ali-elganzory/Qwen3-1.7B-Base-SFT-Tulu3-decontaminated

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:Jan 17, 2026Architecture:Transformer Warm

The ali-elganzory/Qwen3-1.7B-Base-SFT-Tulu3-decontaminated model is a fine-tuned version of the Qwen3-1.7B-Base architecture, developed by ali-elganzory. This 1.7 billion parameter model has been instruction fine-tuned using the TRL framework with Supervised Fine-Tuning (SFT). It is designed for general text generation tasks, leveraging its base Qwen3 capabilities enhanced by instruction following. This model is suitable for applications requiring a compact yet capable language model for conversational or prompt-based interactions.

Loading preview...

Model Overview

This model, ali-elganzory/Qwen3-1.7B-Base-SFT-Tulu3-decontaminated, is an instruction-tuned variant of the Qwen3-1.7B-Base architecture. It was developed by ali-elganzory and fine-tuned using the TRL (Transformer Reinforcement Learning) library, specifically employing Supervised Fine-Tuning (SFT) techniques.

Key Characteristics

  • Base Model: Qwen/Qwen3-1.7B-Base, a 1.7 billion parameter model.
  • Fine-tuning Method: Supervised Fine-Tuning (SFT) using the TRL framework.
  • Training Environment: The training process was tracked and visualized using Weights & Biases.
  • Framework Versions: Utilizes TRL 0.27.0, Transformers 4.57.6, Pytorch 2.6.0+cu126, Datasets 4.5.0, and Tokenizers 0.22.2.

Intended Use Cases

This model is suitable for various text generation tasks where a compact, instruction-following language model is beneficial. Its fine-tuning aims to enhance its ability to respond to user prompts effectively, making it a good candidate for:

  • General question answering.
  • Conversational AI.
  • Text completion based on instructions.
  • Prototyping applications requiring a smaller, efficient LLM.