Jongbin-kr/qwen2.5-coder-7b-verireason_sft-reasoning_official-full-ft

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 21, 2026Architecture:Transformer Featherless Exclusive Cold

Jongbin-kr/qwen2.5-coder-7b-verireason_sft-reasoning_official-full-ft is a 7.6 billion parameter language model fine-tuned from Qwen/Qwen2.5-Coder-7B-Instruct. This model has been specifically trained using Supervised Fine-Tuning (SFT) with TRL to enhance its reasoning capabilities. It is optimized for tasks requiring logical inference and problem-solving, building upon the strong coding foundation of its base model. This fine-tuned version aims to provide improved performance in complex reasoning scenarios.

Loading preview...

Model Overview

This model, Jongbin-kr/qwen2.5-coder-7b-verireason_sft-reasoning_official-full-ft, is a specialized fine-tuned version of the Qwen2.5-Coder-7B-Instruct base model, developed by Jongbin-kr. With 7.6 billion parameters and a context length of 32768 tokens, it builds upon the robust architecture of the Qwen family.

Key Capabilities

  • Enhanced Reasoning: The model has undergone Supervised Fine-Tuning (SFT) using the TRL framework, specifically targeting improved reasoning abilities. This differentiates it from its base model by focusing on logical inference and problem-solving.
  • Code-aware Foundation: Inherits the strong code understanding and generation capabilities from the Qwen2.5-Coder-7B-Instruct base model, making it suitable for tasks that combine coding with complex reasoning.
  • Fine-tuned with TRL: The training process utilized the TRL (Transformers Reinforcement Learning) library, indicating a structured approach to fine-tuning for specific performance objectives.

Use Cases

This model is particularly well-suited for applications requiring a combination of coding proficiency and advanced reasoning. Developers can leverage it for:

  • Complex Code Analysis: Tasks that involve understanding intricate code logic and deriving conclusions.
  • Automated Reasoning in Code: Generating or verifying code snippets based on logical constraints or problem descriptions.
  • Technical Problem Solving: Assisting in debugging or proposing solutions to programming challenges that demand logical thought.

For quick integration, a transformers pipeline example is provided in the model card, demonstrating how to generate text with specific user prompts.

Finetunes
1 models