Thrillcrazyer/Qwen-1.5B_THIP_1125

Hugging Face
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Nov 25, 2025Architecture:Transformer Featherless Exclusive Warm

Thrillcrazyer/Qwen-1.5B_THIP_1125 is a 1.5 billion parameter causal language model, fine-tuned from DeepSeek-R1-Distill-Qwen-1.5B. This model specializes in mathematical reasoning, having been trained on the DeepMath-103k dataset using the GRPO method. It is optimized for tasks requiring strong mathematical problem-solving capabilities.

Loading preview...

Model Overview

Thrillcrazyer/Qwen-1.5B_THIP_1125 is a 1.5 billion parameter language model derived from the DeepSeek-R1-Distill-Qwen-1.5B architecture. Its primary distinction lies in its specialized training for mathematical reasoning tasks.

Key Capabilities

  • Mathematical Reasoning: The model has been fine-tuned specifically on the DeepMath-103k dataset, enhancing its ability to process and solve mathematical problems.
  • GRPO Training Method: It leverages the GRPO (Guided Reasoning Policy Optimization) method, as introduced in the paper "DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models" (arXiv:2402.03300), to improve its mathematical problem-solving proficiency.
  • Efficient Fine-tuning: The model was trained using the TRL (Transformer Reinforcement Learning) library, indicating an efficient fine-tuning process.

When to Use This Model

This model is particularly well-suited for applications requiring robust mathematical reasoning. Developers should consider using Thrillcrazyer/Qwen-1.5B_THIP_1125 for tasks such as:

  • Solving mathematical equations and word problems.
  • Assisting in educational tools focused on mathematics.
  • Generating explanations for mathematical concepts.

Its specialized training makes it a strong candidate for scenarios where accurate and logical mathematical processing is crucial, differentiating it from general-purpose LLMs.