Jongbin-kr/qwen2.5-coder-7b-verireason_sft-NO-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-NO-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 the TRL framework. It is designed for code-related tasks, building upon the capabilities of its base Qwen2.5-Coder architecture.

Loading preview...

Model Overview

This model, qwen2.5-coder-7b-verireason_sft-NO-reasoning_official-full-ft, is a 7.6 billion parameter language model developed by Jongbin-kr. It is a fine-tuned variant of the Qwen/Qwen2.5-Coder-7B-Instruct base model, specifically optimized through Supervised Fine-Tuning (SFT).

Key Characteristics

  • Base Model: Built upon the robust Qwen2.5-Coder-7B-Instruct architecture.
  • Training Method: Utilizes Supervised Fine-Tuning (SFT) for specialized performance.
  • Framework: Training was conducted using the TRL (Transformers Reinforcement Learning) library.
  • Context Length: Supports a context window of 32768 tokens.

Training Details

The model was trained with SFT, leveraging specific versions of key frameworks:

  • TRL: 1.6.0
  • Transformers: 5.7.0
  • Pytorch: 2.10.0+cu128
  • Datasets: 5.0.0
  • Tokenizers: 0.22.2

Use Cases

This model is suitable for applications requiring code-centric language understanding and generation, benefiting from its specialized fine-tuning on a coder-focused base model.