g-assismoraes/DeltaP2S-Qwen2.5-14B-SameFormula-Code-S13-QV

TEXT GENERATIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:14.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 8, 2026Architecture:Transformer Featherless Exclusive Cold

DeltaP2S-Qwen2.5-14B-SameFormula-Code-S13-QV is a 14.8 billion parameter language model developed by g-assismoraes, based on the Qwen2.5-14B architecture with a 32K context length. This model is a merged checkpoint from a Qwen-aware Delta-P2S experiment, indicating specialized training. It is optimized for tasks related to its training methodology, likely focusing on code generation or understanding given its experimental origin.

Loading preview...

Overview

DeltaP2S-Qwen2.5-14B-SameFormula-Code-S13-QV is a 14.8 billion parameter language model derived from the Qwen/Qwen2.5-14B base. It is the result of a Qwen-aware Delta-P2S experiment, suggesting a specialized training approach to enhance its capabilities beyond the base model. The model supports a substantial context length of 32,768 tokens, making it suitable for processing longer sequences of text or code.

Key Capabilities

  • Qwen2.5-14B Foundation: Leverages the robust architecture and pre-training of the Qwen2.5-14B model.
  • Delta-P2S Experimentation: Incorporates specialized training from a Delta-P2S experiment, likely targeting specific performance improvements or domain adaptation.
  • Extended Context Window: Benefits from a 32K token context length, enabling deeper understanding and generation for complex tasks.

Good For

  • Research and Development: Ideal for researchers exploring the impact of Delta-P2S training methodologies on large language models.
  • Specialized Code Tasks: Given its experimental nature and potential focus, it may excel in specific code-related generation or analysis tasks.