PetarKal/Qwen3-4B-Base-ascii-art-v6-phase2-generation
PetarKal/Qwen3-4B-Base-ascii-art-v6-phase2-generation is a 4 billion parameter language model, fine-tuned by PetarKal, building upon the Qwen3-4B-Base architecture. This model is specifically optimized for text generation tasks, having undergone a second phase of training using SFT with the TRL framework. It is designed to generate coherent and contextually relevant text, making it suitable for various generative AI applications.
Loading preview...
Model Overview
PetarKal/Qwen3-4B-Base-ascii-art-v6-phase2-generation is a 4 billion parameter language model developed by PetarKal. It represents the second phase of fine-tuning, building upon the previously established PetarKal/Qwen3-4B-Base-ascii-art-v6-phase1-understanding model. This iteration focuses specifically on enhancing text generation capabilities.
Key Characteristics
- Base Architecture: Utilizes the Qwen3-4B-Base architecture.
- Fine-tuning: Underwent a second phase of fine-tuning using Supervised Fine-Tuning (SFT) with the TRL library.
- Parameter Count: Features 4 billion parameters, offering a balance between performance and computational efficiency.
- Context Length: Supports a context length of 32768 tokens.
Training Details
The model was trained using the TRL framework, with specific versions including TRL 0.29.1, Transformers 5.5.0, Pytorch 2.10.0, Datasets 4.8.4, and Tokenizers 0.22.2. The training process was monitored and can be visualized via Weights & Biases.
Use Cases
This model is particularly well-suited for:
- Text Generation: Creating new text based on given prompts or contexts.
- Conversational AI: Generating responses in dialogue systems.
- Creative Writing: Assisting with generating stories, poems, or other creative content.
It is a generative model, distinct from its 'understanding' predecessor, and should be considered for tasks requiring robust text output.