g-assismoraes/DeltaP2S-Qwen2.5-3B-SameFormula-Code-S13

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 5, 2026Architecture:Transformer Featherless Exclusive Cold

DeltaP2S-Qwen2.5-3B-SameFormula-Code-S13 is a 3.1 billion parameter language model developed by g-assismoraes, based on the Qwen2.5 architecture. This model is a merged checkpoint from a Qwen-aware Delta-P2S experiment, specifically trained using the `Qwen/Qwen2.5-3B` base. It is designed as a large baseline model, indicating its foundational nature for further development or specific applications.

Loading preview...

Model Overview

The g-assismoraes/DeltaP2S-Qwen2.5-3B-SameFormula-Code-S13 is a 3.1 billion parameter language model derived from the Qwen2.5 architecture. It represents a merged checkpoint resulting from a Delta-P2S experiment specifically tailored for Qwen models. This particular iteration, designated as 'large-baseline', was built upon the Qwen/Qwen2.5-3B base model.

Key Characteristics

  • Base Model: Utilizes Qwen/Qwen2.5-3B as its foundational architecture.
  • Parameter Count: Features 3.1 billion parameters, offering a balance between performance and computational efficiency.
  • Development Origin: Produced through a Qwen-aware Delta-P2S experimental package, suggesting a focus on efficient fine-tuning or adaptation techniques.
  • Context Length: Supports a context window of 32768 tokens, enabling processing of longer inputs and generating more coherent extended outputs.

Potential Use Cases

This model is suitable for developers looking for:

  • A solid baseline Qwen2.5-3B variant for further fine-tuning on specific tasks.
  • Experimentation with models derived from Delta-P2S methodologies.
  • Applications requiring a capable 3B parameter model with a substantial context window.