Yale-ROSE/Qwen3-4B-sft_dataset_gpt-sft-trl-v2
Yale-ROSE/Qwen3-4B-sft_dataset_gpt-sft-trl-v2 is a 4 billion parameter language model, fine-tuned from Qwen/Qwen3-4B using Supervised Fine-Tuning (SFT) with the TRL library. This model is designed for text generation tasks, leveraging its base architecture and SFT training to produce coherent and contextually relevant responses. It is suitable for applications requiring instruction-following capabilities derived from its fine-tuning process.
Loading preview...
Overview
This model, Yale-ROSE/Qwen3-4B-sft_dataset_gpt-sft-trl-v2, is a 4 billion parameter language model built upon the Qwen3-4B architecture. It has undergone Supervised Fine-Tuning (SFT) using the Hugging Face TRL library, version 0.23.0, to enhance its instruction-following and text generation capabilities. The training process utilized specific versions of key frameworks including Transformers 4.56.1, Pytorch 2.7.1, Datasets 3.6.0, and Tokenizers 0.22.0.
Key Capabilities
- Instruction-following: Fine-tuned with SFT, enabling it to generate responses based on given prompts and instructions.
- Text Generation: Capable of producing coherent and contextually relevant text for various prompts.
- Base Model: Leverages the robust architecture of Qwen/Qwen3-4B.
Good For
- General Text Generation: Suitable for tasks requiring the creation of human-like text.
- Question Answering: Can be used to answer open-ended questions based on its training.
- Exploratory NLP Tasks: Ideal for developers experimenting with fine-tuned Qwen3-4B models for specific applications.