logan7000/llm-math345-gt-granite2b-endpoint

TEXT GENERATIONPricing:Input $0.32 / Cached $0.016 / Output $1.6Concurrent Unit Cost:1Model Size:2BQuant:BF16Context Size:32kPublished:Aug 25, 2026Architecture:Transformer Featherless Exclusive Cold

The q1716523669/llm-math345-gt-granite2b-endpoint model is a 2 billion parameter instruction-tuned language model based on IBM's Granite 3.3-2B-Instruct architecture. It has been fine-tuned using the GRPO method, which is designed to enhance mathematical reasoning capabilities in language models. With a context length of 32768 tokens, this model is optimized for tasks requiring advanced mathematical problem-solving and logical reasoning. Its training methodology suggests a focus on improving performance in complex quantitative domains.

Loading preview...

Model Overview

This model, q1716523669/llm-math345-gt-granite2b-endpoint, is a specialized fine-tuned version of the IBM Granite 3.3-2B-Instruct model. It leverages a 2 billion parameter architecture and supports a substantial context length of 32768 tokens, making it suitable for processing longer inputs.

Key Differentiator: GRPO Training

A core aspect of this model is its training methodology. It has been fine-tuned using GRPO (Gradient-based Reward Policy Optimization), a method introduced in the research paper "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models" (arXiv:2402.03300). This indicates a specific optimization for:

  • Enhanced Mathematical Reasoning: The GRPO method is designed to improve a model's ability to understand and solve complex mathematical problems.
  • Logical Problem Solving: By focusing on reasoning, the model is likely to perform well in tasks requiring structured thought and logical deduction.

Technical Details

Use Cases

Given its specialized training, this model is particularly well-suited for applications that require:

  • Solving mathematical word problems.
  • Assisting with quantitative analysis.
  • Tasks demanding logical inference and step-by-step reasoning.