Model Overview
Hyeongwon/P2-split2_prob_ascii_normalized_Qwen3-4B-Base_0330-01 is a 4 billion parameter language model developed by Hyeongwon. It is a fine-tuned variant of the Qwen3-4B-Base architecture, specifically trained using Supervised Fine-Tuning (SFT) with the TRL framework.
Key Capabilities
- Text Generation: The model is capable of generating coherent and contextually relevant text based on given prompts.
- Fine-tuned Performance: Benefits from SFT training, which typically enhances performance on specific tasks or domains compared to its base model.
- Large Context Window: Supports a context length of 32768 tokens, allowing it to process and generate longer sequences of text.
Training Details
This model was trained using the TRL (Transformer Reinforcement Learning) library, a framework for fine-tuning large language models. The training procedure involved Supervised Fine-Tuning (SFT), which typically uses a dataset of input-output pairs to teach the model desired behaviors. The specific versions of frameworks used include TRL 0.25.1, Transformers 4.57.3, Pytorch 2.6.0, Datasets 3.6.0, and Tokenizers 0.22.2.
Intended Use
This model is suitable for various text generation applications where a 4 billion parameter model with a substantial context window is beneficial. Developers can integrate it into their projects using the Hugging Face transformers library for tasks such as question answering, creative writing, or conversational AI.