lhkhiem28/qwen2.5-1.5b-sft-iter3

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Oct 31, 2025Architecture:Transformer Cold

The lhkhiem28/qwen2.5-1.5b-sft-iter3 is a 1.5 billion parameter language model, fine-tuned by lhkhiem28 using TRL. This model is an iteration of lhkhiem28/qwen2.5-1.5b-sft-iter2, specifically trained with Supervised Fine-Tuning (SFT) to enhance its conversational capabilities. It is designed for general text generation tasks, particularly those requiring nuanced responses to prompts.

Loading preview...

Model Overview

The lhkhiem28/qwen2.5-1.5b-sft-iter3 is a 1.5 billion parameter language model developed by lhkhiem28. It represents an iterative improvement over its predecessor, lhkhiem28/qwen2.5-1.5b-sft-iter2, through further Supervised Fine-Tuning (SFT).

Key Capabilities

  • Text Generation: Excels at generating coherent and contextually relevant text based on user prompts.
  • Conversational AI: Fine-tuned with SFT, making it suitable for interactive dialogue and question-answering scenarios.
  • Iterative Refinement: Benefits from an iterative training process, suggesting improved performance over previous versions.

Training Details

This model was trained using the TRL (Transformer Reinforcement Learning) library, specifically employing Supervised Fine-Tuning (SFT). The training process utilized the following framework versions:

  • TRL: 0.22.2
  • Transformers: 4.57.1
  • Pytorch: 2.6.0
  • Datasets: 4.3.0
  • Tokenizers: 0.22.1

Good For

  • General Text Generation: Ideal for tasks requiring creative or informative text output.
  • Interactive Applications: Suitable for chatbots, virtual assistants, and other applications needing responsive text generation.
  • Further Fine-tuning: Can serve as a strong base model for additional domain-specific fine-tuning due to its SFT foundation.