g-assismoraes/DeltaP2S-Qwen2.5-3B-DeltaP2S-QwenCoder1.5B-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 6, 2026Architecture:Transformer Featherless Exclusive Cold

DeltaP2S-Qwen2.5-3B-DeltaP2S-QwenCoder1.5B-Code-S13 is a 3.1 billion parameter language model developed by g-assismoraes, created by merging a Qwen2.5 checkpoint with a QwenCoder1.5B model using the Delta-P2S experiment package. This model is specifically designed for code-related tasks, leveraging the strengths of both Qwen2.5 and QwenCoder1.5B architectures. Its primary differentiation lies in its specialized merge process, aiming to enhance code generation and understanding capabilities.

Loading preview...

Model Overview

This model, named DeltaP2S-Qwen2.5-3B-DeltaP2S-QwenCoder1.5B-Code-S13, is a 3.1 billion parameter language model developed by g-assismoraes. It is a merged checkpoint produced through the Qwen-aware Delta-P2S experiment package, combining a Qwen2.5 base with a QwenCoder1.5B model.

Key Characteristics

  • Architecture: Merged Qwen2.5 and QwenCoder1.5B checkpoints.
  • Parameter Count: 3.1 billion parameters.
  • Context Length: Supports a context length of 32768 tokens.
  • Development Method: Utilizes the Delta-P2S experiment package for checkpoint merging.

Primary Focus

This model is specifically engineered for code-related tasks, integrating the capabilities of a general-purpose language model (Qwen2.5) with a code-focused model (QwenCoder1.5B). The Delta-P2S merging process aims to create a specialized model that excels in code generation, comprehension, and other programming-centric applications.

Finetunes
1 models