anujjamwal/OpenMath-Nemotron-1.5B-hcot-archive

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Feb 25, 2026Architecture:Transformer Cold

anujjamwal/OpenMath-Nemotron-1.5B-hcot-archive is a 1.5 billion parameter language model fine-tuned from nvidia/OpenMath-Nemotron-1.5B, featuring a 32768 token context length. This model was trained using Supervised Fine-Tuning (SFT) with the TRL framework. It is designed for text generation tasks, building upon the mathematical reasoning capabilities of its base model.

Loading preview...

Model Overview

anujjamwal/OpenMath-Nemotron-1.5B-hcot-archive is a 1.5 billion parameter language model, fine-tuned from the nvidia/OpenMath-Nemotron-1.5B base model. It leverages a substantial 32768 token context window, making it suitable for processing longer inputs and generating coherent, extended responses. The model was developed using the TRL (Transformers Reinforcement Learning) framework, specifically through a Supervised Fine-Tuning (SFT) procedure.

Key Capabilities

  • Text Generation: Excels at generating human-like text based on given prompts.
  • Extended Context Handling: Benefits from a 32768 token context length, allowing for more complex and detailed interactions.
  • Fine-tuned Performance: Built upon nvidia/OpenMath-Nemotron-1.5B, suggesting potential strengths in areas related to the base model's focus, such as mathematical reasoning.

Training Details

The model underwent Supervised Fine-Tuning (SFT) using the TRL library (version 0.29.0). The training environment included Transformers 5.0.0, Pytorch 2.10.0+cu128, Datasets 4.0.0, and Tokenizers 0.22.2.

Good For

  • Applications requiring robust text generation.
  • Scenarios where a large context window is beneficial for understanding and generating detailed content.
  • Further research and development in fine-tuning language models for specific tasks.