoring -> Complete AI application as your portfolio project The course is project-driven. You learn by building real systems end-to-end. You'll work with PydanticAI, OpenAI Agents SDK, and other frameworks to understand different approaches. By the end, you'll have: 1. 9 core projects demonstrating agent design patterns 2. A full capstone project with evaluation and observability 3. Experience testing and deploying AI systems to production Register here: maven.com/alexey-grigorev/fr…

Accelerating genomic discovery with Google Antigravity 🧬🚀. We’ve integrated the new AlphaGenome Atlas Skill into our scientific workbench. Watch researchers Natasha and Kyle use AI agents to quickly prioritize variants and generate structural plots and build testable hypotheses. Start optimising your workflows today

Introducing Muse, a personal agent that gets things done for you, powered by Muse Spark 1.3. Get an inside look at how we built Muse and what it can do for you: introducing.muse.ai/

We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics. The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra. The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.

Fine-tuning turns a general LLM into a reliable specialist for your particular domain and tasks. And in this course, Tatev teaches you how to fine-tune your LLMs. You'll learn what fine-tuning means, different methods, how to work with massive models on your home workstation, and more. freecodecamp.org/news/how-to…

🚀 Meet MiniCPM5-2B, a 2B-parameter language model bringing high intelligence density to the edge, now open source! It ranks #1 among open-source models under 4B parameters on the @ArtificialAnlys Intelligence Index, with a score of 23. It also scores 20 on the Agentic Index, bringing an early form of general-purpose agent capability to the edge. Across 34 benchmarks, MiniCPM5-2B achieves an average score of 53.9, covering coding, math, long-context understanding, tool use, and agentic tasks. And this release goes beyond the model itself. We’re opening up the data, training recipes, and RL stack behind MiniCPM5-2B. 🤗 Hugging Face: huggingface.co/openbmb/MiniC… 💻 GitHub: github.com/OpenBMB/MiniCPM Modelscope: modelscope.cn/models/OpenBMB… Web: openbmb.cn/