note

【ローカルLLM】OpenThinker 7Bを使ってみた話【Ollama】

Ollamaがアップデートされ、Ollamaライブラリに新しいモデル「OpenThinker」が追加されたので使用レビューです。 OpenThinkerとは、OpenThoughts-114kというオープンソースの推論データ・セットを利用してQwen2.5をチューニングしたモデルです。Open Thoughtsデータ・セット ...
decrypt

New Open Source AI Model Rivals DeepSeek's Performance—With Far Less Training Data

Add Decrypt as your preferred source to see more of our stories on Google. A team of international researchers from leading academic institutions and tech companies upended the AI reasoning landscape ...
marktechpost

Meet OpenThinker-32B: A State-of-the-Art Open-Data Reasoning Model

Artificial intelligence has made significant strides, yet developing models capable of nuanced reasoning remains a challenge. Many existing models struggle with complex problem-solving tasks, ...
techzine

New AI model beats DeepSeek with 86% less data

OpenThinker-32B achieves groundbreaking results with only 14% of the data required by DeepSeek. It’s a win for open-source AI. A team of international researchers from leading academic institutions ...
GitHub

Questions About OpenThinker-7B Training Setup and Dataset Usage

I attempted to reproduce OpenThinker-7B by training an SFT model using the OpenThoughts-114k dataset, but I was unable to achieve the reported results. Specifically, my model obtained an lcbV2 score ...