IBM has launched the following technology fashions in its Granite household: Granite 3.2 8B Instruct, Granite 3.2 2B Instruct, Granite Imaginative and prescient 3.2 2B, Granite-Timeseries-TTM-R2.1, Granite-Embedding-30M-Sparse, and new mannequin sizes for Granite Guardian 3.2.
Granite 3.2 8B Instruct and Granite 3.2 2B Instruct present chain of thought reasoning that may be toggled on and off. Based on IBM, chain of thought reasoning could be highly effective, however requires important computing energy that isn’t wanted for each activity, which may result in pointless utilization.
The corporate took steps to mitigate this by permitting this characteristic to be simply turned off when it’s not wanted, and making use of Thought Desire Optimization (TPO)-based reinforcement studying, which permits it to attain larger efficiency on advanced reasoning with out compromising efficiency elsewhere, the corporate defined.
“The discharge of Granite 3.2 marks solely the start of IBM’s explorations into reasoning capabilities for enterprise fashions. A lot of our ongoing analysis goals to benefit from the inherently longer, extra strong thought means of Granite 3.2 for additional mannequin optimization,” IBM wrote in a weblog put up.
Granite Imaginative and prescient 3.2B is a brand new multimodal mannequin that was designed for doc understanding duties. Based on IBM, this mannequin matches or exceeds Llama 3.2 11B and Pixtral 12B on enterprise benchmarks together with DocVQA, ChartQA, AI2D, and OCRBench.
Granite-Timeseries-TTM-R2.1 extends the mannequin’s forecasting capabilities to now supply every day and weekly predictions. Beforehand, it solely supported forecasting for minutes and hours.
Granite-Embedding-30M-Sparse is an evolution of the Granite Embedding fashions that now has the power to study sparse embeddings, by which their embedding dimension equals their vocabulary dimension, and could be considerably quicker than dense embeddings for shorter textual content passages.
The corporate can also be releasing a 30% smaller Granite Guardian security mannequin, Granite Guardian 3.2 5B, that matches the efficiency of the earlier technology. Granite Guardian additionally has a brand new characteristic, verbalized confidence, offering a “extra nuanced danger evaluation that acknowledges ambiguity in security monitoring.”
IBM can also be releasing Granite Guardian 3.2 3B-A800M, which was created by fine-tuning the corporate’s combination of specialists (MoE) base mannequin.
All the new Granite 3.2 fashions can be found on Hugging Face underneath the Apache 2.0 license. Moreover, a few of the fashions are accessible via IBM watsonx.ai, Ollama, Replicate, and LM Studio.
