ForSureTesterSim/merge-test-1-golden-triangle

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 20, 2026Architecture:Transformer Featherless Exclusive Cold

ForSureTesterSim/merge-test-1-golden-triangle is a 1.5 billion parameter language model created by ForSureTesterSim using the DELLA merge method. It combines DeepSeek-R1-Distill-Qwen-1.5B with specialized models for mathematics and coding, leveraging a 32768-token context length. This model is designed to enhance performance in mathematical reasoning and code generation tasks through its unique merged architecture.

Loading preview...

Model Overview

ForSureTesterSim/merge-test-1-golden-triangle is a 1.5 billion parameter language model developed by ForSureTesterSim. It was created using the DELLA merge method with deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B as its base model. The merging process integrated several specialized models to combine their strengths.

Key Capabilities

This model is a composite of three distinct models, suggesting a focus on diverse capabilities:

  • Mathematical Reasoning: Incorporates RLinf/RLinf-math-1.5B, indicating enhanced performance in mathematical problem-solving and understanding.
  • Code Generation: Includes agentica-org/DeepCoder-1.5B-Preview, suggesting proficiency in generating and understanding code.
  • General Language Understanding: Built upon a DeepSeek-R1-Distill-Qwen base, providing a strong foundation in general language tasks.

When to Use This Model

This model is particularly well-suited for use cases requiring a combination of:

  • Mathematical computations and problem-solving.
  • Code generation, completion, or analysis.
  • Tasks benefiting from a broad language understanding combined with specialized reasoning abilities.

The DELLA merge method, with specific weight, density, and epsilon parameters for each merged component, aims to optimize the integration of these diverse capabilities into a single, efficient 1.5B parameter model with a 32768-token context length.