Lansechen/Qwen2.5-7B-Open-R1-Distill

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Feb 12, 2025Architecture:Transformer Featherless Exclusive Cold

Lansechen/Qwen2.5-7B-Open-R1-Distill is a 7.6 billion parameter language model, fine-tuned from Qwen/Qwen2.5-7B-Instruct. This model was trained using SFT on the HuggingFaceH4/Bespoke-Stratos-17k dataset, leveraging TRL for its training procedure. It is designed for general text generation tasks, offering a 32K context length for processing longer inputs.

Loading preview...

Overview

Lansechen/Qwen2.5-7B-Open-R1-Distill is a 7.6 billion parameter language model derived from the Qwen2.5-7B-Instruct architecture. It has been specifically fine-tuned using Supervised Fine-Tuning (SFT) on the HuggingFaceH4/Bespoke-Stratos-17k dataset with the TRL library.

Key Capabilities

  • Instruction Following: As a fine-tuned instruct model, it is optimized to follow user instructions for various text generation tasks.
  • Text Generation: Capable of generating coherent and contextually relevant text based on prompts.
  • Context Handling: Supports a substantial context length of 32,768 tokens, allowing for processing and generating longer sequences.

Training Details

The model's training procedure involved SFT, utilizing specific versions of popular machine learning frameworks:

  • TRL: 0.15.0.dev0
  • Transformers: 4.49.0.dev0
  • Pytorch: 2.5.1+cu121
  • Datasets: 3.2.0
  • Tokenizers: 0.21.0

Good For

  • Developers looking for a Qwen2.5-7B-Instruct variant fine-tuned on a specific dataset.
  • Applications requiring general-purpose text generation with good instruction-following capabilities.
  • Use cases benefiting from a 32K token context window for more extensive input processing.