Компактная, но эффективная модель Granite 3.2 2B предлагает продвинутую логику в легком формате, идеально подходящем для быстрой работы. Этот AI-инструмент отлично справляется с генерацией кода, переводом и суммаризацией, поддерживая те же инновационные методы рассуждения, что и старшие версии.
The new Granite 3.2 8B Instruct and Granite 3.2 2B Instruct offer experimental chain-of-thought reasoning capabilities that significantly improve their ability to follow complex instructions with no sacrifice to general performance. The reasoning process can be toggled on and off, allowing for efficient use of computing resources. When combined with IBM’s inference scaling techniques, Granite 3.2 8B Instruct’s extended thought process enables it to meet or exceed the reasoning performance of much larger models, including GPT-4o and Claude 3.5 Sonnet. Like their predecessors, all new IBM Granite models are released open sourced under a permissive Apache 2.0 license. Granite 3.2 models are now available on IBM watsonx.ai, Hugging Face, Ollama, LMStudio, and Replicate.