Overview
This model, PetarKal/Qwen3-4B-Base-ascii-art-v5dd-e3-lr5e-5-ga16-ctx4096, is a 4 billion parameter language model derived from the Qwen3-4B-Base architecture. It has been fine-tuned by PetarKal using the TRL (Transformers Reinforcement Learning) framework, specifically employing Supervised Fine-Tuning (SFT).
Key Capabilities
- Text Generation: Capable of generating coherent and contextually relevant text based on provided prompts.
- Base Model: Built upon the robust Qwen3-4B-Base, suggesting strong general language understanding.
- Fine-tuned Performance: The SFT process aims to enhance specific aspects of text generation, though the exact focus (e.g., style, domain) is not explicitly detailed beyond the 'ascii-art' in the model name, which might imply a specialization in creative text or specific formatting.
Training Details
The model was trained using SFT, leveraging TRL version 0.29.1, Transformers 5.3.0, Pytorch 2.5.1, Datasets 4.8.4, and Tokenizers 0.22.2. It supports a context length of 32768 tokens, allowing for processing and generating longer sequences of text.
Good for
- Developers looking for a fine-tuned Qwen3-4B-Base variant.
- Applications requiring text generation with a potentially specialized output style, possibly related to creative text or formatted content, as hinted by the model's name.